Compare commits

...

1049 Commits

Author SHA1 Message Date
Brandon Hancock
51c17c763b drop record new episodes 2025-01-02 16:03:51 -05:00
Brandon Hancock
e5ee91fcd1 final clean up 2025-01-02 15:55:39 -05:00
Brandon Hancock
b5ec0ed8b1 Fixing tests 2025-01-02 15:51:23 -05:00
Brandon Hancock
767aeb5913 drop large file 2025-01-02 15:31:16 -05:00
Brandon Hancock
1d3b4fde04 fix tets 2025-01-02 15:24:57 -05:00
Brandon Hancock
9429253ac2 more test fixes 2025-01-02 15:18:43 -05:00
Brandon Hancock
0545294a27 sync packages with uv.lock 2025-01-02 15:07:23 -05:00
Brandon Hancock
a60c66a9af sync packages with uv.lock 2025-01-02 15:07:23 -05:00
Brandon Hancock
217ba655c7 Update llama3 cassettes 2025-01-02 14:56:03 -05:00
Brandon Hancock
8535c0c759 Update llama3 cassettes 2025-01-02 14:56:03 -05:00
Brandon Hancock
0088d6d397 Reverting uv.lock and pyproject 2025-01-02 14:44:37 -05:00
Brandon Hancock
98be37c18a Reverting uv.lock and pyproject 2025-01-02 14:44:37 -05:00
Brandon Hancock
54316109d5 more test changes 2025-01-02 14:34:18 -05:00
Brandon Hancock
e05cde0b46 more test changes 2025-01-02 14:34:18 -05:00
Brandon Hancock
db61f5dd59 tests should work now 2025-01-02 14:18:11 -05:00
Brandon Hancock
8c175b8333 tests should work now 2025-01-02 14:18:11 -05:00
Brandon Hancock
11ff8270ea add back in crewai tool dependencies and drop litellm version 2025-01-02 11:42:47 -05:00
Brandon Hancock
6ba36a3485 add back in crewai tool dependencies and drop litellm version 2025-01-02 11:42:47 -05:00
Brandon Hancock
9d4d4d495a revert uv.lock 2025-01-02 11:22:30 -05:00
Brandon Hancock
1237c05aee revert uv.lock 2025-01-02 11:22:30 -05:00
Brandon Hancock
640e68100c crew_test changes werent applied 2025-01-02 11:15:09 -05:00
Brandon Hancock
8569c2d254 crew_test changes werent applied 2025-01-02 11:15:09 -05:00
Brandon Hancock
ab93fdd348 more timeouts 2025-01-02 11:08:51 -05:00
Brandon Hancock
5fd01292b8 more timeouts 2025-01-02 11:08:51 -05:00
Brandon Hancock
e7696f9b07 timeout in crew_tests 2025-01-02 10:23:13 -05:00
Brandon Hancock
16d4bc1f56 timeout in crew_tests 2025-01-02 10:23:13 -05:00
Brandon Hancock
50efccd20b trying next crew_test timeout 2025-01-02 10:03:56 -05:00
Brandon Hancock
fbc7230859 trying next crew_test timeout 2025-01-02 10:03:56 -05:00
Brandon Hancock
d44eb89b7e Trying out timeouts 2025-01-02 09:56:31 -05:00
Brandon Hancock
e041103c04 Trying out timeouts 2025-01-02 09:56:31 -05:00
Brandon Hancock (bhancock_ai)
6cae5fd34b Suppressed userWarnings from litellm pydantic issues (#1833)
* Suppressed userWarnings from litellm pydantic issues

* change litellm version

* Fix failling ollama tasks
2024-12-31 18:40:51 -03:00
devin-ai-integration[bot]
31f595197b fix: Include agent knowledge in planning process (#1818)
* test: Add test demonstrating knowledge not included in planning process

Issue #1703: Add test to verify that agent knowledge sources are not currently
included in the planning process. This test will help validate the fix once
implemented.

- Creates agent with knowledge sources
- Verifies knowledge context missing from planning
- Checks other expected components are present

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Include agent knowledge in planning process

Issue #1703: Integrate agent knowledge sources into planning summaries
- Add agent_knowledge field to task summaries in planning_handler
- Update test to verify knowledge inclusion
- Ensure knowledge context is available during planning phase

The planning agent now has access to agent knowledge when creating
task execution plans, allowing for better informed planning decisions.

Co-Authored-By: Joe Moura <joao@crewai.com>

* style: Fix import sorting in test_knowledge_planning.py

- Reorganize imports according to ruff linting rules
- Fix I001 linting error

Co-Authored-By: Joe Moura <joao@crewai.com>

* test: Update task summary assertions to include knowledge field

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Update ChromaDB mock path and fix knowledge string formatting

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Improve knowledge integration in planning process with error handling

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Update task summary format for empty tools and knowledge

- Change empty tools message to 'agent has no tools'
- Remove agent_knowledge field when empty
- Update test assertions to match new format
- Improve test messages for clarity

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Update string formatting for agent tools in task summary

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Update string formatting for agent tools in task summary

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Update string formatting for agent tools and knowledge in task summary

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Update knowledge field formatting in task summary

Co-Authored-By: Joe Moura <joao@crewai.com>

* style: Fix import sorting in test_planning_handler.py

Co-Authored-By: Joe Moura <joao@crewai.com>

* style: Fix import sorting order in test_planning_handler.py

Co-Authored-By: Joe Moura <joao@crewai.com>

* test: Add ChromaDB mocking to test_create_tasks_summary_with_knowledge_and_tools

Co-Authored-By: Joe Moura <joao@crewai.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-12-31 01:56:38 -03:00
Marco Vinciguerra
714134e8d3 feat: add docstring (#1819)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-12-31 01:51:43 -03:00
devin-ai-integration[bot]
f53b7f463c Docstring, Error Handling, and Type Hints Improvements (#1828)
* docs: add comprehensive docstrings to Flow class and methods

- Added NumPy-style docstrings to all decorator functions
- Added detailed documentation to Flow class methods
- Included parameter types, return types, and examples
- Enhanced documentation clarity and completeness

Co-Authored-By: Joe Moura <joao@crewai.com>

* feat: add secure path handling utilities

- Add path_utils.py with safe path handling functions
- Implement path validation and security checks
- Integrate secure path handling in flow_visualizer.py
- Add path validation in html_template_handler.py
- Add comprehensive error handling for path operations

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: add comprehensive docstrings and type hints to flow utils (#1819)

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: add type annotations and fix import sorting

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: add type annotations to flow utils and visualization utils

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: resolve import sorting and type annotation issues

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: properly initialize and update edge_smooth variable

Co-Authored-By: Joe Moura <joao@crewai.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
2024-12-31 01:39:19 -03:00
devin-ai-integration[bot]
a7b00cee08 fix: add tiktoken as explicit dependency and document Rust requirement (#1826)
* feat: add tiktoken as explicit dependency and document Rust requirement

- Add tiktoken>=0.8.0 as explicit dependency to ensure pre-built wheels are used
- Document Rust compiler requirement as fallback in README.md
- Addresses issue #1824 tiktoken build failure

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: adjust tiktoken version to ~=0.7.0 for dependency compatibility

- Update tiktoken dependency to ~=0.7.0 to resolve conflict with embedchain
- Maintain compatibility with crewai-tools dependency chain
- Addresses CI build failures

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: add troubleshooting section and make tiktoken optional

Co-Authored-By: Joe Moura <joao@crewai.com>

* Update README.md

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-12-30 17:10:56 -03:00
devin-ai-integration[bot]
cac69e90fa fix(manager_llm): handle coworker role name case/whitespace properly (#1820)
* fix(manager_llm): handle coworker role name case/whitespace properly

- Add .strip() to agent name and role comparisons in base_agent_tools.py
- Add test case for varied role name cases and whitespace
- Fix issue #1503 with manager LLM delegation

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix(manager_llm): improve error handling and add debug logging

- Add debug logging for better observability
- Add sanitize_agent_name helper method
- Enhance error messages with more context
- Add parameterized tests for edge cases:
  - Embedded quotes
  - Trailing newlines
  - Multiple whitespace
  - Case variations
  - None values
- Improve error handling with specific exceptions

Co-Authored-By: Joe Moura <joao@crewai.com>

* style: fix import sorting in base_agent_tools and test_manager_llm_delegation

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix(manager_llm): improve whitespace normalization in role name matching

Co-Authored-By: Joe Moura <joao@crewai.com>

* style: fix import sorting in base_agent_tools and test_manager_llm_delegation

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix(manager_llm): add error message template for agent tool execution errors

Co-Authored-By: Joe Moura <joao@crewai.com>

* style: fix import sorting in test_manager_llm_delegation.py

Co-Authored-By: Joe Moura <joao@crewai.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
2024-12-30 16:58:18 -03:00
devin-ai-integration[bot]
3731a8c083 Fix interpolation for output_file in Task (#1803) (#1814)
* fix: interpolate output_file attribute from YAML

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: add security validation for output_file paths

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: add _original_output_file private attribute to fix type-checker error

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: update interpolate_only to handle None inputs and remove duplicate attribute

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: improve output_file validation and error messages

Co-Authored-By: Joe Moura <joao@crewai.com>

* test: add end-to-end tests for output_file functionality

Co-Authored-By: Joe Moura <joao@crewai.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
2024-12-29 01:57:59 -03:00
João Moura
d993b5133c fixing file paths for knowledge source 2024-12-28 02:05:19 -03:00
devin-ai-integration[bot]
289b56e122 docs: add agent-specific knowledge documentation and examples (#1811)
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
2024-12-28 01:48:51 -03:00
João Moura
2576037cfb Update README.md 2024-12-28 01:03:33 -03:00
devin-ai-integration[bot]
755722fa4c docs: update README to highlight Flows (#1809)
* docs: highlight Flows feature in README

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: enhance README with LangGraph comparison and flows-crews synergy

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: replace initial Flow example with advanced Flow+Crew example; enhance LangGraph comparison

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: incorporate key terms and enhance feature descriptions

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: refine technical language, enhance feature descriptions, fix string interpolation

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: update README with performance metrics, feature enhancements, and course links

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: update LangGraph comparison with paragraph and P.S. section

Co-Authored-By: Joe Moura <joao@crewai.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
2024-12-28 01:00:58 -03:00
devin-ai-integration[bot]
49ad4bc63e fix: handle optional storage with null checks (#1808)
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-12-27 21:30:39 -03:00
Erick Amorim
1bc914edf4 fix: Change storage initialization to None for KnowledgeStorage (#1804)
* fix: Change storage initialization to None for KnowledgeStorage

* refactor: Change storage field to optional and improve error handling when saving documents

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-12-27 21:18:25 -03:00
siddharth Sambharia
40173c2f53 Portkey Integration with CrewAI (#1233)
* Create Portkey-Observability-and-Guardrails.md

* crewAI update with new changes

* small change

---------

Co-authored-by: siddharthsambharia-portkey <siddhath.s@portkey.ai>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-12-27 18:16:47 -03:00
devin-ai-integration[bot]
1c90f02984 docs: add guide for multimodal agents (#1807)
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
2024-12-27 18:16:02 -03:00
João Igor
f6f5f3db4f chore: removing crewai-tools from dev-dependencies (#1760)
As mentioned in issue #1759, listing crewai-tools as dev-dependencies makes pip install it a required dependency, and not an optional

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-12-27 17:45:06 -03:00
João Moura
0006fdb655 Adding Multimodal Abilities to Crew (#1805)
* initial fix on delegation tools

* fixing tests for delegations and coding

* Refactor prepare tool and adding initial add images logic

* supporting image tool

* fixing linter

* fix linter

* Making sure multimodal feature support i18n

* fix linter and types

* mixxing translations

* fix types and linter

* Revert "fixing linter"

This reverts commit ef323e3487e62ee4f5bce7f86378068a5ac77e16.

* fix linters

* test

* fix

* fix

* fix linter

* fix

* ignore

* type improvements
2024-12-27 17:03:35 -03:00
Brandon Hancock (bhancock_ai)
1aa6cfdf2d Feat/joao flow improvement requests (#1795)
* Add in or and and in router

* In the middle of improving plotting

* final plot changes

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-12-24 18:55:44 -03:00
Lorenze Jay
a8e0836add removed some redundancies (#1796)
* removed some redundancies

* cleanup
2024-12-23 13:54:16 -05:00
Lorenze Jay
a8ffb60928 Feat/docling-support (#1763)
* added tool for docling support

* docling support installation

* use file_paths instead of file_path

* fix import

* organized imports

* run_type docs

* needs to be list

* fixed logic

* logged but file_path is backwards compatible

* use file_paths instead of file_path 2

* added test for multiple sources for file_paths

* fix run-types

* enabling local files to work and type cleanup

* linted

* fix test and types

* fixed run types

* fix types

* renamed to CrewDoclingSource

* linted

* added docs

* resolve conflicts

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2024-12-23 13:19:58 -05:00
devin-ai-integration[bot]
764eac12e4 feat: Add interpolate_only method and improve error handling (#1791)
* Fixed output_file not respecting system path

* Fixed yaml config is not escaped properly for output requirements

* feat: Add interpolate_only method and improve error handling

- Add interpolate_only method for string interpolation while preserving JSON structure
- Add comprehensive test coverage for interpolate_only
- Add proper type annotation for logger using ClassVar
- Improve error handling and documentation for _save_file method

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Sort imports to fix lint issues

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Reorganize imports using ruff --fix

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Consolidate imports and fix formatting

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Apply ruff automatic import sorting

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Sort imports using ruff --fix

Co-Authored-By: Joe Moura <joao@crewai.com>

---------

Co-authored-by: Frieda (Jingying) Huang <jingyingfhuang@gmail.com>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Frieda Huang <124417784+frieda-huang@users.noreply.github.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
2024-12-23 13:05:29 -05:00
devin-ai-integration[bot]
8c53880dca feat: Add task guardrails feature (#1742)
* feat: Add task guardrails feature

Add support for custom code guardrails in tasks that validate outputs
before proceeding to the next task. Features include:

- Optional task-level guardrail function
- Pre-next-task execution timing
- Tuple return format (success, data)
- Automatic result/error routing
- Configurable retry mechanism
- Comprehensive documentation and tests

Link to Devin run: https://app.devin.ai/sessions/39f6cfd6c5a24d25a7bd70ce070ed29a

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Add type check for guardrail result and remove unused import

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Remove unnecessary f-string prefix

Co-Authored-By: Joe Moura <joao@crewai.com>

* feat: Add guardrail validation improvements

- Add result/error exclusivity validation in GuardrailResult
- Make return type annotations optional in Task guardrail validator
- Improve error messages for validation failures

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: Add comprehensive guardrails documentation

- Add type hints and examples
- Add error handling best practices
- Add structured error response patterns
- Document retry mechanisms
- Improve documentation organization

Co-Authored-By: Joe Moura <joao@crewai.com>

* refactor: Update guardrail functions to handle TaskOutput objects

Co-Authored-By: Joe Moura <joao@crewai.com>

* feat: Add task guardrails feature

Add support for custom code guardrails in tasks that validate outputs
before proceeding to the next task. Features include:

- Optional task-level guardrail function
- Pre-next-task execution timing
- Tuple return format (success, data)
- Automatic result/error routing
- Configurable retry mechanism
- Comprehensive documentation and tests

Link to Devin run: https://app.devin.ai/sessions/39f6cfd6c5a24d25a7bd70ce070ed29a

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Add type check for guardrail result and remove unused import

Co-Authored-By: Joe Moura <joao@crewai.com>

* fix: Remove unnecessary f-string prefix

Co-Authored-By: Joe Moura <joao@crewai.com>

* feat: Add guardrail validation improvements

- Add result/error exclusivity validation in GuardrailResult
- Make return type annotations optional in Task guardrail validator
- Improve error messages for validation failures

Co-Authored-By: Joe Moura <joao@crewai.com>

* docs: Add comprehensive guardrails documentation

- Add type hints and examples
- Add error handling best practices
- Add structured error response patterns
- Document retry mechanisms
- Improve documentation organization

Co-Authored-By: Joe Moura <joao@crewai.com>

* refactor: Update guardrail functions to handle TaskOutput objects

Co-Authored-By: Joe Moura <joao@crewai.com>

* style: Fix import sorting in task guardrails files

Co-Authored-By: Joe Moura <joao@crewai.com>

* fixing docs

* Fixing guardarils implementation

* docs: Enhance guardrail validator docstring with runtime validation rationale

Co-Authored-By: Joe Moura <joao@crewai.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-12-22 00:52:02 -03:00
PJ
757bfe07aa Correcting a small grammatical issue that was bugging me: from _satisfy the expect criteria_ to _satisfies the expected criteria_ (#1783)
Signed-off-by: PJ Hagerty <pjhagerty@gmail.com>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-20 10:17:34 -05:00
Vini Brasil
0487a0e8fb Add tool.crewai.type pyproject attribute in templates (#1789) 2024-12-20 10:36:18 -03:00
Vini Brasil
7f357d2696 Remove relative import in flow main.py template (#1782) 2024-12-18 10:47:44 -03:00
alan blount
08f252c49b Gemini 2.0 (#1773)
* Update llms.mdx (Gemini 2.0)

- Add Gemini 2.0 flash to Gemini table.
- Add link to 2 hosting paths for Gemini in Tip.
- Change to lower case model slugs vs names, user convenience.
- Add https://artificialanalysis.ai/ as alternate leaderboard.
- Move Gemma to "other" tab.

* Update llm.py (gemini 2.0)

Add setting for Gemini 2.0 context window to llm.py

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-17 16:44:10 -05:00
Tony Kipkemboi
6ff669e5da Merge pull request #1777 from crewAIInc/fix/python-max-version
Fix/python max version
2024-12-17 16:09:44 -05:00
Brandon Hancock
791d156dce change to <13 instead of <=12 2024-12-17 16:00:15 -05:00
Brandon Hancock
1d98a83296 include 12 but not 13 2024-12-17 15:29:11 -05:00
Karan Vaidya
9ecc534f8d Fix bool and null handling (#1771) 2024-12-16 16:23:53 -05:00
Shahar Yair
497724f3a4 Fix: CrewJSONEncoder now accepts enums (#1752)
* bugfix: CrewJSONEncoder now accepts enums

* sort imports

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-12 15:13:10 -05:00
Brandon Hancock (bhancock_ai)
2f4681e110 drop print (#1755) 2024-12-12 15:08:37 -05:00
Brandon Hancock (bhancock_ai)
49c02d06c3 apply agent ops changes and resolve merge conflicts (#1748)
* apply agent ops changes and resolve merge conflicts

* Trying to fix tests

* add back in vcr

* update tools

* remove pkg_resources which was causing issues

* Fix tests

* experimenting to see if unique content is an issue with knowledge

* experimenting to see if unique content is an issue with knowledge

* update chromadb which seems to have issues with upsert

* generate new yaml for failing test

* Investigating upsert

* Drop patch

* Update casettes

* Fix duplicate document issue

* more fixes

* add back in vcr

* new cassette for test

---------

Co-authored-by: Lorenze Jay <lorenzejaytech@gmail.com>
2024-12-12 15:04:32 -05:00
Brandon Hancock (bhancock_ai)
6738a02b8b remove pkg_resources which was causing issues (#1751) 2024-12-12 12:41:13 -05:00
Rip&Tear
ec6981d8d3 Feature/add workflow permissions (#1749)
* fix: Call ChromaDB reset before removing storage directory to fix disk I/O errors

* feat: add workflow permissions to stale.yml

* revert rag_storage.py changes

* revert rag_storage.py changes

---------

Co-authored-by: Matt B <mattb@Matts-MacBook-Pro.local>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-12 12:31:43 -05:00
André Lago
983ca25f5c Fix small typo in sample tool (#1747)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-12 10:11:47 -05:00
Rashmi Pawar
33c0c72194 NVIDIA Provider : UI changes (#1746)
* docs: add nvidia as provider

* nvidia ui docs changes

* add note for updated list

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-12 10:01:53 -05:00
Anmol Deep
32f2a39693 Added is_auto_end flag in agentops.end session in crew.py (#1320)
When using agentops, we have the option to pass the `skip_auto_end_session` parameter, which is supposed to not end the session if the `end_session` function is called by Crew.

Now the way it works is, the `agentops.end_session` accepts `is_auto_end` flag and crewai should have passed it as `True` (its `False` by default). 

I have changed the code to pass is_auto_end=True

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-11 11:34:17 -05:00
Bowen Liang
93425db024 sort imports with isort rules by ruff linter (#1730)
* sort imports

* update

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Eduardo Chiarotti <dudumelgaco@hotmail.com>
2024-12-11 10:46:53 -05:00
Brandon Hancock (bhancock_ai)
ec2f0a7c76 include event emitter in flows (#1740)
* include event emitter in flows

* Clean up

* Fix linter
2024-12-11 10:16:05 -05:00
Paul Cowgill
2a3698d53c Remove manager_callbacks reference (#1741) 2024-12-11 10:13:57 -05:00
Archkon
bc1ebf36e5 fix:typo error (#1738)
* Update base_agent_tools.py

typo error

* Update main.py

typo error

* Update base_file_knowledge_source.py

typo error

* Update test_main.py

typo error

* Update en.json

* Update prompts.json

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-10 11:18:45 -05:00
Brandon Hancock (bhancock_ai)
e2f71464ed copy googles changes. Fix tests. Improve LLM file (#1737)
* copy googles changes. Fix tests. Improve LLM file

* Fix type issue
2024-12-10 11:14:37 -05:00
Brandon Hancock (bhancock_ai)
7d85046eb6 Update pyproject.toml and uv.lock to drop crewai-tools as a default requirement (#1711) 2024-12-09 14:17:46 -05:00
Brandon Hancock (bhancock_ai)
6f7c94e88b Bugfix/restrict python version compatibility (#1736)
* drop 3.13

* revert

* Drop test cassette that was causing error

* trying to fix failing test

* adding thiago changes

* resolve final tests

* Drop skip

* drop pipeline
2024-12-09 14:07:57 -05:00
Brandon Hancock (bhancock_ai)
30566a8dfa restrict python version compatibility (#1731)
* drop 3.13

* revert

* Drop test cassette that was causing error

* trying to fix failing test

* adding thiago changes

* resolve final tests

* Drop skip
2024-12-09 14:00:18 -05:00
Carlos Souza
e5ccfbf68d Fix disk I/O error when resetting short-term memory. (#1724)
* Fix disk I/O error when resetting short-term memory.

Reset chromadb client and nullifies references before
removing directory.

* Nit for clarity

* did the same for knowledge_storage

* cleanup

* cleanup order

* Cleanup after the rm of the directories

---------

Co-authored-by: Lorenze Jay <lorenzejaytech@gmail.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2024-12-09 10:30:51 -08:00
Piotr Mardziel
7d4d5c6bf7 Add missing @functools.wraps when wrapping functions and preserve wrapped class name in @CrewBase. (#1560)
* Update annotations.py

* Update utils.py

* Update crew_base.py

* Update utils.py

* Update crew_base.py

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-09 11:51:12 -05:00
Tony Kipkemboi
317bcac4c3 format bullet points (#1734)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-09 11:40:01 -05:00
fuckqqcom
55d420d1ad _execute_tool_and_check_finality 结果给回调参数,这样就可以提前拿到结果信息,去做数据解析判断做预判 (#1716)
Co-authored-by: xiaohan <fuck@qq.com>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-09 11:37:54 -05:00
lgesuellip
4a52db6f84 Add doc structured tool (#1713)
* Add doc structured tool

* Fix example

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-09 11:34:07 -05:00
Tony Kipkemboi
f5107d7238 Merge pull request #1733 from rokbenko/main
[DOCS] Fix Spaceflight News API docs link on Knowledge docs page
2024-12-09 11:27:01 -05:00
Tony Kipkemboi
eb3076b0f3 Merge branch 'main' into main 2024-12-09 11:23:36 -05:00
Aviral Jain
eae0eb2905 call storage.search in user context search instead of memory.search (#1692)
Co-authored-by: Eduardo Chiarotti <dudumelgaco@hotmail.com>
2024-12-09 08:07:52 -08:00
Rok Benko
f724f30d16 Fix Knowledge docs Spaceflight News API dead link 2024-12-09 10:58:51 -05:00
Archkon
6fb6ef6c56 fix:typo error (#1732)
* Update crew_agent_executor.py

typo error

* Update en.json

typo error
2024-12-09 10:53:55 -05:00
Frieda Huang
b64098bbb6 Fixed output_file not respecting system path (#1726)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-09 10:05:54 -05:00
Eduardo Chiarotti
36eb6354c2 docs: Add quotes to agentops installing command (#1729)
* docs: Add quotes to agentops installing command

* feat: Add ContextualMemory to __init__

* feat: remove import due to circular improt

* feat: update tasks config main template typos
2024-12-09 11:42:36 -03:00
Brandon Hancock (bhancock_ai)
ade3934e2a add support for langfuse with litellm (#1721) 2024-12-06 13:57:28 -05:00
Brandon Hancock (bhancock_ai)
440513674a drop metadata requirement (#1712)
* drop metadata requirement

* fix linting

* Update docs for new knowledge

* more linting

* more linting

* make save_documents private

* update docs to the new way we use knowledge and include clearing memory
2024-12-05 14:59:52 -05:00
Brandon Hancock (bhancock_ai)
55456a2e2e Incorporate Stale PRs that have feedback (#1693)
* incorporate #1683

* add in --version flag to cli. closes #1679.

* Fix env issue

* Add in suggestions from @caike to make sure ragstorage doesnt exceed os file limit. Also, included additional checks to support windows.

* remove poetry.lock as pointed out by @sanders41 in #1574.

* Incorporate feedback from crewai reviewer

* Incorporate @lorenzejay feedback
2024-12-05 12:17:23 -05:00
João Moura
7a4d0dd8a2 curting new verson 2024-12-05 13:53:10 -03:00
João Moura
db0d0c25f1 updating tools 2024-12-05 13:51:20 -03:00
Brandon Hancock (bhancock_ai)
d77c35a4ba New docs about yaml crew with decorators. Simplify template crew with… (#1701)
* New docs about yaml crew with decorators. Simplify template crew with links

* Fix spelling issues.
2024-12-05 11:23:20 -05:00
Brandon Hancock (bhancock_ai)
03abf53ba9 Brandon/cre 509 hitl multiple rounds of followup (#1702)
* v1 of HITL working

* Drop print statements

* HITL code more robust. Still needs to be refactored.

* refactor and more clear messages

* Fix type issue

* fix tests

* Fix test again

* Drop extra print
2024-12-05 10:14:04 -05:00
Tony Kipkemboi
06d02c0f62 add knowledge demo + improve knowledge docs (#1706) 2024-12-05 09:49:44 -05:00
Rashmi Pawar
3820594581 docs: add nvidia as provider (#1632)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-04 15:38:46 -05:00
Brandon Hancock (bhancock_ai)
5f9de33cc0 remove all references to pipeline and pipeline router (#1661)
* remove all references to pipeline and router

* fix linting

* drop poetry.lock
2024-12-04 12:39:34 -05:00
Tony Kipkemboi
385c78ec54 Merge pull request #1698 from crewAIInc/brandon/cre-510-update-docs-to-talk-about-pydantic-and-json-outputs
Talk about getting structured consistent outputs with tasks.
2024-12-04 11:07:52 -05:00
Tony Kipkemboi
ec844ed7bf Merge branch 'main' into brandon/cre-510-update-docs-to-talk-about-pydantic-and-json-outputs 2024-12-04 11:05:47 -05:00
Brandon Hancock
c5659663ef Talk about getting structured consistent outputs with tasks. 2024-12-04 10:46:39 -05:00
Stephen
dea6b14255 Update README.md (#1694)
Corrected the statement which says users can not disable telemetry, but now users can disable by setting the environment variable OTEL_SDK_DISABLED to true.

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-03 16:08:19 -05:00
Lorenze Jay
1f8ee15753 Knowledge project directory standard (#1691)
* Knowledge project directory standard

* fixed types

* comment fix

* made base file knowledge source an abstract class

* cleaner validator on model_post_init

* fix type checker

* cleaner refactor

* better template
2024-12-03 12:27:48 -08:00
Feynman Liang
04cbf10a78 Fix indentation in llm-connections.mdx code block (#1573)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-03 12:52:23 -05:00
Patcher
b2a0bec3f6 [Doc]: Add documenation for openlit observability (#1612)
* Create openlit-observability.mdx

* Update doc with images and steps

* Update mkdocs.yml and add OpenLIT guide link

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-03 12:38:49 -05:00
Tom Mahler, PhD
d6fdb9980c [FEATURE] Support for custom path in RAGStorage (#1659)
* added path to RAGStorage

* added path to short term and entity memory

* add path for long_term_storage for completeness

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-03 12:22:29 -05:00
Ola Hungerford
79cfa87341 Update using langchain tools docs (#1664)
* Update example of how to use LangChain tools with correct syntax

* Use .env

* Add  Code back

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-03 11:13:06 -05:00
Javier Saldaña
1ca68aff08 Update reset memories command based on the SDK (#1688)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-03 10:09:30 -05:00
Tony Kipkemboi
e449e535f7 fix missing code in flows docs (#1690)
* docs: improve tasks documentation clarity and structure

- Add Task Execution Flow section
- Add variable interpolation explanation
- Add Task Dependencies section with examples
- Improve overall document structure and readability
- Update code examples with proper syntax highlighting

* docs: update agent documentation with improved examples and formatting

- Replace DuckDuckGoSearchRun with SerperDevTool
- Update code block formatting to be consistent
- Improve template examples with actual syntax
- Update LLM examples to use current models
- Clean up formatting and remove redundant comments

* docs: enhance LLM documentation with Cerebras provider and formatting improvements

* docs: simplify LLMs documentation title

* docs: improve installation guide clarity and structure

- Add clear Python version requirements with check command
- Simplify installation options to recommended method
- Improve upgrade section clarity for existing users
- Add better visual structure with Notes and Tips
- Update description and formatting

* docs: improve introduction page organization and clarity

- Update organizational analogy in Note section
- Improve table formatting and alignment
- Remove emojis from component table for cleaner look
- Add 'helps you' to make the note more action-oriented

* docs: add enterprise and community cards

- Add Enterprise deployment card in quickstart
- Add community card focused on open source discussions
- Remove deployment reference from community description
- Clean up introduction page cards
- Remove link from Enterprise description text

* docs: add code snippet to Getting Started section in flows.mdx

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-12-03 10:02:06 -05:00
João Moura
ab7a594301 preparing new version 2024-12-02 18:28:58 -03:00
Brandon Hancock (bhancock_ai)
4d06708938 Fixes issues with result as answer not properly exiting LLM loop (#1689)
* v1 of fix implemented. Need to confirm with tokens.

* remove print statements
2024-12-02 13:38:17 -05:00
Tony Kipkemboi
aa532acdd2 Documentation Improvements: LLM Configuration and Usage (#1684)
* docs: improve tasks documentation clarity and structure

- Add Task Execution Flow section
- Add variable interpolation explanation
- Add Task Dependencies section with examples
- Improve overall document structure and readability
- Update code examples with proper syntax highlighting

* docs: update agent documentation with improved examples and formatting

- Replace DuckDuckGoSearchRun with SerperDevTool
- Update code block formatting to be consistent
- Improve template examples with actual syntax
- Update LLM examples to use current models
- Clean up formatting and remove redundant comments

* docs: enhance LLM documentation with Cerebras provider and formatting improvements

* docs: simplify LLMs documentation title

* docs: improve installation guide clarity and structure

- Add clear Python version requirements with check command
- Simplify installation options to recommended method
- Improve upgrade section clarity for existing users
- Add better visual structure with Notes and Tips
- Update description and formatting

* docs: improve introduction page organization and clarity

- Update organizational analogy in Note section
- Improve table formatting and alignment
- Remove emojis from component table for cleaner look
- Add 'helps you' to make the note more action-oriented

* docs: add enterprise and community cards

- Add Enterprise deployment card in quickstart
- Add community card focused on open source discussions
- Remove deployment reference from community description
- Clean up introduction page cards
- Remove link from Enterprise description text
2024-12-02 09:50:12 -05:00
Tony Kipkemboi
404da4066b Merge pull request #1675 from rokbenko/rok
[DOCS] Update Agents docs to include two approaches for creating an agent
2024-11-30 11:26:10 -05:00
Rok Benko
5735496227 Update Agents docs to include two approaches for creating an agent: with and without YAML configuration 2024-11-28 17:20:53 +01:00
Lorenze Jay
cd9a17a281 added knowledge to agent level (#1655)
* added knowledge to agent level

* linted

* added doc

* added from suggestions

* added test

* fixes from discussion

* fix docs

* fix test

* rm cassette for knowledge_sources test as its a mock and update agent doc string

* fix test

* rm unused

* linted
2024-11-27 11:33:07 -08:00
Brandon Hancock (bhancock_ai)
3fa44e9a07 Feat/remove langchain (#1668)
* feat: add initial changes from langchain

* feat: remove kwargs of being processed

* feat: remove langchain, update uv.lock and fix type_hint

* feat: change docs

* feat: remove forced requirements for parameter

* feat add tests for new structure tool

* feat: fix tests and adapt code for args

* fix tool calling for langchain tools

* doc strings

---------

Co-authored-by: Eduardo Chiarotti <dudumelgaco@hotmail.com>
2024-11-27 11:22:49 -05:00
Eduardo Chiarotti
3d23f09107 Feat/remove langchain (#1654)
* feat: add initial changes from langchain

* feat: remove kwargs of being processed

* feat: remove langchain, update uv.lock and fix type_hint

* feat: change docs

* feat: remove forced requirements for parameter

* feat add tests for new structure tool

* feat: fix tests and adapt code for args
2024-11-26 16:59:52 -03:00
Ivan Peevski
e357a6b7f3 Update readme for running mypy (#1614)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-11-26 12:45:08 -05:00
Brandon Hancock (bhancock_ai)
8856ebcd21 fix spelling issue found by @Jacques-Murray (#1660) 2024-11-26 11:36:29 -05:00
Bowen Liang
f754eba6fb update (#1638)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-11-26 11:24:21 -05:00
Bowen Liang
08f15f8f9d Update Github actions (#1639)
* actions/checkout@v4

* actions/cache@v4

* actions/setup-python@v5

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-11-26 11:08:50 -05:00
Brandon Hancock (bhancock_ai)
b3a49e65e5 Improve typed task outputs (#1651)
* V1 working

* clean up imports and prints

* more clean up and add tests

* fixing tests

* fix test

* fix linting

* Fix tests

* Fix linting

* add doc string as requested by eduardo
2024-11-26 09:41:14 -05:00
Tony Kipkemboi
dbe0c5a176 Merge pull request #1652 from tonykipkemboi/main
add knowledge to mint.json
2024-11-25 16:51:48 -05:00
Tony Kipkemboi
fc653be765 add knowledge to mint.json 2024-11-25 20:37:27 +00:00
Vini Brasil
6812febf0e Log in to Tool Repository on crewai login (#1650)
This commit adds an extra step to `crewai login` to ensure users also
log in to Tool Repository, that is, exchanging their Auth0 tokens for a
Tool Repository username and password to be used by UV downloads and API
tool uploads.
2024-11-25 15:57:47 -03:00
João Moura
9f13c8afbf preparing new version 2024-11-25 10:05:15 -03:00
Gui Vieira
f41d9cacee Merge pull request #1640 from crewAIInc/gui/fix-threading
Fix threading
2024-11-21 15:50:46 -03:00
Gui Vieira
e9c999d533 Fix threading 2024-11-21 15:33:20 -03:00
Andy Bromberg
749cff8411 Update Perplexity example in documentation (#1623) 2024-11-20 21:54:04 -03:00
Bob Conan
2238f7fd47 Updated README.md, fix typo(s) (#1637) 2024-11-20 21:52:41 -03:00
Brandon Hancock (bhancock_ai)
8100d3e947 Knowledge (#1567)
* initial knowledge

* WIP

* Adding core knowledge sources

* Improve types and better support for file paths

* added additional sources

* fix linting

* update yaml to include optional deps

* adding in lorenze feedback

* ensure embeddings are persisted

* improvements all around Knowledge class

* return this

* properly reset memory

* properly reset memory+knowledge

* consolodation and improvements

* linted

* cleanup rm unused embedder

* fix test

* fix duplicate

* generating cassettes for knowledge test

* updated default embedder

* None embedder to use default on pipeline cloning

* improvements

* fixed text_file_knowledge

* mypysrc fixes

* type check fixes

* added extra cassette

* just mocks

* linted

* mock knowledge query to not spin up db

* linted

* verbose run

* put a flag

* fix

* adding docs

* better docs

* improvements from review

* more docs

* linted

* rm print

* more fixes

* clearer docs

* added docstrings and type hints for cli

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
Co-authored-by: Lorenze Jay <lorenzejaytech@gmail.com>
2024-11-20 15:40:08 -08:00
Gui Vieira
208057eaf1 Merge pull request #1636 from crewAIInc/gui/make-it-green
Make it green!
2024-11-20 16:12:58 -03:00
Gui Vieira
5edbb86cf0 Make mypy happy 2024-11-20 16:08:08 -03:00
Gui Vieira
9b2b44bbf3 Merge pull request #1635 from crewAIInc/gui/kickoff-callbacks
Move kickoff callbacks to crew's domain
2024-11-20 14:37:52 -03:00
Gui Vieira
93471dea08 Cassettes 2024-11-20 10:26:00 -03:00
Gui Vieira
d36c3644a6 Move kickoff callbacks to crew's domain 2024-11-20 10:06:49 -03:00
Tony Kipkemboi
03029a336d Merge pull request #1634 from crewAIInc/github_tool_update
docs: add gh_token documentation to GithubSearchTool
2024-11-20 07:21:24 -05:00
theCyberTech
e761f330c5 docs: add gh_token documentation to GithubSearchTool 2024-11-20 19:23:09 +08:00
Tony Kipkemboi
704025fe1e Update CLI Watson supported models + docs (#1628) 2024-11-19 19:42:54 -03:00
João Moura
6c29ad29c9 adding before and after crew 2024-11-18 00:21:36 -03:00
João Moura
e6305ca11b preparing enw version 2024-11-18 00:21:36 -03:00
Lorenze Jay
781ac736ce upgrade chroma and adjust embedder function generator (#1607)
* upgrade chroma and adjust embedder function generator

* >= version

* linted
2024-11-14 14:13:12 -08:00
Dev Khant
fcb8114132 Add support for retrieving user preferences and memories using Mem0 (#1209)
* Integrate Mem0

* Update src/crewai/memory/contextual/contextual_memory.py

Co-authored-by: Deshraj Yadav <deshraj@gatech.edu>

* pending commit for _fetch_user_memories

* update poetry.lock

* fixes mypy issues

* fix mypy checks

* New fixes for user_id

* remove memory_provider

* handle memory_provider

* checks for memory_config

* add mem0 to dependency

* Update pyproject.toml

Co-authored-by: Deshraj Yadav <deshraj@gatech.edu>

* update docs

* update doc

* bump mem0 version

* fix api error msg and mypy issue

* mypy fix

* resolve comments

* fix memory usage without mem0

* mem0 version bump

* lazy import mem0

---------

Co-authored-by: Deshraj Yadav <deshraj@gatech.edu>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-11-14 10:59:24 -08:00
Eduardo Chiarotti
5ca23ce757 feat: Reduce level for Bandit and fix code to adapt (#1604) 2024-11-14 13:12:35 -03:00
Thiago Moretto
e1b1a9361c Merge pull request #1597 from crewAIInc/tm-fix-crew-train-test
Fix crew_train_success test
2024-11-13 10:52:49 -03:00
Thiago Moretto
11bdc7c679 Fix crew_train_success test 2024-11-13 10:47:49 -03:00
Thiago Moretto
80598969ee Merge pull request #1596 from crewAIInc/tm-recording-cached-prompt-tokens
Add cached prompt tokens info on usage metrics
2024-11-13 10:37:29 -03:00
Thiago Moretto
65266658db Merge branch 'main' into tm-recording-cached-prompt-tokens 2024-11-13 10:19:02 -03:00
Thiago Moretto
b1a0b85097 do not include cached on total 2024-11-13 10:18:30 -03:00
Thiago Moretto
6cab25aba9 Cached prompt tokens on usage metrics 2024-11-13 10:16:30 -03:00
Eduardo Chiarotti
1097abff32 fix: Step callback issue (#1595)
* fix: Step callback issue

* fix: Add empty thought since its required
2024-11-13 10:07:28 -03:00
João Moura
5c2c41eda9 removing prints 2024-11-12 18:37:57 -03:00
Thiago Moretto
c5471a78e9 Merge pull request #1588 from crewAIInc/tm-workaround-litellm-bug
fixing LiteLLM callback replacement bug
2024-11-12 17:19:01 -03:00
Thiago Moretto
ccd7723d91 fix test_agent_usage_metrics_are_captured_for_hierarchical_process 2024-11-12 16:43:43 -03:00
Thiago Moretto
d1169ad79d fix LiteLLM callback replacement 2024-11-12 15:04:57 -03:00
João Moura
12fb3fb0e8 add missing init 2024-11-11 02:29:40 -03:00
João Moura
cc1087764c preparing new version 2024-11-11 00:03:52 -03:00
João Moura
88ecd6b0c5 preparing new version 2024-11-10 23:46:38 -03:00
João Moura
8eb54cf168 curring new version 2024-11-10 21:16:36 -03:00
João Moura
e15bb1e95b preparing new version 2024-11-10 20:47:56 -03:00
João Moura
80dcbc7e46 updating LLM docs 2024-11-10 11:36:03 -03:00
João Moura
5bb1a3b257 preparing new version 2024-11-10 11:00:16 -03:00
João Moura
1267219c3d making sure we don't check for agents that were not used in the crew 2024-11-06 23:07:23 -03:00
Brandon Hancock (bhancock_ai)
bd3f4042e2 fix missing config (#1557) 2024-11-05 12:07:29 -05:00
Brandon Hancock (bhancock_ai)
9a979f80a0 Fix flows to support cycles and added in test (#1556) 2024-11-05 12:02:54 -05:00
Brandon Hancock (bhancock_ai)
8204de61c3 Feat/watson in cli (#1535)
* getting cli and .env to work together for different models

* support new models

* clean up prints

* Add support for cerebras

* Fix watson keys
2024-11-05 12:01:57 -05:00
Tony Kipkemboi
e160fef306 docs update (#1558)
* add llm providers accordion group

* fix numbering

* Fix directory tree & add llms to accordion

* update crewai enterprise link in docs
2024-11-05 11:26:19 -05:00
Brandon Hancock (bhancock_ai)
9c6344967c Raise an error if an LLM doesnt return a response (#1548) 2024-11-04 11:42:38 -05:00
Gui Vieira
8065a02f06 Increase providers fetching timeout 2024-11-01 18:54:40 -03:00
Brandon Hancock (bhancock_ai)
bd1a53a718 add inputs to flows (#1553)
* add inputs to flows

* fix flows lint
2024-11-01 14:37:02 -07:00
Brandon Hancock (bhancock_ai)
e873950e4c Feat/ibm memory (#1549)
* Everything looks like its working. Waiting for lorenze review.

* Update docs as well.

* clean up for PR
2024-11-01 16:42:46 -04:00
Tony Kipkemboi
ad41065b03 Update docs (#1550)
* add llm providers accordion group

* fix numbering

* Fix directory tree & add llms to accordion
2024-11-01 15:58:36 -04:00
C0deZ
ae33fdd05f refactor: Move BaseTool to main package and centralize tool description generation (#1514)
* move base_tool to main package and consolidate tool desscription generation

* update import path

* update tests

* update doc

* add base_tool test

* migrate agent delegation tools to use BaseTool

* update tests

* update import path for tool

* fix lint

* update param signature

* add from_langchain to BaseTool for backwards support of langchain tools

* fix the case where StructuredTool doesn't have func

---------

Co-authored-by: c0dez <li@vitablehealth.com>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-11-01 12:30:48 -04:00
Vini Brasil
bb9e5461d6 Replace .netrc with uv environment variables (#1541)
This commit replaces .netrc with uv environment variables for installing
tools from private repositories. To store credentials, I created a new
and reusable settings file for the CLI in
`$HOME/.config/crewai/settings.json`.

The issue with .netrc files is that they are applied system-wide and are
scoped by hostname, meaning we can't differentiate tool repositories
requests from regular requests to CrewAI's API.
2024-10-31 15:00:58 -03:00
Tony Kipkemboi
4eb5cab464 Add llm providers accordion group (#1534)
* add llm providers accordion group

* fix numbering
2024-10-30 21:56:13 -04:00
Robin Wang
54386c0de4 Enhance log storage to support more data types (#1530) 2024-10-30 16:45:19 -04:00
Brandon Hancock (bhancock_ai)
f7d7b5fe18 Disable telemetry explicitly (#1536)
* Disable telemetry explicitly

* fix linting

* revert parts to og
2024-10-30 16:37:21 -04:00
Rip&Tear
f4a8aa5bda Added security.md file (#1533) 2024-10-30 12:07:38 -04:00
João Moura
5d264d8e5a prepare new version 2024-10-30 00:07:46 -03:00
Brandon Hancock (bhancock_ai)
e8bade008d Bugfix/flows with multiple starts plus ands breaking (#1531)
* bugfix/flows-with-multiple-starts-plus-ands-breaking

* fix user found issue

* remove prints
2024-10-29 19:36:53 -03:00
Brandon Hancock (bhancock_ai)
20a0e4c0dd Update flows cli to allow you to easily add additional crews to a flow (#1525)
* Update flows cli to allow you to easily add additional crews to a flow

* fix failing test

* adding more error logs to test thats failing

* try again
2024-10-29 11:53:48 -04:00
Tony Kipkemboi
17006e2fe2 Merge pull request #1519 from crewAIInc/feat/improve-tooling-docs
Improve tooling and flow docs
2024-10-29 11:05:17 -04:00
Brandon Hancock (bhancock_ai)
06ce3e7f85 Merge branch 'main' into feat/improve-tooling-docs 2024-10-29 10:41:04 -04:00
Brandon Hancock (bhancock_ai)
0f37e861aa Update flows.mdx - Fix link 2024-10-29 10:40:49 -04:00
Brandon Hancock
73788e6c5b Update flow docs to talk about self evaluation example 2024-10-28 12:18:03 -05:00
Brandon Hancock
1eb87a59cc Update flow docs to talk about self evaluation example 2024-10-28 12:17:44 -05:00
Brandon Hancock
eac392974f Improve tooling docs 2024-10-28 09:40:56 -05:00
Brandon Hancock (bhancock_ai)
26c2812baf improve tool text description and args (#1512)
* improve tool text descriptoin and args

* fix lint

* Drop print

* add back in docstring
2024-10-25 18:42:55 -04:00
Vini Brasil
f131507e90 Forward install command options to uv sync (#1510)
Allow passing additional options from `crewai install` directly to
`uv sync`. This enables commands like `crewai install --locked` to work
as expected by forwarding all flags and options to the underlying uv
command.
2024-10-25 11:20:41 -03:00
Eduardo Chiarotti
c42c787f36 feat: add tomli so we can support 3.10 (#1506)
* feat: add tomli so we can support 3.10

* feat: add validation for poetry data
2024-10-25 10:33:21 -03:00
Brandon Hancock (bhancock_ai)
570c255bae update plot command (#1504) 2024-10-24 14:44:30 -04:00
João Moura
a1e766afb2 new version 2024-10-23 18:10:37 -03:00
João Moura
da238e02f5 new version 2024-10-23 18:08:49 -03:00
João Moura
bf79353e43 updating crewai version 2024-10-23 17:58:58 -03:00
Brandon Hancock (bhancock_ai)
083f579290 Fix memory imports for embedding functions (#1497) 2024-10-23 11:21:27 -04:00
Brandon Hancock (bhancock_ai)
3f8f19a82b support unsafe code execution. add in docker install and running checks. (#1496)
* support unsafe code execution. add in docker install and running checks.

* Update return type
2024-10-23 11:01:00 -04:00
Maicon Peixinho
0b486d562a chore(readme-fix): fixing step for 'running tests' in the contribution section (#1490)
Co-authored-by: Eduardo Chiarotti <dudumelgaco@hotmail.com>
2024-10-23 11:38:41 -03:00
Rip&Tear
ed3edc5c43 fix/fixed missing API prompt + CLI docs update (#1464)
* updated CLI to allow for submitting API keys

* updated click prompt to remove default number

* removed all unnecessary comments

* feat: implement crew creation CLI command

- refactor code to multiple functions
- Added ability for users to select provider and model when uing crewai create command and ave API key to .env

* refactered select_choice function for early return

* refactored  select_provider to have an ealry return

* cleanup of comments

* refactor/Move functions into utils file, added new provider file and migrated fucntions thre, new constants file + general function refactor

* small comment cleanup

* fix unnecessary deps

* Added docs for new CLI provider + fixed missing API prompt

* Minor doc updates

* allow user to bypass api key entry + incorect number selected logic + ruff formatting

* ruff updates

* Fix spelling mistake

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2024-10-23 09:41:14 -04:00
João Moura
38a131d525 preparing new verison 2024-10-23 05:34:34 -03:00
Brandon Hancock (bhancock_ai)
ab05c2048d use copy to split testing and training on crews (#1491)
* use copy to split testing and training on crews

* make tests handle new copy functionality on train and test

* fix last test

* fix test
2024-10-22 21:31:44 -04:00
Lorenze Jay
aa18967629 ensure original embedding config works (#1476)
* ensure original embedding config works

* some fixes

* raise error on unsupported provider

* WIP: brandons notes

* fixes

* rm prints

* fixed docs

* fixed run types

* updates to add more docs and correct imports with huggingface embedding server enabled

---------

Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2024-10-22 12:30:30 -07:00
Tony Kipkemboi
845b764ce9 Add Cerebras LLM example configuration to LLM docs (#1488) 2024-10-22 13:41:29 -04:00
Brandon Hancock (bhancock_ai)
dc16ac4cc3 simplify flow (#1482)
* simplify flow

* propogate changes

* Update docs and scripts

* Template fix

* make flow kickoff sync

* Clean up docs
2024-10-21 19:32:55 -04:00
Brandon Hancock (bhancock_ai)
fd1c9ec63a drop unneccesary tests (#1484)
* drop uneccesary tests

* fix linting
2024-10-21 15:26:30 -04:00
Sam
06793d1318 fix(docs): typo (#1470) 2024-10-21 11:49:33 -04:00
Vini Brasil
233fec1ea8 Adapt crewai tool install <tool> to uv (#1481)
This commit updates the tool install comamnd to uv's new custom index
feature.

Related: https://github.com/astral-sh/uv/pull/7746/
2024-10-21 09:24:03 -03:00
João Moura
9278736718 new verison 2024-10-18 17:57:37 -03:00
João Moura
e5a18a6ccf cutting new version 2024-10-18 17:57:02 -03:00
Brandon Hancock (bhancock_ai)
b3d16bba5f fix tool calling issue (#1467)
* fix tool calling issue

* Update tool type check

* Drop print
2024-10-18 15:56:56 -03:00
Eduardo Chiarotti
69cd84d78f feat: add poetry.lock to uv migration (#1468) 2024-10-18 15:45:01 -03:00
João Moura
e4f950720c Avoiding exceptions 2024-10-18 08:32:06 -03:00
João Moura
7948e62fd5 fix tasks and agents ordering 2024-10-18 08:06:38 -03:00
João Moura
c00e714460 fixing annotations 2024-10-18 07:46:30 -03:00
João Moura
02eb7e7f81 preparing new version 2024-10-18 07:13:17 -03:00
Lorenze Jay
65c32806ec Feat/memory base (#1444)
* byom - short/entity memory

* better

* rm uneeded

* fix text

* use context

* rm dep and sync

* type check fix

* fixed test using new cassete

* fixing types

* fixed types

* fix types

* fixed types

* fixing types

* fix type

* cassette update

* just mock the return of short term mem

* remove print

* try catch block

* added docs

* dding error handling here
2024-10-17 13:19:33 -03:00
Rok Benko
0eb3ba34dd Fix incorrect parameter name in Vision tool docs page (#1461)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-10-17 13:18:31 -03:00
Rip&Tear
175f40024b feat/updated CLI to allow for model selection & submitting API keys (#1430)
* updated CLI to allow for submitting API keys

* updated click prompt to remove default number

* removed all unnecessary comments

* feat: implement crew creation CLI command

- refactor code to multiple functions
- Added ability for users to select provider and model when uing crewai create command and ave API key to .env

* refactered select_choice function for early return

* refactored  select_provider to have an ealry return

* cleanup of comments

* refactor/Move functions into utils file, added new provider file and migrated fucntions thre, new constants file + general function refactor

* small comment cleanup

* fix unnecessary deps

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2024-10-17 10:05:07 -04:00
Eduardo Chiarotti
c86d4ef29c feat: ADd warning from poetry -> uv (#1458) 2024-10-16 18:58:08 -03:00
Tony Kipkemboi
d4213cecb7 Upgrade docs to mirror change from Poetry to UV (#1451)
* Update docs to use  instead of

* Add Flows YouTube tutorial & link images
2024-10-16 10:57:41 -04:00
Stephen Hankinson
8720316e2f use the same i18n as the agent for tool usage (#1440)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-10-16 10:38:42 -04:00
Vini Brasil
42f960b2bd Adapt Tools CLI to uv (#1455)
* Adapt Tools CLI to UV

* Fix failing test
2024-10-16 10:55:04 -03:00
dbubel
60a87c7f77 fix typo in template file (#1432) 2024-10-14 16:51:04 -04:00
Stephen Hankinson
99bcc44ce6 Correct the role for the message being added to the messages list (#1438)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-10-14 16:49:16 -04:00
Muhammad Noman Fareed
dda5e0de0f Fix Cache Typo in Documentation (#1441) 2024-10-14 16:30:31 -04:00
Stephen Hankinson
bcffbca854 Use a slice for the manager request. Make the task use the agent i18n settings (#1446) 2024-10-14 16:30:05 -04:00
Eduardo Chiarotti
a6d3898080 fix: training issue (#1433)
* fix: training issue

* fix: output from crew

* fix: message
2024-10-11 22:35:17 -03:00
Eduardo Chiarotti
2256462b7e Feat/poetry to uv migration (#1406)
* feat: Start migrating to UV

* feat: add uv to flows

* feat: update docs on Poetry -> uv

* feat: update docs and uv.locl

* feat: update tests and github CI

* feat: run ruff format

* feat: update typechecking

* feat: fix type checking

* feat: update python version

* feat: type checking gic

* feat: adapt uv command to run the tool repo

* Adapt tool build command to uv

* feat: update logic to let only projects with crew to be deployed

* feat: add uv to tools

* fix; tests

* fix: remove breakpoint

* fix :test

* feat: add crewai update to migrate from poetry to uv

* fix: tests

* feat: add validation for ˆ character on pyproject

* feat: add run_crew to pyproject if doesnt exist

* feat: add validation for poetry migration

* fix: warning

---------

Co-authored-by: Vinicius Brasil <vini@hey.com>
2024-10-11 19:11:27 -03:00
Brandon Hancock (bhancock_ai)
f1ecbc3f14 Trying to fix linting and other warnings (#1417)
* Trying to fix linting

* fixing more type issues

* clean up ci

* more ci fixes

---------

Co-authored-by: Eduardo Chiarotti <dudumelgaco@hotmail.com>
2024-10-11 09:45:53 -04:00
João Moura
02a8edf866 Preparing new version 2024-10-10 19:58:54 -03:00
João Moura
3a1bb36848 updating init 2024-10-10 19:41:58 -03:00
João Moura
7faff4710d preparing new version 2024-10-10 19:35:52 -03:00
João Moura
24139f541d fixing tests 2024-10-10 19:32:26 -03:00
Shahar Yair
d5427fb019 Fix/logger - fix #1412 (#1413)
* improved logger

* log file looks better

* better lines written to log file

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-10-10 19:15:34 -03:00
Tony Kipkemboi
063ad2d99d Migrate docs from MkDocs to Mintlify (#1423)
* add new mintlify docs

* add favicon.svg

* minor edits

* add github stats
2024-10-10 19:14:28 -03:00
Brandon Hancock (bhancock_ai)
8119b7239d fix task cloning error (#1416) 2024-10-10 12:00:28 -04:00
Lennex Zinyando
384288e7b1 Update twitter logo to x-twiiter (#1403) 2024-10-07 10:21:47 -04:00
Akesh kumar
cdc907a87d Added version details (#1402)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-10-06 18:01:34 -03:00
Brandon Hancock (bhancock_ai)
32395b14d2 reduce import time by 6x (#1396)
* reduce import by 6x

* fix linting
2024-10-06 17:55:32 -03:00
Brandon Hancock (bhancock_ai)
f5699ddf68 quick fixes (#1385)
* quick fixes

* add generic name

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-10-04 13:23:42 -03:00
Brandon Hancock (bhancock_ai)
4361f4ff75 Brandon/cre 291 flow improvements (#1390)
* Implement joao feedback

* update colors for crew nodes

* clean up

* more linting clean up

* round legend corners

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-10-04 13:22:46 -03:00
Brandon Hancock (bhancock_ai)
f98c2c00d8 Brandon/cre 288 add telemetry to flows (#1391)
* Telemetry for flows

* store node names
2024-10-04 13:21:55 -03:00
Brandon Hancock (bhancock_ai)
b106927a4e add plotting to flows documentation (#1394) 2024-10-04 13:19:09 -03:00
Vini Brasil
5dee13e078 Add --force option to crewai tool publish (#1383)
This commit adds an option to bypass Git remote validations when
publishing tools.
2024-10-04 11:02:50 -03:00
Eren Küçüker
d063ed3014 docs: correct miswritten command name (#1365)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-10-03 12:22:07 -04:00
Tony Kipkemboi
91f9d56544 Update README (#1376)
* Change all instaces of crewAI to CrewAI and fix installation step

* Update the  example to use YAML format

* Update  to come after setup and edits

* Remove double tool instance
2024-10-03 12:09:26 -04:00
Guilherme de Amorim
fd3c8a8f92 fix: JSON encoding date objects (#1374) 2024-10-02 16:06:10 -04:00
Thiago Moretto
8742400b67 Merge pull request #1382 from crewAIInc/tm-basic-event-structure
Add tool usage events
2024-10-02 12:54:51 -03:00
Vini Brasil
7c1f88cd07 Add Git validations for publishing tools (#1381)
This commit prevents tools from being published if the underlying Git
repository is unsynced with origin.
2024-10-02 11:46:18 -03:00
Thiago Moretto
02fe5814f7 Make tests green again 2024-10-02 11:36:27 -03:00
Thiago Moretto
5166e7abd7 Merge branch 'main' into tm-basic-event-structure 2024-10-02 11:18:46 -03:00
Thiago Moretto
43d7bbbd03 Add tool usage events 2024-10-02 11:11:07 -03:00
Vini Brasil
8aba99a67d Create crewai tool create <tool> command (#1379)
This commit creates a new CLI command for scaffolding tools.
2024-10-01 18:58:27 -03:00
Vini Brasil
2c74efc8f2 Change Tool Repository authentication scope (#1378)
This commit adds a new command for adding custom PyPI indexes
credentials to the project. This was changed because credentials are now
user-scoped instead of organization.
2024-10-01 18:44:08 -03:00
João Moura
94f148e524 preparing new version 2024-10-01 14:18:17 -07:00
João Moura
ec010c37a7 hadnling pydantic obejct with Optional fields 2024-10-01 14:18:11 -07:00
João Moura
8a0afd6250 updating dependencies 2024-10-01 11:37:57 -07:00
João Moura
9407f5a7da preparing new version 2024-10-01 11:33:07 -07:00
Brandon Hancock (bhancock_ai)
8fb08a0b25 Flow visualizer (#1377)
* Almost working!

* It fully works but not clean enought

* Working but not clean engouth

* Everything is workign

* WIP. Working on adding and & or to flows. In the middle of setting up template for flow as well

* template working

* Everything is working

* More changes and todos

* Add more support for @start

* Router working now

* minor tweak to

* minor tweak to conditions and event handling

* Update logs

* Too trigger happy with cleanup

* Added in Thiago fix

* Flow passing results again

* Working on docs.

* made more progress updates on docs

* Finished talking about controlling flows

* add flow output

* fixed flow output section

* add crews to flows section is looking good now

* more flow doc changes

* Update docs and add more examples

* drop visualizer

* save visualizer

* pyvis is beginning to work

* pyvis working

* it is working

* regular methods and triggers working. Need to work on router next.

* properly identifying router and router children nodes. Need to fix color

* children router working. Need to support loops

* curving cycles but need to add curve conditionals

* everythin is showing up properly need to fix curves

* all working. needs to be cleaned up

* adjust padding

* drop lib

* clean up prior to PR

* incorporate joao feedback

* final tweaks for joao

* Refactor to make crews easier to understand

* update CLI and templates

* Fix crewai version in flows

* Fix merge conflict
2024-10-01 15:20:26 -03:00
João Moura
f65ecef670 remove unnecessary line 2024-09-30 23:21:50 -07:00
João Moura
3331ea186f preparing new version 2024-09-30 23:13:47 -07:00
Brandon Hancock (bhancock_ai)
45704fe16d Flow visualizer (#1375)
* Almost working!

* It fully works but not clean enought

* Working but not clean engouth

* Everything is workign

* WIP. Working on adding and & or to flows. In the middle of setting up template for flow as well

* template working

* Everything is working

* More changes and todos

* Add more support for @start

* Router working now

* minor tweak to

* minor tweak to conditions and event handling

* Update logs

* Too trigger happy with cleanup

* Added in Thiago fix

* Flow passing results again

* Working on docs.

* made more progress updates on docs

* Finished talking about controlling flows

* add flow output

* fixed flow output section

* add crews to flows section is looking good now

* more flow doc changes

* Update docs and add more examples

* drop visualizer

* save visualizer

* pyvis is beginning to work

* pyvis working

* it is working

* regular methods and triggers working. Need to work on router next.

* properly identifying router and router children nodes. Need to fix color

* children router working. Need to support loops

* curving cycles but need to add curve conditionals

* everythin is showing up properly need to fix curves

* all working. needs to be cleaned up

* adjust padding

* drop lib

* clean up prior to PR

* incorporate joao feedback

* final tweaks for joao
2024-09-30 20:52:56 -03:00
João Moura
c2124b7c01 fixing test 2024-09-30 12:01:50 -07:00
Shreyan Sood
4abcb7e3b3 Update Pipeline.md, fixed typo "=inputs" was repeated. (#1363) 2024-09-28 01:27:43 -03:00
Rip&Tear
19bdabf2ee flow template copy fix (#1364) 2024-09-28 01:27:17 -03:00
João Moura
5cbe6db486 temporary dropping excamples 2024-09-27 21:15:52 -03:00
João Moura
018eadce2b preparing for new verison 2024-09-27 20:28:25 -03:00
João Moura
86c035c9e1 preparing new verion 2024-09-27 20:24:37 -03:00
João Moura
76a826c1f0 fixing tasks order 2024-09-27 20:21:46 -03:00
Brandon Hancock (bhancock_ai)
f82420e7d6 Brandon/cre 19 workflows (#1347)
Flows
2024-09-27 12:11:17 -03:00
João Moura
f94aee3dc8 preparing for version 0.64.0 2024-09-26 21:53:09 -03:00
João Moura
30979e646d ordering tasks properly 2024-09-26 21:41:23 -03:00
João Moura
39d4773b3a Fixing summarization logic 2024-09-26 21:41:23 -03:00
João Moura
22d187c714 increase default max inter 2024-09-26 21:41:23 -03:00
Vini Brasil
35ef69d0e8 CLI for Tool Repository (#1357)
This commit adds two commands to the CLI:

- `crewai tool publish`
    - Builds the project using Poetry
    - Uploads the tarball to CrewAI's tool repository

- `crewai tool install my-tool`
    - Adds my-tool's index to Poetry and its credentials
    - Installs my-tool from the custom index
2024-09-26 17:23:31 -03:00
Thiago Moretto
bbfdcb90a7 Merge pull request #1360 from crewAIInc/tm-fix-base-agent-key
Crew's key must remain stable after input interpolation
2024-09-26 15:08:36 -03:00
Thiago Moretto
6b3a749cf4 Crew's key must remain stable after input interpolation 2024-09-26 14:55:33 -03:00
João Moura
3f8b15f34c Fixing trainign feature 2024-09-26 14:17:23 -03:00
João Moura
1120ed1f8c fixing training 2024-09-26 14:17:23 -03:00
Brandon Hancock (bhancock_ai)
cfc0645afb Fixed typing issues for new crews (#1358) 2024-09-26 14:12:24 -03:00
Vini Brasil
f311a465be Move crewai.cli.deploy.utils to crewai.cli.utils (#1350)
* Prevent double slashes when joining URLs

* Move crewai.cli.deploy.utils to crewai.cli.utils

This commit moves this package so it's reusable across commands.
2024-09-25 14:06:20 -03:00
Vini Brasil
d4d1882e72 Create client for Tools API (#1348)
This commit creates a class for the new Tools API. It extracts common
methods from crewai.cli.deploy.api.CrewAPI to a parent class.
2024-09-25 12:37:54 -03:00
DanKing1903
a5f3dd290b docs: fix misspelling of "EXA Search" in mkdocs.yml (#1346) 2024-09-25 12:34:11 -03:00
Lennex Zinyando
8b7ff930e7 Point footer socials to crewAIInc accounts (#1349) 2024-09-25 12:32:18 -03:00
João Moura
53bb18f9e8 updating version 2024-09-25 00:26:03 -03:00
João Moura
2fbd7b09b9 Updating logs and preparing new version 2024-09-24 23:55:12 -03:00
João Moura
2638ed9641 updating dependencies 2024-09-24 22:40:24 -03:00
João Moura
cbb858d375 Bringing support to o1 family back + any models that don't support stop words 2024-09-24 22:18:20 -03:00
João Moura
a1023739e0 cutting version 0.63.2 2024-09-24 05:31:58 -03:00
João Moura
ffae3f5a92 fixing importing 2024-09-24 01:54:02 -03:00
João Moura
8d1768fcc3 adding proepr LLM import 2024-09-24 01:53:23 -03:00
LogCreative
33695aa2fd docs: update "LLM-Connections" import and "Tasks" formatting (#1345)
* Update Tasks.md

Current formating of the page Tasks has been broken, fix the markdown formatting.

* Update LLM-Connections.md

LLM class has been moved to llm.py file
2024-09-24 01:52:41 -03:00
João Moura
6958c8dd48 adding OPENAI_BASE_URL as fallback 2024-09-23 23:39:04 -03:00
João Moura
09eaa76b44 prepare new version 2024-09-23 22:05:48 -03:00
João Moura
44f74fd6f6 removing logs 2024-09-23 20:56:58 -03:00
João Moura
9eeebd3c65 removing logs 2024-09-23 19:59:23 -03:00
João Moura
8abe4d98ed removing logging 2024-09-23 19:37:23 -03:00
João Moura
6f061cc306 updating tests 2024-09-23 17:45:20 -03:00
João Moura
8ebc89a227 Checking supports_function_calling isntead of gpt models 2024-09-23 16:23:38 -03:00
João Moura
9a62aa2977 preapring new version 2024-09-23 04:28:26 -03:00
João Moura
4ad69c573a ignore type checker 2024-09-23 04:25:13 -03:00
João Moura
2867cc4482 updating colors 2024-09-23 04:06:10 -03:00
Mr. Guo
d43135ca45 Fix encoding issue when loading i18n json file (#1341)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-09-23 04:01:35 -03:00
João Moura
73497596ae updating docs 2024-09-23 03:59:16 -03:00
João Moura
b440d143ed Adding new LLM class 2024-09-23 03:59:05 -03:00
João Moura
355338767c updating tests 2024-09-23 03:58:41 -03:00
João Moura
035929814e adding callbacks to llm 2024-09-23 00:54:01 -03:00
João Moura
699631fd1d supressing warning 2024-09-23 00:30:14 -03:00
João Moura
2d5af62df2 implementing initial LLM class 2024-09-22 22:37:29 -03:00
João Moura
7c0633e5de linter 2024-09-22 17:04:40 -03:00
Ayo Ayibiowu
6682fe3d89 feat(memory): adds support for customizable memory interface (#1339)
* feat(memory): adds support for customizing crew storage

* chore: allow overwriting the crew memory configuration

* docs: update custom storage usage

* fix(lint): use correct syntax

* fix: type check warning

* fix: type check warnings

* fix(test): address agent default failing test

* fix(lint). address type checker error

* Update crew.py

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-09-22 17:03:23 -03:00
João Moura
0f283325e1 fixing linting 2024-09-22 16:51:01 -03:00
Arthur Chien
f7994667e5 Fix encoding issue when loading YAML file (#1316)
related to #1270

Co-authored-by: ccw@cht.com.tw <ccw@cht.com.tw>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-09-22 16:50:50 -03:00
João Moura
f8169b74f1 updating dependencies 2024-09-22 16:47:57 -03:00
João Moura
cf74f5c9b6 fix test 2024-09-22 13:57:52 -03:00
FabioPolito24
f8a48a1389 Refactor: Remove redundant task creation in kickoff_for_each_async (#1326)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2024-09-22 10:42:05 -04:00
João Moura
76d0ec9f46 respecting OPENAI_MODEL_NAME 2024-09-22 11:20:54 -03:00
João Moura
08ed84dc21 bringin back gpt-4o-mini as default 2024-09-22 11:15:17 -03:00
Rip&Tear
5051e0b55e Merge pull request #1335 from lloydchang/patch-1
docs(Start-a-New-CrewAI-Project-Template-Method.md): fix typo
2024-09-22 18:11:18 +08:00
lloydchang
bc85480dd8 docs(Start-a-New-CrewAI-Project-Template-Method.md): fix typo
agents → tasks
2024-09-18 03:17:22 -07:00
João Moura
4f2806f5ba preparing new version 2024-09-18 04:36:05 -03:00
João Moura
2340de3c12 printing max rpm message in different color 2024-09-18 04:35:18 -03:00
João Moura
51b9e251dd Updating all cassetes 2024-09-18 04:17:41 -03:00
João Moura
25147476f7 always ending on a user message 2024-09-18 04:17:20 -03:00
João Moura
71f272b2b2 updating dependenceis 2024-09-18 03:26:46 -03:00
João Moura
213d245f4a preparing new version 2024-09-18 03:24:20 -03:00
João Moura
20a635970f quick bug fixes 2024-09-18 03:22:56 -03:00
João Moura
ae0c84cea6 Removing LangChain and Rebuilding Executor (#1322)
* rebuilding executor

* removing langchain

* Making all tests good

* fixing types and adding ability for nor using system prompts

* improving types

* pleasing the types gods

* pleasing the types gods

* fixing parser, tools and executor

* making sure all tests pass

* final pass

* fixing type

* Updating Docs

* preparing to cut new version
2024-09-16 14:14:04 -03:00
Paul Nugent
38189fb555 Merge pull request #1315 from crewAIInc/docs_update
update readme.md
2024-09-10 15:26:00 +01:00
Rip&Tear
4efc29db63 update readme.md 2024-09-10 21:56:46 +08:00
João Moura
fe7583413f preparing enw version with deploy 2024-09-07 11:17:12 -07:00
João Moura
ede37bc07e preparing new verison 0.55.1 2024-09-07 10:16:07 -07:00
João Moura
8306e49fb7 updating dependencies 2024-09-07 00:55:21 -07:00
João Moura
e6aea0304f preparing to cut new version 2024-09-07 00:34:34 -07:00
Sean
262637c3a4 Update LLM-Connections.md (#1181)
* Update LLM-Connections.md

* Update LLM-Connections.md

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-09-07 04:31:09 -03:00
Brandon Hancock (bhancock_ai)
1ac64b8852 Update regex (#1228) 2024-09-07 04:27:58 -03:00
Brandon Hancock (bhancock_ai)
7cc143624c add in 2 small improvements based on joao feedback (#1264) 2024-09-07 04:13:23 -03:00
Astha Puri
0fd5c7bab0 Update Start-a-New-CrewAI-Project-Template-Method.md (#1276)
* Update Start-a-New-CrewAI-Project-Template-Method.md

* Update Start-a-New-CrewAI-Project-Template-Method.md

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-09-07 04:12:51 -03:00
Astha Puri
87e4188e91 Add missing virtual environment commands (#1277)
* Add missing virtual environment commands

* Update Start-a-New-CrewAI-Project-Template-Method.md

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-09-07 04:12:04 -03:00
Astha Puri
638134fda3 Update Tasks.md (#1279) 2024-09-07 04:05:56 -03:00
Rip&Tear
284c085cdd Update readme.md (#1294)
* Update pyproject.toml

More GH link updates

* Added FAQ section in README.md

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-09-07 03:59:48 -03:00
Ali Waleed
f2ed29a511 Fix: Langtrace Docs (#1297)
* fix langtrace docs

* remove gif for size constraint
2024-09-07 03:58:27 -03:00
Brandon Hancock (bhancock_ai)
14544c8fe9 Brandon/cre 256 default template crew isnt running properly (#1299)
* Update config typecheck to accept agents

* Clean up prints
2024-09-07 03:57:36 -03:00
anmol-aidora
64354ac66d Updated CrewAI Documentation and Repository link in tools.poetry.urls (#1305)
* Updated CrewAI Documentation and Repository link in tools.poetry.urls

* Update pyproject.toml

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-09-07 03:55:02 -03:00
Brandon Hancock (bhancock_ai)
a234eb8baa Brandon/cre 252 add agent to crewai test (#1308)
* Update config typecheck to accept agents

* Clean up prints

* Adding agents to crew evaluator output table

* Properly generating table now

* Update tests
2024-09-07 03:53:23 -03:00
Brandon Hancock (bhancock_ai)
01124daf55 move away from pydantic v1 (#1284) 2024-09-06 14:22:01 -04:00
Paul Nugent
41a61e6d82 Merge pull request #1290 from crewAIInc/DOCS/readme_update
Docs/readme update
2024-09-06 16:18:31 +01:00
Rip&Tear
3ef9a41f48 Revert "feat: Improve documentation for Conditional Tasks in crewAI"
This reverts commit 2527ba9074.
2024-09-05 10:30:08 +08:00
Rip&Tear
172557684a Revert "docs: Improve "Creating and Utilizing Tools in crewAI" documentation"
This reverts commit a65598bc72.
2024-09-05 10:30:00 +08:00
Rip&Tear
8b732247cd Revert "feat: Improve documentation for TXTSearchTool"
This reverts commit f7015763d4.
2024-09-05 10:29:03 +08:00
Rip&Tear
b9b75c7e1d feat: Improve documentation for TXTSearchTool
Updated wording positioning
2024-09-05 10:27:11 +08:00
Rip&Tear
0c59f8ea57 Update README.md
Updated  GitHub links to point to new Repos
2024-09-05 10:17:46 +08:00
Rip&Tear (aider)
f7015763d4 feat: Improve documentation for TXTSearchTool 2024-09-05 00:06:11 +08:00
Rip&Tear (aider)
a65598bc72 docs: Improve "Creating and Utilizing Tools in crewAI" documentation 2024-09-04 18:31:09 +08:00
Rip&Tear (aider)
2527ba9074 feat: Improve documentation for Conditional Tasks in crewAI 2024-09-04 18:26:12 +08:00
Rip&Tear
ca8535a74b Merge pull request #1273 from Astha0024/main
Update README.md with default model
2024-09-01 00:43:40 +08:00
Astha Puri
a1698744d4 Merge branch 'main' into main 2024-08-30 21:58:02 -04:00
Thiago Moretto
a092c7f2e6 Merge pull request #1269 from crewAIInc/tm-fix-cli-for-py310
Add py 3.10 support back to CLI + fixes
2024-08-30 13:39:04 -03:00
Thiago Moretto
36cb08c062 Add comment to warn about dro simple_toml_parser 2024-08-30 11:52:53 -03:00
Astha Puri
2f4fd36eb1 Update README.md 2024-08-30 06:55:31 -04:00
Astha Puri
ef2b783be0 Update README.md 2024-08-30 06:54:34 -04:00
João Moura
1dcb9934b7 preparing new version 2024-08-30 00:33:51 -03:00
João Moura
7a828f9ad9 updating deployment cli with 2024-08-30 00:32:18 -03:00
João Moura
d03b89486d updating docs 2024-08-30 00:15:06 -03:00
João Moura
2f2945169d removing base_model from telemetry 2024-08-29 23:35:05 -03:00
Thiago Moretto
d305c45273 Fix test 2024-08-29 15:58:47 -03:00
Thiago Moretto
b0e410f10e Read as str no bytes
+handle when project_name is None (fails, basically)
2024-08-29 15:17:51 -03:00
Thiago Moretto
a0b8431ac7 Fix type checking + lint 2024-08-29 15:02:19 -03:00
Thiago Moretto
329027c2b8 Add python 3.10 support back to CLI +fixes 2024-08-29 14:37:34 -03:00
Thiago Moretto
2230279e05 Get current crewai version from poetry.lock 2024-08-29 11:14:04 -03:00
Thiago Moretto
b1ce3d57f0 Add Python 3.10 support to CLI 2024-08-29 10:22:54 -03:00
mvanwyk
d6034cebaa bug: fix incorrect mkdocs site_url (#1238)
* bug: fix incorrect mkdocs site_url

* bug: fix incorrect mkdocs repo_url

Co-authored-by: Eduardo Chiarotti <dudumelgaco@hotmail.com>

---------

Co-authored-by: Eduardo Chiarotti <dudumelgaco@hotmail.com>
2024-08-24 15:45:59 -03:00
Brandon Hancock (bhancock_ai)
d73fd96ee5 Fix deployment name issue to support Azure (#1253)
* Fix deployment name issue to support Azure

* More carefully check atters on llm
2024-08-23 12:58:37 -04:00
Brandon Hancock (bhancock_ai)
e838638bef Update async docs with more examples (#1254)
* Update async docs with more examples

* Add use cases
2024-08-23 12:51:58 -04:00
Eduardo Chiarotti
87d88e26ee fix: All files pre commit (#1249) 2024-08-23 10:52:36 -03:00
Paul Nugent
f9be04c311 Update LLM-Connections.md (#1190)
Added missing quotes around os.environ

Co-authored-by: Eduardo Chiarotti <dudumelgaco@hotmail.com>
2024-08-23 10:39:06 -03:00
Eduardo Chiarotti
a962896d0e Feat/cli deploy (#1240)
* feat: set basic structure deploy commands

* feat: add first iteration of CLI Deploy

* feat: some minor refactor

* feat: Add api, Deploy command and update cli

* feat: Remove test token

* feat: add auth0 lib, update cli and improve code

* feat: update code and decouple auth

* fix: parts of the code

* feat: Add token manager to encrypt access token and get and save tokens

* feat: add audience to costants

* feat: add subsystem saving credentials and remove comment of type hinting

* feat: add get crew version to send on header of request

* feat: add docstrings

* feat: add tests for authentication module

* feat: add tests for utils

* feat: add unit tests for cl

* feat: add tests

* feat: add deploy man tests

* feat: fix type checking issue

* feat: rename tests to pass ci

* feat: fix pr issues

* feat: fix get crewai versoin

* fix: add timeout for tests.yml
2024-08-23 10:20:03 -03:00
Rip&Tear
c0c1302611 Merge pull request #1239 from ShuHuang/patch-1
Bugfix: Update LLM-Connections.md
2024-08-23 09:49:46 +08:00
Shu Huang
e0c1af14bd Bugfix: Update LLM-Connections.md
The original code doesn't work due to a comma
2024-08-22 14:39:15 +01:00
Brandon Hancock (bhancock_ai)
45a5e12ff8 Brandon/cre 211 fix agent and task config for yaml based projects (#1211)
* Fixed agents. Now need to fix tasks.

* Add type fixes and fix task decorator

* Clean up logs

* fix more type errors

* Revert back to required

* Undo changes.

* Remove default none for properties that cannot be none

* Clean up comments

* Implement all of Guis feedback
2024-08-20 09:31:02 -04:00
William Espegren
afa2847b3f docs: add spider docs (#1165)
* docs: add spider docs

* chore: add "Spider scraper" to mkdocs.yml
2024-08-20 07:53:04 -03:00
Rip&Tear
122dd945fe Merge pull request #1216 from theCyberTech/main 2024-08-20 18:32:04 +08:00
Eduardo Chiarotti
e684e06809 feat: Add only on release to deploy docs (#1212) 2024-08-20 07:26:50 -03:00
Rip&Tear
cc9620f7fd Merge pull request #2 from theCyberTech/theCyberTech-operations-per-run
Update operations-per-run in stale.yml
2024-08-20 12:54:55 +08:00
Rip&Tear
d4784507d0 Update operations-per-run in stale.yml
operations-per-run: 1200

this will allow for complete cleanup of all exiting issues
2024-08-20 12:54:26 +08:00
Rip&Tear
dbde306639 Merge pull request #1206 from theCyberTech/main
Create Cli.md
2024-08-17 21:51:13 +08:00
Rip&Tear
e4f01f4906 Update Cli.md 2024-08-17 20:55:46 +08:00
Rip&Tear
6ec2070936 Create Cli.md
Added initial Cli.md to help users get info on Cli commands
2024-08-17 20:06:31 +08:00
Rip&Tear
46e5929622 Merge pull request #1205 from theCyberTech/theCyberTech-stale-fix
Update stale.yml
2024-08-17 20:00:43 +08:00
Eduardo Chiarotti
ef2502a14f feat: Add crewai install CLI command (#1203)
* feat: Add crewai install CLI command

* feat: Add crewai install to the docs and force now crewai run
2024-08-17 08:41:53 -03:00
Rip&Tear
7fd6ef7012 Update stale.yml
Added  
operations-per-run: 500
2024-08-17 19:16:31 +08:00
Rip&Tear
dbede37121 Merge pull request #1194 from crewAIInc/docs_update
Updated Documentation to fix minor issues + minor .github fixes
2024-08-17 08:14:17 +08:00
Brandon Hancock (bhancock_ai)
678dfffb62 Adding Autocomplete to OSS (#1198)
* Cleaned up model_config

* Fix pydantic issues

* 99% done with autocomplete

* fixed test issues

* Fix type checking issues
2024-08-16 15:04:21 -04:00
Brandon Hancock (bhancock_ai)
c511f4d0b5 Clean up pipeline (#1187)
* Clean up pipeline

* Make versioning dynamic in templates

* fix .env issues when openai is trying to use invalid keys

* Fix type checker issue in pipeline

* Fix tests.
2024-08-16 14:47:28 -04:00
Vini Brasil
8fdf741b73 Add name and expected_output to TaskOutput (#1199)
* Add name and expected_output to TaskOutput

This commit adds task information to the TaskOutput class. This is
useful to provide extra context to callbacks.

* Populate task name from function names

This commit populates task name from function names when using
annotations.
2024-08-15 22:24:41 +01:00
Eduardo Chiarotti
a5d8ca7b16 feat: Add bandit ci pipeline (#1200)
* feat: Add bandit ci pipeline

* feat: add useforsecurty false for bandit pipeline

* feat: Add report only for High severity issues
2024-08-15 18:19:57 -03:00
theCyberTech
a6f433597c Updated Documentaion to fix navigation link for pipelin feature, removed legacy md fiel from .github & added missing config.yml config to remove custom issues from user access 2024-08-15 16:35:05 +08:00
Rip&Tear
323790384c Merge pull request #1183 from crewAIInc/feature-templates
Feature templates
2024-08-15 11:29:36 +08:00
Rip&Tear
44068c8779 Merge pull request #1182 from crewAIInc/git-temaplates
updated bug report template to yml for more control
2024-08-15 11:28:31 +08:00
Eduardo Chiarotti
dedab16ff1 fix: Fix planning_llm issue (#1189)
* fix: Fix planning_llm issue

* fix: add poetry.lock updated version

* fix: type checking issues

* fix: tests
2024-08-14 18:54:53 -03:00
theCyberTech
b279b84a55 Addded feature request template in YAML format
Added config .yml to remove blank template
2024-08-14 15:49:55 +08:00
theCyberTech
9e16df200c updated bug report template to yml for more control 2024-08-14 15:08:59 +08:00
Eduardo Chiarotti
ac97aafd78 docs: fix references to annotations (#1176) 2024-08-13 12:58:12 -03:00
Eduardo Chiarotti
08eaffbb7c docs: Update Dalle, FileWrite, Nl2Sql and Side menu Tools (#1175)
* docs: Update Dalle, FileWrite, Nl2Sql and Side menu Tools

* docs: remove unused phrase

* docs: fix identation
2024-08-13 12:29:34 -03:00
Rafael Miller
c1ae3a64ed Added Firecrawl tools to docs (#628) 2024-08-13 12:09:11 -03:00
João Moura
bce7bb793c preparing new version 2024-08-11 22:07:54 -03:00
João Moura
ff3ad45de9 Fixing telemetry condition that was missing 2024-08-11 22:07:45 -03:00
João Moura
fcacebb60f fix broken link 2024-08-11 15:52:25 -03:00
João Moura
3879cbb897 adding new docs 2024-08-11 15:50:42 -03:00
João Moura
61b3d04d0d adding testing link 2024-08-11 15:39:30 -03:00
João Moura
81a16a3e01 Updating docs 2024-08-11 15:04:45 -03:00
João Moura
a579da3b5f preparing new version 2024-08-11 01:33:20 -03:00
João Moura
277a217b31 Fixing evaluator reporter 2024-08-11 01:32:40 -03:00
João Moura
e81f4a1f35 Updating templates to new versions 2024-08-11 01:02:47 -03:00
João Moura
11d39b3f23 Preparing new version 2024-08-11 00:58:41 -03:00
João Moura
d96f20d0ef adding docs for new tools 2024-08-11 00:07:00 -03:00
João Moura
8eca3dae14 preparing new verion 2024-08-10 17:59:17 -03:00
João Moura
00997e5453 missing arg 2024-08-10 17:58:54 -03:00
João Moura
69df8245c9 fixing mock_agent_ops_provider 2024-08-10 17:26:45 -03:00
João Moura
ac48b7a669 fixing mock_agent_ops_provider 2024-08-10 17:21:21 -03:00
Abebe M.
b80ea04fe1 Handle minor issue: tools name shouldn't contain space for openai (#961)
As per (https://github.com/langchain-ai/langchain/pull/16395), OpenAI functions don't accept tool names with space. Therefore, I added an exception handling snippet to raise an issue if a custom tool name has a space.
2024-08-10 16:51:08 -03:00
Joshua Harper
817a838015 Sanitize agent roles to ensure valid directory names (#1037) 2024-08-10 09:50:38 -03:00
Vikram Guhan Subbiah
c0005e112e AgentOps ENG-525: Decouple CrewAI and AgentOps (#1033)
* Make AgentOps import optional upon AGENTOPS_API_KEY
    being set

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-08-10 09:47:13 -03:00
David
d1770b3749 remove broken links (#1043) 2024-08-10 09:45:21 -03:00
Jason Wu
bf87f3d5d3 Update AgentOps-Observability.md (#1044)
Fix the incorrectly formatted external link
2024-08-10 09:43:22 -03:00
Thiago Moretto
59faec2404 Increase test coverage for output to file (#1049) 2024-08-10 09:42:47 -03:00
Constantin Schreiber
276a7e5acc Update Start-a-New-CrewAI-Project-Template-Method.md (#1054)
Fixed grammar and typo

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-08-10 09:39:49 -03:00
fastali
fde60b0973 Update LLM-Connections.md (#1071)
ollama integration example code bug fixed.
2024-08-10 08:56:30 -03:00
Chris Johnston
5a8ce2b05c Update Start-a-New-CrewAI-Project-Template-Method.md (#1081)
I helped 💚
2024-08-10 08:55:39 -03:00
maf-rnmourao
5e1a9dd2ba Fix misplaced task info from process doc (#1098)
Co-authored-by: rnmourao <robertonunesmourao@yahoo.com.br>
2024-08-10 08:55:18 -03:00
Giulio De Luise
70452af9db Fix documentation typo. (#1153) 2024-08-10 08:54:40 -03:00
Muhammad Hakim Asy'ari
48edf67cad Remove orphan links (#1163)
Remove deprecated links, related to #1019
2024-08-10 08:54:12 -03:00
João Moura
17fbc74f34 preparing new verison 2024-08-10 03:28:53 -07:00
João Moura
96aba70531 adding test results telemetry 2024-08-10 03:13:11 -07:00
Eduardo Chiarotti
b4221ea560 feat: add ability to train on custom file (#1161)
* feat: add ability to train on custom file

* feat: add pkl file validation

* feat: fix tests

* feat: fix tests

* feat: fix tests
2024-08-09 19:41:58 -03:00
Lorenze Jay
4c122321ad Brandon/cre 130 pipeline project structure (#1066)
* WIP. Procedure appears to be working well. Working on mocking properly for tests

* All tests are passing now

* rshift working

* Add back in Gui's tool_usage fix

* WIP

* Going to start refactoring for pipeline_output

* Update terminology

* new pipeline flow with traces and usage metrics working. need to add more tests and make sure PipelineOutput behaves likew CrewOutput

* Fix pipelineoutput to look more like crewoutput and taskoutput

* Implemented additional tests for pipeline. One test is failing. Need team support

* Update docs for pipeline

* Update pipeline to properly process input and ouput dictionary

* Update Pipeline docs

* Add back in commentary at top of pipeline file

* Starting to work on router

* Drop router for now. will add in separately

* In the middle of fixing router. A ton of circular dependencies. Moving over to a new design.

* WIP.

* Fix circular dependencies and updated PipelineRouter

* Add in Eduardo feedback. Still need to add in more commentary describing the design decisions for pipeline

* Add developer notes to explain what is going on in pipelines.

* Add doc strings

* Fix missing rag datatype

* WIP. Converting usage metrics from a dict to an object

* Fix tests that were checking usage metrics

* Drop todo

* Fix 1 type error in pipeline

* Update pipeline to use UsageMetric

* Add missing doc string

* WIP.

* Change names

* Rename variables based on joaos feedback

* Fix critical circular dependency issues. Now needing to fix trace issue.

* Tests working now!

* Add more tests which showed underlying issue with traces

* Fix tests

* Remove overly complicated test

* Add router example to docs

* Clean up end of docs

* Clean up docs

* Working on creating Crew templates and pipeline templates

* WIP.

* WIP

* Fix poetry install from templates

* WIP

* Restructure

* changes for lorenze

* more todos

* WIP: create pipelines cli working

* wrapped up router

* ignore mypy src on templates

* ignored signature of copy

* fix all verbose

* rm print statements

* brought back correct folders

* fixes missing folders and then rm print statements

* fixed tests

* fixed broken test

* fixed type checker

* fixed type ignore

* ignore types for templates

* needed

* revert

* exclude only required

* rm type errors on templates

* rm excluding type checks for template files on github action

* fixed missing quotes

---------

Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2024-08-09 14:13:29 -07:00
Eduardo Chiarotti
c808f7bec9 Update issue templates (#1076)
* Update issue templates

* Update custom.md
2024-08-08 20:10:41 -03:00
Eduardo Chiarotti
34223c6576 Create stale.yml (#1158) 2024-08-08 11:54:13 -03:00
Eduardo Chiarotti
a38848097f feat: add cli to run the crew (#1080)
* feat: add cli to run the crew

* feat: change command to run_crew

* feat: change pyprojet to run_Crew

* docs: change docs to address crewai run
2024-08-08 10:48:22 -03:00
Lorenze Jay
8eea22c763 Fix logging types to bool (#1051)
* fixes pydantic validations hierarchical

* more tests

* logger logs everything or not

* verbose rm levels to bool

* updated readme verbose levels
2024-08-07 10:31:18 -07:00
Eduardo Chiarotti
033b6f23e3 Update issue templates (#1067)
* Update issue templates

Add both Bug and Feature templates

* Update feature_request.md
2024-08-06 14:47:00 -03:00
Thiago Moretto
b738f3e265 Merge pull request #1064 from crewAIInc/thiago/pipeline-fix
Fix flaky test due to suppressed error on `on_llm_start` callback
2024-08-05 16:13:19 -03:00
Thiago Moretto
7b62890113 Fix lint issue 2024-08-05 13:34:03 -03:00
Thiago Moretto
6d7e089be6 Fix flaky test due to suppressed error on on_llm_start callback 2024-08-05 13:29:39 -03:00
Rip&Tear
bf691af088 Update LLM-Connections.md (#1039)
* Minor fixes and updates

* minor fixes across docs

* Updated LLM-Connections.md

---------

Co-authored-by: theCyberTech <mattrapidb@gmail.com>
2024-08-02 15:04:52 -03:00
Rip&Tear
95e2e0bb8e Docs minor fixes (#1035)
* Minor fixes and updates

* minor fixes across docs

---------

Co-authored-by: theCyberTech <mattrapidb@gmail.com>
2024-08-02 15:01:16 -03:00
Lorenze Jay
071122791e Feat/sliding context window (#1042)
* patching for non-gpt model

* removal of json_object tool name assignment

* fixed issue for smaller models due to instructions prompt

* fixing for ollama llama3 models

* WIP: generated summary from documents split, could also create memgpt approach

* WIP: need tests but user inputted summarization strategy implemented - handling context window exceeding errors

* rm extra line

* removed type ignores

* added tests

* handling n to summarize prompt

* code cleanup, using click for cli asker

* rm not used class

* better refactor

* reverted poetry lock

* reverted poetry.locl

* improved context window exceeding exception class
2024-08-01 13:15:50 -07:00
João Moura
745ed5c8ae Preparing for new version 2024-07-30 19:21:18 -04:00
Lorenze Jay
38f9c3c500 WIP fixed mypy src types (#1036) 2024-07-30 10:59:50 -07:00
Eduardo Chiarotti
18d867aa47 feat: Add execution time to both task and testing feature (#1031)
* feat: Add execution time to both task and testing feature

* feat: Remove unused functions

* feat: change test_crew to evalaute_crew to avoid issues with testing libs

* feat: fix tests
2024-07-29 23:17:07 -03:00
Matt Young
c82f612c07 telemetry.py - fix typo in comment. (#1020) 2024-07-29 23:03:51 -03:00
Deepak Tammali
9c3e1a708f docs: Fix crewai-tools package name typo in getting-started docs (#1026) 2024-07-29 23:03:32 -03:00
Monarch Wadia
fa3af7db93 Fixed package name typo in pip install command (#1029)
Changed `pip install crewai-tools` to `pip install crewai-tools`
2024-07-29 23:02:48 -03:00
Mackensie Alvarez
7a70e393c4 Update Start-a-New-CrewAI-Project-Template-Method.md (#1030) 2024-07-29 23:02:18 -03:00
Brandon Hancock (bhancock_ai)
134be4984b Add in missing triple quote and execution time to resume agent functionality. (#1025)
* Add in missing triple quote and execution time to resume agent functionality

* Fixing broken kwargs and other issues causing our tests to fail
2024-07-29 14:39:02 -03:00
Rip&Tear
b8ff35f076 Minor fixes and updates (#1019)
Co-authored-by: theCyberTech <mattrapidb@gmail.com>
2024-07-29 03:24:23 -03:00
Rip&Tear
f8a09489f1 Small 404 error fixes (#1018)
* Updated Docs:  New Getting started section + content update / addition

* fixed indentation issue

* Minor updates to fix typos

* Fixed up 404 error on latest commit

---------

Co-authored-by: theCyberTech <the_t3ch@pm.me>
Co-authored-by: theCyberTech <mattrapidb@gmail.com>
2024-07-28 22:01:04 -03:00
Nuraly
496a4c087c Update Force-Tool-Ouput-as-Result.md (#964)
I think there is some mistake, because there is no such parameter as force_output_result, and as the code shows, the correct parameter result_as_answer is set during agent creation, not task.
2024-07-28 15:41:56 -03:00
Carine Bruyndoncx
93e0de2ed9 Update Crews.md - correct result variable to crew_output (#972) 2024-07-28 15:40:36 -03:00
Taleb
ca9deaebb7 Performed spell check across the rest of code base, and enahnced the yaml paraser code a little (#895)
* Performed spell check across the entire documentation

Thank you once again!

* Performed spell check across the most of code base
Folders been checked:
- agents
- cli
- memory
- project
- tasks
- telemetry
- tools
- translations

* Trying to add a max_token for the agents, so they limited by number of tokens.

* Performed spell check across the rest of code base, and enahnced the yaml paraser code a little

* Small change in the main agent doc

* Improve _save_file method to handle both dict and str inputs

- Add check for dict type input
- Use json.dump for dict serialization
- Convert non-dict inputs to string
- Remove type ignore comments

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-28 15:39:54 -03:00
Henri Wenlin
218b17f70f feat: add verbose option for printing in ToolUsage (#990) 2024-07-28 15:12:10 -03:00
Samuel Mallet
5626b72742 Add docs for new parameters to SerperDevTool (#993) 2024-07-28 15:09:55 -03:00
Taleb
a1e2ef376b Improve _save_file method to handle both dict and str inputs (#1011)
- Add check for dict type input
- Use json.dump for dict serialization
- Convert non-dict inputs to string
- Remove type ignore comments
2024-07-28 15:03:18 -03:00
Lennex Zinyando
9b2a113b58 Fixes getting started section links (#1016) 2024-07-28 15:02:41 -03:00
João Moura
32b1fb237b updating test 2024-07-28 13:23:03 -04:00
Rip&Tear
67179bbacb Docs update (#1008)
* Updated Docs:  New Getting started section + content update / addition

* fixed indentation issue

* Minor updates to fix typos

---------

Co-authored-by: theCyberTech <the_t3ch@pm.me>
2024-07-28 11:55:09 -03:00
ResearchAI
2b7a0b3342 Update reset_memories_command.py (#974) 2024-07-26 14:40:47 -07:00
Brandon Hancock (bhancock_ai)
5627159419 Json Task Output Truncation with Escape Characters (#1009)
* Fixed special character issue when converting json to models. Added numerous tests to ensure thigns work properly.

* Fix linting error and cleaned up tests

* Fix customer_converter_cls test failure

* Fixed tests. Thank you lorenze for pointing that out. added a few more to ensure converter creation works properly

* Address lorenze feedback

* Fix linting issues
2024-07-26 17:27:01 -04:00
Brandon Hancock (bhancock_ai)
7f5c4fded6 Merge pull request #1012 from crewAIInc/fix/breaking-test-task-eval
fix test due to asserting instructions model_schema change
2024-07-26 16:55:26 -04:00
Lorenze Jay
8054828aac fix test due to asserting instructions model_schema change 2024-07-26 13:37:44 -07:00
Lorenze Jay
67c2428495 Patch/non gpt model pydantic output (#1003)
* patching for non-gpt model

* removal of json_object tool name assignment

* fixed issue for smaller models due to instructions prompt

* fixing for ollama llama3 models

* closing brackets

* removed not used and fixes
2024-07-26 10:57:56 -07:00
Lorenze Jay
0c6514024e hierarchical process unblocked for async tasks (#995)
* WIP: hierarchical unblock for async tasks

* added better test

* update name change

* added more test and crew manager cleanup

* remove prints

* code cleanup, no need to pass manager
2024-07-26 10:55:51 -07:00
Eduardo Chiarotti
b415e2273a feat: add ability to set LLM for AgentPLanner on Crew (#1001)
* feat: add ability to set LLM for AgentPLanner on Crew

* feat: fixes issue on instantiating the ChatOpenAI on the crew

* docs: add docs for the planning_llm new parameter

* docs: change message to ChatOpenAI llm

* feat: add tests
2024-07-26 14:24:29 -03:00
Eduardo Chiarotti
56cb344c70 feat: add crew Testing/Evaluating feature (#998)
* feat: add crew Testing/evalauting feature

* feat: add docs and add unit test

* feat: improve testing output table

* feat: add tests

* feat: fix type checking issue

* feat: add raise ValueError when testing if output is not the expected

* docs: add docs for Testing

* feat: improve tests and fix some issue

* feat: back to sync

* feat: change opdeai model

* feat: fix test
2024-07-26 14:23:51 -03:00
Brandon Hancock (bhancock_ai)
b77cf9b279 Merge pull request #994 from crewAIInc/fix/getting-started-docs
fixed bullet points for crew yaml annoations
2024-07-23 14:36:45 -04:00
Lorenze Jay
5791325e63 clearer usage for crewai create command 2024-07-23 11:32:25 -07:00
Lorenze Jay
15e8593597 fixed bullet points for crew yaml annoations 2024-07-23 11:31:09 -07:00
Lorenze Jay
80c626504d Feat yaml config all attributes (#985)
* WIP: yaml proper mapping for agents and agent

* WIP: added output_json and output_pydantic setup

* WIP: core logic added, need cleanup

* code cleanup

* updated docs and example template to use yaml to reference agents within tasks

* cleanup type errors

* Update Start-a-New-CrewAI-Project.md

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-23 00:21:01 -03:00
Eduardo Chiarotti
21dea21e97 feat: add crewai test feature (#984)
* feat: add crewai test feature

* fix: remove unused import

* feat: update docstirng

* fix: tests
2024-07-22 17:21:05 -03:00
João Moura
0bbafe7e3b prepping new version 2024-07-20 12:26:32 -04:00
Eduardo Chiarotti
fa15c9012a fix: planning feature output (#969)
* fix: planning feature output

* fix: add validation for planning result
2024-07-20 11:56:53 -03:00
João Moura
16a949e7e4 preparing new verions 2024-07-19 13:22:28 -04:00
Eduardo Chiarotti
56fd603723 fix: agent missing fix (#966) 2024-07-19 13:15:33 -03:00
João Moura
67c06e5cef rmeoving extra logging 2024-07-19 01:16:15 -04:00
Dev Khant
78518f139d Docs: Update info about tools (#896) 2024-07-19 01:38:42 -03:00
ariel
4f3ae32eef Fix broken link to the installation guide (#912)
Updated the installation guide link to use the absolute URL instead of a relative path, ensuring it correctly points to 'https://docs.crewai.com/how-to/Installing-CrewAI/'.
2024-07-19 01:37:54 -03:00
Salman Faroz
da5faeb451 Update Crews.md (#889)
To solve :
I encountered an error while trying to use the tool. This was the error: DuckDuckGoSearchRun._run() got an unexpected keyword argument 'q'.
 Tool duckduckgo_search accepts these inputs: A wrapper around DuckDuckGo Search. Useful for when you need to answer questions about current events. Input should be a search query.

refer : https://github.com/joaomdmoura/crewAI/issues/316
2024-07-19 01:37:24 -03:00
robbyriverside
341fcad9a4 Update Memory.md (#728)
The memory documentation left me with a lot of questions.  After I went through the code to find an answer.  I added this paragraph to explain what I found.  Hope this is helpful.
2024-07-19 01:36:54 -03:00
Braelyn Boynton
96ca81b593 upgrade agentops to 0.3 (#957)
* upgrade agentops to 0.3

* lockfile
2024-07-18 13:30:04 -03:00
Lorenze Jay
405d45c3fb Reset memory (#958)
* reseting memory on cli

* using storage.reset

* deleting memories on command

* added tests

* handle when no flags are used

* added docs
2024-07-18 13:29:42 -03:00
Eduardo Chiarotti
3f2f832e8d feat: Add planning feature to crew (#919)
* feat: add planning feature to crew

* feat: add test to planning handler and change to execute_async method

* docs: add planning parameter to the Core documentation

* docs: add planning docs

* fix: fix type checking issue

* fix: test and logic
2024-07-18 13:15:08 -03:00
Lorenze Jay
4f99ea547f Merge pull request #951 from crewAIInc/test-hierarchical-tools-proper-setup
Test hierarchical tools proper setup
2024-07-17 08:53:23 -07:00
Lorenze Jay
716d794092 better spacing 2024-07-17 08:40:52 -07:00
Lorenze Jay
9a1c19cfbd code cleanup 2024-07-17 08:39:57 -07:00
Lorenze Jay
868ee4ce87 using gpt4o 2024-07-17 08:27:43 -07:00
Lorenze Jay
f6cc5d4c92 Merge branch 'main' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-17 08:21:13 -07:00
Brandon Hancock (bhancock_ai)
da59bb22e6 Merge pull request #954 from crewAIInc/hotfix/improve-async-logging
Fix logging for async and sync tasks
2024-07-17 11:20:13 -04:00
Lorenze Jay
e58b0a8d70 fixed test 2024-07-17 08:20:05 -07:00
Brandon Hancock
20863079fc Merge branch 'main' into hotfix/improve-async-logging 2024-07-17 11:17:23 -04:00
Lorenze Jay
547729cdd7 Merge branch 'main' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-17 08:16:44 -07:00
Brandon Hancock (bhancock_ai)
69867bc77e Merge pull request #950 from crewAIInc/conditional-task-f
conditional task feat
2024-07-17 11:08:06 -04:00
Brandon Hancock
c4164440ca Fix issues found by linter 2024-07-17 11:05:31 -04:00
Brandon Hancock
9777bf984f Add more tests. Clean up docs. Improve conditional task 2024-07-17 11:03:11 -04:00
Brandon Hancock
80d6596247 Fix logging 2024-07-17 10:10:34 -04:00
João Moura
a1b37f073d Adding better support for open source tool calling models (#952)
* Adding better support for open source tool calling models

* making sure the right tool is called

* fixing tests

* better support opensource models
2024-07-17 05:54:13 -03:00
Lorenze Jay
d261d68527 Merge branch 'conditional-task-f' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 20:35:27 -07:00
Lorenze Jay
d5ae6a6f59 Merge branch 'main' of github.com:joaomdmoura/crewAI into conditional-task-f 2024-07-16 20:34:35 -07:00
Lorenze Jay
36b7d03612 Merge branch 'test-hierarchical-tools-proper-setup' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 20:31:42 -07:00
Lorenze Jay
39ab81ea83 Merge branch 'conditional-task-f' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 20:28:50 -07:00
Lorenze Jay
dae39d37e9 code cleanup 2024-07-16 20:11:52 -07:00
Lorenze Jay
615cc03b9f code cleanup 2024-07-16 20:07:05 -07:00
Brandon Hancock (bhancock_ai)
d4d9d475b0 Merge pull request #941 from crewAIInc/bugfix/minor-max-retry-recursion-fix
Properly capture result from max retry recursive call
2024-07-16 22:05:58 -04:00
Lorenze Jay
8b5948d307 Merge branch 'conditional-task-f' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 16:05:09 -07:00
Lorenze Jay
510472db93 added docs and tests 2024-07-16 16:04:41 -07:00
Lorenze Jay
dcc8a671b8 Merge branch 'conditional-task-f' of github.com:joaomdmoura/crewAI into test-hierarchical-tools-proper-setup 2024-07-16 15:20:46 -07:00
Lorenze Jay
101bbc8954 ensures _update_manager_tools has a manager otherwise throw error 2024-07-16 15:15:50 -07:00
Lorenze Jay
e329e09b58 updated fixes for conditional tasks 2024-07-16 15:10:13 -07:00
Lorenze Jay
8833dc4451 fixed hierarchial manager tools when assigned an agent 2024-07-16 14:00:25 -07:00
Lorenze Jay
8710e6f545 better code spacing 2024-07-16 13:07:31 -07:00
Lorenze Jay
32491a156f removing unused code 2024-07-16 13:06:50 -07:00
Lorenze Jay
c373d6136f conditional task feat 2024-07-16 12:04:34 -07:00
Brandon Hancock (bhancock_ai)
c1be369566 Add docs for crewoutput and taskoutput (#943)
* Add docs for crewoutput and taskoutput

* Add reference to change log
2024-07-15 21:39:15 -03:00
Gui Vieira
02f6da700a Introduce structure keys (#902)
* Introduce structure keys

* Add agent key to tasks

* Rebasing is hard

* Rename task output telemetry

* Feedback
2024-07-15 19:37:07 -03:00
Gui Vieira
18fe9fc921 Fix crew creation telemetry (#939)
* Fix crew creation telemetry

* Remove task index
2024-07-15 17:43:57 -03:00
Lorenze Jay
387528c3fb Replay feat using db (#930)
* Cleaned up task execution to now have separate paths for async and sync execution. Updating all kickoff functions to return CrewOutput. WIP. Waiting for Joao feedback on async task execution with task_output

* Consistently storing async and sync output for context

* outline tests I need to create going forward

* Major rehaul of TaskOutput and CrewOutput. Updated all tests to work with new change. Need to add in a few final tricky async tests and add a few more to verify output types on TaskOutput and CrewOutput.

* Encountering issues with callback. Need to test on main. WIP

* working on tests. WIP

* WIP. Figuring out disconnect issue.

* Cleaned up logs now that I've isolated the issue to the LLM

* more wip.

* WIP. It looks like usage metrics has always been broken for async

* Update parent crew who is managing for_each loop

* Merge in main to bugfix/kickoff-for-each-usage-metrics

* Clean up code for review

* Add new tests

* Final cleanup. Ready for review.

* Moving copy functionality from Agent to BaseAgent

* Fix renaming issue

* Fix linting errors

* use BaseAgent instead of Agent where applicable

* Fixing missing function. Working on tests.

* WIP. Needing team to review change

* Fixing issues brought about by merge

* WIP: need to fix json encoder

* WIP need to fix encoder

* WIP

* WIP: replay working with async. need to add tests

* Implement major fixes from yesterdays group conversation. Now working on tests.

* The majority of tasks are working now. Need to fix converter class

* Fix final failing test

* Fix linting and type-checker issues

* Add more tests to fully test CrewOutput and TaskOutput changes

* Add in validation for async cannot depend on other async tasks.

* WIP: working replay feat fixing inputs, need tests

* WIP: core logic of seq and heir for executing tasks added into one

* Update validators and tests

* better logic for seq and hier

* replay working for both seq and hier just need tests

* fixed context

* added cli command + code cleanup TODO: need better refactoring

* refactoring for cleaner code

* added better tests

* removed todo comments and fixed some tests

* fix logging now all tests should pass

* cleaner code

* ensure replay is delcared when replaying specific tasks

* ensure hierarchical works

* better typing for stored_outputs and separated task_output_handler

* added better tests

* added replay feature to crew docs

* easier cli command name

* fixing changes

* using sqllite instead of .json file for logging previous task_outputs

* tools fix

* added to docs and fixed tests

* fixed .db

* fixed docs and removed unneeded comments

* separating ltm and replay db

* fixed printing colors

* added how to doc

---------

Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2024-07-15 17:14:10 -03:00
Gui Vieira
39587aa3f9 Fix tool usage (#925)
* Fix tool usage

* new tests

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-15 17:13:35 -03:00
Brandon Hancock
4f1bde0cfe capture result from recursive call 2024-07-15 13:59:58 -04:00
Brandon Hancock
a118d49bb1 Add return statement to recursive call 2024-07-15 13:40:51 -04:00
Gui Vieira
fbae4909a0 [DO NOT MERGE] Provide inputs on crew creation (#898)
* Provide inputs on crew creation

* Better naming

* Add crew id and task index to tasks

* Fix type again
2024-07-15 09:00:02 -03:00
Eduardo Chiarotti
bc8cb4984a feat: add max retry limit to agent execution (#899)
* feat: add max retry limit to agent execution

* feat: add test to max retry limit feature

* feat: add code execution docstring

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-15 08:58:50 -03:00
Brandon Hancock (bhancock_ai)
93d6655228 Feature/use converter instead of manually trimming (#894)
* Exploring output being passed to tool selector to see if we can better format data

* WIP. Adding JSON repair functionality

* Almost done implementing JSON repair. Testing fixes vs current base case.

* More action cleanup with additional tests

* WIP. Trying to figure out what is going on with tool descriptions

* Update tool description generation

* WIP. Trying to find out what is causing the tools to duplicate

* Replacing tools properly instead of duplicating them accidentally

* Fixing issues for MR

* Update dependencies for JSON_REPAIR

* More cleaning up pull request

* preppering for call

* Fix type-checking issues

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-15 08:53:41 -03:00
OP (oppenheimer)
e525b87fd3 Add Groq - OpenAI Compatible API - details (#934) 2024-07-14 16:11:54 -03:00
Brandon Hancock (bhancock_ai)
2fcaf68312 Feature/kickoff consistent output (#847)
* Cleaned up task execution to now have separate paths for async and sync execution. Updating all kickoff functions to return CrewOutput. WIP. Waiting for Joao feedback on async task execution with task_output

* Consistently storing async and sync output for context

* outline tests I need to create going forward

* Major rehaul of TaskOutput and CrewOutput. Updated all tests to work with new change. Need to add in a few final tricky async tests and add a few more to verify output types on TaskOutput and CrewOutput.

* Encountering issues with callback. Need to test on main. WIP

* working on tests. WIP

* WIP. Figuring out disconnect issue.

* Cleaned up logs now that I've isolated the issue to the LLM

* more wip.

* WIP. It looks like usage metrics has always been broken for async

* Update parent crew who is managing for_each loop

* Merge in main to bugfix/kickoff-for-each-usage-metrics

* Clean up code for review

* Add new tests

* Final cleanup. Ready for review.

* Moving copy functionality from Agent to BaseAgent

* Fix renaming issue

* Fix linting errors

* use BaseAgent instead of Agent where applicable

* Fixing missing function. Working on tests.

* WIP. Needing team to review change

* Fixing issues brought about by merge

* WIP

* Implement major fixes from yesterdays group conversation. Now working on tests.

* The majority of tasks are working now. Need to fix converter class

* Fix final failing test

* Fix linting and type-checker issues

* Add more tests to fully test CrewOutput and TaskOutput changes

* Add in validation for async cannot depend on other async tasks.

* Update validators and tests
2024-07-11 00:35:02 -03:00
João Moura
ca22a91b8a adding new docs 2024-07-08 03:15:14 -04:00
prime-computing-lab
c7e1376c4b Update MDXSearchTool.md (#745)
description fixed to markdown language instead of marketing search
2024-07-08 02:21:00 -03:00
João Moura
aa79050a43 updating crewAI-tools verison 2024-07-08 01:17:22 -04:00
Taleb
ea5811735a Performed spell check across most of code base (#882)
* Performed spell check across the entire documentation

Thank you once again!

* Performed spell check across the most of code base
Folders been checked:
- agents
- cli
- memory
- project
- tasks
- telemetry
- tools
- translations
2024-07-07 13:00:05 -03:00
WellyngtonF
33ece82e08 passing cloned agents when copying context (#885) 2024-07-07 12:58:38 -03:00
Gui Vieira
b56d584efc Emit task created (#875)
* Emit task created

* Limit data to shared crews
2024-07-07 12:58:24 -03:00
João Moura
51068ce766 TYPO 2024-07-06 20:03:54 -04:00
João Moura
87e39faa33 new docs 2024-07-06 16:32:00 -04:00
João Moura
a5662909cf preparing new version 2024-07-06 12:26:41 -04:00
João Moura
325a582330 updating dependencies and fixing tests (#878) 2024-07-06 02:14:52 -03:00
Eelke van den Bos
2aa9904392 Add converter_cls option to Task (#800)
* Add converter_cls option to Task

Fixes #799

* Update task_test.py

* Update task.py

* Update task.py

* Update task_test.py

* Update task.py

* Update task.py

* Update task.py

* Update task.py

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-06 02:01:39 -03:00
João Moura
b65eee45a8 TYPO 2024-07-06 00:34:50 -04:00
Ikko Eltociear Ashimine
42708d60bc chore: fix typo (#810)
* chore: update converter.py

attemps -> attempts

* chore: update tool_usage.py

attemps -> attempts
2024-07-06 01:33:48 -03:00
Alex Brinsmead
75feeabc3c Fix incorrect definition of RAG in GithubTool docs (#864) 2024-07-06 01:31:51 -03:00
Taleb
f36a0b3b9c Performed spell check across the entire documentation (#872)
Thank you once again!
2024-07-06 01:30:40 -03:00
Eduardo Chiarotti
57041af313 Fix/async tasks (#877)
* fix: async tasks calls

* fix: some issue along with some type check errors

* fix: some issue along with some type check errors

* fix: async test
2024-07-06 01:30:07 -03:00
Eduardo Chiarotti
8dfc40ff98 fix: Fix tests (#873)
* fix: call asserts

* fix: test_increment_tool_errors

* fix: test_increment_delegations_for_sequential_process

* fix: test_increment_delegations_for_hierarchical_process

* fix: test_code_execution_flag_adds_code_tool_upon_kickoff

* fix: test_tool_usage_information_is_appended_to_agent

* fix: try to fix test_crew_full_output

* fix: try to fix test_crew_full_output

* fix: test remove vcr to test crew_test test

* fix: comment test to see if ci passes

* fix: comment test to see if ci passes

* fix: test changing prompt tokens to get error on CI

* fix: test changing prompt tokens to get error on CI

* fix: test changing prompt tokens to get error on CI

* fix: test changing prompt tokens to get error on CI

* fix: test new approach

* fix: comment funciont not working in CI

* fix: github python version

* fix: remove need of vcr

* fix: fix and add comments for all type checking errors
2024-07-05 09:06:56 -03:00
João Moura
b51cf24f0f Adding support to force a tool return to be the final answer. (#867)
* Adding support to force a tool return to be the final answer.
This will at the end of the execution return the tool output.
It will return the output of the latest tool with the flag

* Update src/crewai/agent.py

Co-authored-by: Gui Vieira <guilherme_vieira@me.com>

* Update tests/agent_test.py

Co-authored-by: Gui Vieira <guilherme_vieira@me.com>

---------

Co-authored-by: Gui Vieira <guilherme_vieira@me.com>
2024-07-04 16:36:00 -03:00
MO Jr
45a4d15811 Update Crews.md (#868)
Fix misspelling
2024-07-04 16:35:07 -03:00
Eduardo Chiarotti
3d78ad4fff fix: file_handler issue (#869)
* fix: file_handler issue

* fix: add logic for the trained_agent data
2024-07-04 16:34:43 -03:00
João Moura
cc9e30ac23 TYPO 2024-07-03 18:41:52 -04:00
João Moura
4cb0d4e572 TYPO 2024-07-03 18:41:52 -04:00
João Moura
62e662a690 TYPO 2024-07-03 18:41:52 -04:00
João Moura
58bbff124b fix agentops attribute 2024-07-03 18:41:52 -04:00
Lorenze Jay
fae843a243 Lj/optional agent in task bug (#843)
* fixed bug for manager overriding task agent and then added pydanic valditors to sequential when no agent is added to task

* better test and fixed task.agent logic

* fixed tests and better validator message

* added validator for async_execution true in tasks whenever in hierarchical run
2024-07-03 18:45:53 -03:00
Brandon Hancock (bhancock_ai)
0b277e066d Bugfix/kickoff for each usage metrics (#844)
* WIP. Figuring out disconnect issue.

* Cleaned up logs now that I've isolated the issue to the LLM

* more wip.

* WIP. It looks like usage metrics has always been broken for async

* Update parent crew who is managing for_each loop

* Merge in main to bugfix/kickoff-for-each-usage-metrics

* Clean up code for review

* Add new tests

* Final cleanup. Ready for review.

* Moving copy functionality from Agent to BaseAgent

* Fix renaming issue

* Fix linting errors

* use BaseAgent instead of Agent where applicable
2024-07-03 15:30:53 -03:00
Alex Brinsmead
01b14ed3a7 Fix typos in EN "human_feedback" string (#859)
* Fix typo in EN "human_feedback" string

* Fix typos in EN "human_feedback" string
2024-07-03 15:26:58 -03:00
Taleb
e5f6374d98 Improved documentation for training module usage (#860)
- Added detailed steps for training the crew programmatically.
- Clarified the distinction between using the CLI and programmatic approaches.

This update makes it easier for users to understand how to train their crew both through the CLI and programmatically, whether using a UI or API endpoints.

Again Thank you to the author for the great project and the excellent foundation provided!
2024-07-03 15:26:32 -03:00
Brandon Hancock (bhancock_ai)
c9a639b057 Fix issue agentop poetry install issue (#863)
* Fix issue agentop poetry install issue

* Updated install requirements tests to fail if .lock becomes out of sync with poetry install. Cleaned up old issues that were merged back in.
2024-07-03 15:22:32 -03:00
Braelyn Boynton
75ecdae00e Add back AgentOps as Optional Dependency (#543)
* implements agentops with a langchain handler, agent tracking and tool call recording

* track tool usage

* end session after completion

* track tool usage time

* better tool and llm tracking

* code cleanup

* make agentops optional

* optional dependency usage

* remove telemetry code

* optional agentops

* agentops version bump

* remove org key

* true dependency

* add crew org key to agentops

* cleanup

* Update pyproject.toml

* Revert "true dependency"

This reverts commit e52e8e9568.

* Revert "cleanup"

This reverts commit 7f5635fb9e.

* optional parent key

* agentops 0.1.5

* Revert "Revert "cleanup""

This reverts commit cea33d9a5d.

* Revert "Revert "true dependency""

This reverts commit 4d1b460b

* cleanup

* Forcing version 0.1.5

* Update pyproject.toml

* agentops update

* noop

* add crew tag

* black formatting

* use langchain callback handler to support all LLMs

* agentops version bump

* track task evaluator

* merge upstream

* Fix typo in instruction en.json (#676)

* Enable search in docs (#663)

* Clarify text in docstring (#662)

* Update agent.py (#655)

Changed default model value from gpt-4 to gpt-4o.
Reasoning.
gpt-4 costs 30$ per million tokens while gpt-4o costs 5$.
This is more cost friendly for default option.

* Update README.md (#652)

Rework example so that if you use a custom LLM it doesn't throw code errors by uncommenting.

* Update BrowserbaseLoadTool.md (#647)

* Update crew.py (#644)

Fixed Type on line 53

* fixes #665 (#666)

* Added timestamp to logger (#646)

* Added timestamp to logger

Updated the logger.py file to include timestamps when logging output. For example:

 [2024-05-20 15:32:48][DEBUG]: == Working Agent: Researcher
 [2024-05-20 15:32:48][INFO]: == Starting Task: Research the topic
 [2024-05-20 15:33:22][DEBUG]: == [Researcher] Task output:

* Update tool_usage.py

* Revert "Update tool_usage.py"

This reverts commit 95d18d5b6f.

incorrect bramch for this commit

* support skip auto end session

* conditional protect agentops use

* fix crew logger bug

* fix crew logger bug

* Update crew.py

* Update tool_usage.py

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
Co-authored-by: Howard Gil <howardbgil@gmail.com>
Co-authored-by: Olivier Roberdet <niox5199@gmail.com>
Co-authored-by: Paul Sanders <psanders1@gmail.com>
Co-authored-by: Anudeep Kolluri <50168940+Anudeep-Kolluri@users.noreply.github.com>
Co-authored-by: Mike Heavers <heaversm@users.noreply.github.com>
Co-authored-by: Mish Ushakov <10400064+mishushakov@users.noreply.github.com>
Co-authored-by: theCyberTech - Rip&Tear <84775494+theCyberTech@users.noreply.github.com>
Co-authored-by: Saif Mahmud <60409889+vmsaif@users.noreply.github.com>
2024-07-02 21:52:15 -03:00
Salman Faroz
6848d813bf Update Sequential.md (#849)
To Resolve : 
pydantic_core._pydantic_core.ValidationError: 1 validation error for Task
expected_output
Field required [type=missing, input_value=, input_type=dict]
For further information visit https://errors.pydantic.dev/2.6/v/missing

"Expected Output" is mandatory now as it forces people to be specific about the expected result and get better result


refer : https://github.com/joaomdmoura/crewAI/issues/308
2024-07-02 21:17:53 -03:00
Taleb
138bb6169d Enhanced documentation for readability and clarity (#855)
- Added a "Parameters" column to attribute tables. Improved overall document formatting for enhanced readability and ease of use.

Thank you to the author for the great project and the excellent foundation provided!
2024-07-02 21:17:04 -03:00
Lorenze Jay
5f0af16616 fixed mixin (#831)
* fixed mixin

* WIP: fixing types

* type fixes on mixin
2024-07-02 21:16:26 -03:00
João Moura
9de4f0d9a4 preparing new version 2024-07-02 09:03:20 -07:00
Eduardo Chiarotti
cd77aeebb9 docs: Update training feature/code interpreter docs (#852)
* docs: remove training docs from README

* docs: add CodeinterpreterTool to docs and update docs

* docs: fix name of tool
2024-07-02 13:00:37 -03:00
João Moura
5ad3712810 adding link to docs 2024-07-01 18:41:31 -07:00
João Moura
8be02d948d preparing new version 2024-07-01 18:28:11 -07:00
João Moura
9dcf96eb4c updatign tools 2024-07-01 15:25:29 -07:00
João Moura
5c78188d22 rollback update to new version 2024-07-01 15:25:10 -07:00
João Moura
b67b691fb8 preparing new version 2024-07-01 15:12:22 -07:00
João Moura
14f4add4ab preparing new version 2024-07-01 15:10:13 -07:00
João Moura
6386903c91 preparing new version 2024-07-01 08:41:13 -07:00
João Moura
819f5794e3 preparing new version 2024-07-01 06:08:46 -07:00
João Moura
edc46b2163 preparing new version 2024-07-01 05:48:47 -07:00
João Moura
8c63dbd4e1 new docs 2024-07-01 05:32:22 -07:00
João Moura
0dd77b5662 small formatting details 2024-07-01 05:32:22 -07:00
João Moura
49ab880623 Updating docs 2024-07-01 05:32:22 -07:00
João Moura
0f596480b0 updating docs 2024-07-01 05:32:22 -07:00
João Moura
dee7bd6258 small refractoring for new version 2024-07-01 05:32:22 -07:00
gpu7
64ec4eb1e6 bugfix in python script sample code (#787)
Add the line:

process = Process.sequential
2024-07-01 00:23:06 -03:00
JoePro
29e72b6ff5 Update LLM-Connections.md (#796)
Revised to utilize Ollama from langchain.llms instead as the functionality from the other method simply doesn't work when delegating.

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-07-01 00:22:38 -03:00
Eelke van den Bos
13283639e4 Set manager verbosity to crew verbosity by default (#797)
Fixes #793
2024-07-01 00:20:39 -03:00
finecwg
f14ddff141 Update tool_usage.py (#828)
fixed error for some cases with Pandas DataFrame:

ValueError: The truth value of a DataFrame is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().
2024-07-01 00:19:36 -03:00
Bruno Tanabe
1c884f50ed fix: Fix grammar error in documentation 'Crew Attributes' (#836)
Correction of grammar error in the CrewAI documentation, on the page 'https://docs.crewai.com/core-concepts/Crews/' it says 'ustom' instead of 'Custom'.
2024-07-01 00:16:06 -03:00
Gui Vieira
647bd794ed Improve telemetry (#818)
* Improve telemetry

* Minor adjustments

* Try to fix typing error

* Try to fix typing error [2]
2024-06-28 20:05:47 -03:00
João Moura
0807798777 preparing new version 2024-06-27 11:04:08 -07:00
Eduardo Chiarotti
1e9c398ca5 docs: add docs for training (#824) 2024-06-27 14:56:32 -03:00
Lorenze Jay
9678d22724 Lorenzejay/byoa (#776)
* better spacing

* works with llama index

* works on langchain custom just need delegation to work

* cleanup for custom_agent class

* works with different argument expectations for agent_executor

* cleanup for hierarchial process, better agent_executor args handler and added to the crew agent doc page

* removed code examples for langchain + llama index, added to docs instead

* added key output if return is not a str for and added some tests

* added hinting for CustomAgent class

* removed pass as it was not needed

* closer just need to figuire ou agentTools

* running agents - llamaindex and langchain with base agent

* some cleanup on baseAgent

* minimum for agent to run for base class and ensure it works with hierarchical process

* cleanup for original agent to take on BaseAgent class

* Agent takes on langchainagent and cleanup across

* token handling working for usage_metrics to continue working

* installed llama-index, updated docs and added better name

* fixed some type errors

* base agent holds token_process

* heirarchail process uses proper tools and no longer relies on hasattr for token_processes

* removal of test_custom_agent_executions

* this fixes copying agents

* leveraging an executor class for trigger llamaindex agent

* llama index now has ask_human

* executor mixins added

* added output converter base class

* type listed

* cleanup for output conversions and tokenprocess eliminated redundancy

* properly handling tokens

* simplified token calc handling

* original agent with base agent builder structure setup

* better docs

* no more llama-index dep

* cleaner docs

* test fixes

* poetry reverts and better docs

* base_agent_tools set for third party agents

* updated task and test fix
2024-06-27 14:56:08 -03:00
Eduardo Chiarotti
4e1506f68e fix: fix trainig_data error (#820)
* fix: fix trainig_data error

* fix: fix lack crew on agent

* fix: fix lack crew on agent executor
2024-06-27 12:58:20 -03:00
Eduardo Chiarotti
a912ed33aa fix: fix tests (#814) 2024-06-27 05:45:23 -03:00
Eduardo Chiarotti
695bb4848e feat: add CodeInterpreterTool to run when enable code execution (#804)
* feat: add CodeInterpreterTool to run when enable code execution is allowed on agent

* feat: change to allow_code_execution

* feat: add readme for CodeInterpreterTool
2024-06-27 02:25:39 -03:00
Nuraly
b9bf7c19aa Update Agents.md (#816)
Made a space to ensure that Header formatting is displayed correctly on the website
2024-06-27 02:23:18 -03:00
Eduardo Chiarotti
3573a61568 feat: Add Train feature for Crews (#686)
* feat: add training logic to agent and crew

* feat: add training logic to agent executor

* feat: add input parameter  to cli command

* feat: add utilities for the training logic

* feat: polish code, logic and add private variables

* feat: add docstring and type hinting to executor

* feat: add constant file, add constant to code

* feat: fix name of training handler function

* feat: remove unused var

* feat: change file handler file name

* feat: Add training handler file, class and change on the code

* feat: fix name error from file

* fix: change import to adapt to logic

* feat: add training handler test

* feat: add tests for file and training_handler

* feat: add test for task evaluator function

* feat: change text to fit in-screen

* feat: add test for train function

* feat: add test for agent training_handler function

* feat: add test for agent._use_trained_data
2024-06-27 02:22:34 -03:00
Bruno Tanabe
0594a7f9d8 fix: Fix grammar error in documentation in PDF Search Tool (#819)
Correction of grammar error in the CrewAI documentation, on the page 'https://docs.crewai.com/tools/PDFSearchTool/' it says 'Optinal' instead of 'Optional'.
2024-06-27 00:41:22 -03:00
João Moura
41debd1191 updating docs 2024-06-22 19:49:50 -03:00
João Moura
08745a8632 preparing new version 2024-06-22 17:47:35 -03:00
João Moura
c12fa808ae Preparing new version 2024-06-22 17:01:22 -03:00
João Moura
aee991fb7b preapring to cut new version 2024-06-20 12:58:50 -03:00
João Moura
3d5d71f096 addding new kickoff docs 2024-06-20 02:46:13 -03:00
João Moura
25528dbee1 adding new docs to the menu 2024-06-20 02:24:02 -03:00
João Moura
73c3d26d55 Updating Docs 2024-06-20 02:19:35 -03:00
Brandon Hancock (bhancock_ai)
72e20a5dbb Resolved Merge Conflicts for PR #712: Remove Hyphen in co-workers (#786)
* removed hyphen in co-workers

* Fix issue with AgentTool agent selection. The LLM included double quotes in the agent name which messed up the string comparison. Added additional types. Cleaned up error messaging.

* Remove duplicate import

* Improve explanation

* Revert poetry.lock changes

* Fix missing line in poetry.lock

---------

Co-authored-by: madmag77 <goncharov.artemv@gmail.com>
2024-06-18 16:57:56 -03:00
João Moura
ff80f57816 fixing bug to multiple crews on yaml format in the same project 2024-06-18 02:32:53 -03:00
Lorenze Jay
9a71e66a62 Lorenzejay/crew kickoff union type (#767)
* added extra parameter for kickoff to return token usage count after result

* added output_token_usage to class and in full_output

* logger duplicated

* added more types

* added usage_metrics to full output instead

* added more to the description on full_output

* possible mispacing

* updated kickoff return types to be either string or dict applicable when full_output is set

* removed duplicates
2024-06-14 14:23:55 -03:00
Lorenze Jay
b992fd26b9 fixes crewai docs assembling crew code block example code (#768) 2024-06-14 14:23:30 -03:00
Dan McKinley
2aae7600f4 updates instructor to the latest version. (#760)
* updates instructor to the latest version. adds jsonref, which instructor seems to depend on.

* updates embedchain reference, necessary for python 3.12
2024-06-14 01:57:40 -03:00
Lorenze Jay
14e7046980 added usage_metrics to full output (#756)
* added extra parameter for kickoff to return token usage count after result

* added output_token_usage to class and in full_output

* logger duplicated

* added more types

* added usage_metrics to full output instead

* added more to the description on full_output

* possible mispacing
2024-06-12 14:18:52 -03:00
Guangqiang Lu
9e2eb2700a add datetime import for logger.py (#702) 2024-06-11 16:43:15 -03:00
Matt Thompson
4f093e2626 fix: correct default model (gpt-4o), correct token counts, and correct TaskOutput attributes (added agent) (#749)
* fix: 'from datetime import datetime for logging' to print the timestamp

* fix: correct default model (gpt-4o), correct token counts, and correct TaskOutput attributes (added agent)

* test: verify Task callback data is an instance of TaskOutput
2024-06-11 15:29:22 -03:00
Brandon Hancock (bhancock_ai)
e202592715 Feature/kickoff for each sync (#680)
* Sync with deep copy working now

* async working!!

* Clean up code for review

* Fix naming

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-06-11 12:51:39 -03:00
Taradepan R
3a77b418cb updated the import for cohere llm (#696) 2024-06-04 03:32:23 -03:00
Karthik Kalyanaraman
e0a42eb394 Add Langtrace to the "How to" docs for CrewAI Agent Observability (#634)
* Add files via upload

* Create Langtrace-Observability.md

* Rename crewai-agentops-stats.png to crewai-langtrace-stats.png
2024-05-29 02:14:29 -03:00
theCyberTech - Rip&Tear
eecb6402cf Added timestamp to logger (#646)
* Added timestamp to logger

Updated the logger.py file to include timestamps when logging output. For example:

 [2024-05-20 15:32:48][DEBUG]: == Working Agent: Researcher
 [2024-05-20 15:32:48][INFO]: == Starting Task: Research the topic
 [2024-05-20 15:33:22][DEBUG]: == [Researcher] Task output:

* Update tool_usage.py

* Revert "Update tool_usage.py"

This reverts commit 95d18d5b6f.

incorrect bramch for this commit
2024-05-26 01:32:16 -03:00
Saif Mahmud
0f3e92108f fixes #665 (#666) 2024-05-26 01:31:28 -03:00
theCyberTech - Rip&Tear
824b0e85f0 Update crew.py (#644)
Fixed Type on line 53
2024-05-24 00:06:27 -03:00
Mish Ushakov
81788d1ad2 Update BrowserbaseLoadTool.md (#647) 2024-05-24 00:05:52 -03:00
Mike Heavers
c317c0ee36 Update README.md (#652)
Rework example so that if you use a custom LLM it doesn't throw code errors by uncommenting.
2024-05-24 00:05:32 -03:00
Anudeep Kolluri
59336515b0 Update agent.py (#655)
Changed default model value from gpt-4 to gpt-4o.
Reasoning.
gpt-4 costs 30$ per million tokens while gpt-4o costs 5$.
This is more cost friendly for default option.
2024-05-24 00:04:53 -03:00
Paul Sanders
492d86b701 Clarify text in docstring (#662) 2024-05-24 00:04:01 -03:00
Paul Sanders
e64512a67e Enable search in docs (#663) 2024-05-24 00:03:31 -03:00
Olivier Roberdet
bc786cb9ba Fix typo in instruction en.json (#676) 2024-05-24 00:03:07 -03:00
Eduardo Chiarotti
b48beaaf9c feat: Add crew train cli (#624)
* fix: fix crewai-tools cli command

* feat: add crewai train CLI command

* feat: add the tests

* fix: fix typing hinting issue on code

* fix: test.yml

* fix: fix test

* fix: removed fix since it didnt changed the test
2024-05-23 18:46:45 -03:00
João Moura
393a86792c adding agent to task output 2024-05-16 05:12:32 -03:00
Jason Schrader
77f595e617 Add version command to CLI (#348)
* feat: add version command to cli with tools flag

* test: check output of version and tools flag

* fix: add version tool info to cli outputs
2024-05-15 19:50:49 -03:00
João Moura
978653db75 fixing crew base 2024-05-14 17:40:38 -03:00
João Moura
99af98b16a ppreparing new version 0.30.9 2024-05-14 11:32:05 -03:00
João Moura
643c1d6d31 cutting new version with no yaml parsing 2024-05-13 23:09:29 -03:00
João Moura
a0dcc65dac preparing new version 2024-05-13 22:32:24 -03:00
João Moura
fc510dbc3d New version, updating dependencies, fixing memory 2024-05-13 22:26:41 -03:00
João Moura
eaa8aa7d35 preparing new version 2024-05-13 12:59:55 -03:00
João Moura
6e1fe5171e preparing new version 2024-05-13 02:35:46 -03:00
Saif Mahmud
526f594d47 Fixes #603 (#604) 2024-05-13 02:34:52 -03:00
João Moura
f8949ba975 Adding new tests 2024-05-13 02:34:33 -03:00
João Moura
f175ac32d0 Small RC Fixes (#608)
* mentioning ollama on the docs as embedder

* lowering barrier to match tool with simialr name

* Fixing agent tools to support co_worker

* Adding new tests

* Fixing type"

* updating tests

* fixing conflict
2024-05-13 02:29:04 -03:00
Ítalo Vieira
c0a7e75f29 fix typo exectue -> execute (#607) 2024-05-13 02:19:06 -03:00
João Moura
bc741e9e3b preparing new version 2024-05-12 19:56:40 -03:00
Eduardo Chiarotti
6eb0c0666b feat: add mypy as type checker, update code and add comment to reference (#591)
* fix: fix test actually running

* fix: fix test to not send request to openai

* fix: fix linting to remove cli files

* fix: exclude only files that breaks black

* fix: Fix all Ruff checkings on the code and Fix Test with repeated name

* fix: Change linter name on yml file

* feat: update pre-commit

* feat: remove need for isort on the code

* feat: add mypy as type checker, update code and add comment to reference

* feat: remove black linter

* feat: remove poetry to run the command

* feat: change logic to test mypy

* feat: update tests yml to try to fix the tests gh action

* feat: try to add just mypy to run on gh action

* feat: fix yml file

* feat: add comment to avoid issue on gh action

* feat: decouple pytest from the necessity of poetry install

* feat: change tests.yml to test different approach

* feat: change to poetry run

* fix: parameter field on yml file

* fix: update parameters to be on the pyproject

* fix: update pyproject to remove import untyped errors
2024-05-10 16:37:52 -03:00
Steven Edwards
b20853d21d Task needs an expected_output field in docs. (#568)
* Task needs an expected_output field in docs..

* Add missing comma.
2024-05-10 11:55:10 -03:00
Ayo Ayibiowu
dedaafd863 feat: adds support to automatically fallback to the default encoding (#596)
* feat: adds support to automatically fallbackk to the default encoding

* fix: use the correct method
2024-05-10 11:54:45 -03:00
Eduardo Chiarotti
f0c9e80d33 Feat: Add Ruff to improve linting/formatting (#588)
* fix: fix test actually running

* fix: fix test to not send request to openai

* fix: fix linting to remove cli files

* fix: exclude only files that breaks black

* fix: Fix all Ruff checkings on the code and Fix Test with repeated name

* fix: Change linter name on yml file

* feat: update pre-commit

* feat: remove need for isort on the code

* feat: remove black linter

* feat: update tests yml to try to fix the tests gh action
2024-05-10 11:53:53 -03:00
GabeKoga
16907b13db Fix/yaml formatting (#590)
* Bug/curly_braces_yaml

Added parser to help users on yaml syntax

* context error

Patch and later will prioritize this again to have context work with the yaml
2024-05-09 21:35:21 -03:00
Eduardo Chiarotti
1b73933be0 fix: fix test actually running (#587)
* fix: fix test actually running

* fix: fix test to not send request to openai

* fix: fix linting to remove cli files

* fix: exclude only files that breaks black
2024-05-09 21:33:48 -03:00
João Moura
cbf6be9df1 prepping new version 2024-05-09 09:12:57 -03:00
Eduardo Chiarotti
8063e1d154 fix: Add validation fix output_file issue when have '/' (#585)
* fix: Add validation fix output_file issue when have /

* fix: run black to format code

* fix: run black to format code
2024-05-09 08:11:00 -03:00
João Moura
402c5f477b Revert "Fix .md doc file 404 error on github (#564)" (#567)
This reverts commit 6f17b2d0ff.
2024-05-05 10:35:46 -03:00
Alex Fazio
8106f3bbba corrected imprecision in the instantiation (#555) 2024-05-05 03:55:13 -03:00
João Moura
5c52ae731d preparing new RC version 2024-05-05 02:57:29 -03:00
Jackie Qi
6f17b2d0ff Fix .md doc file 404 error on github (#564)
* fix md file link not working on github

* miss one changed file
2024-05-05 02:53:20 -03:00
João Moura
d6b08f097f updating .gitignore 2024-05-05 02:52:43 -03:00
João Moura
54668d252c TYPO 2024-05-05 02:14:49 -03:00
João Moura
9071f27d9f Fixing manager_agent_support 2024-05-05 00:51:18 -03:00
João Moura
e9cc746851 cutting new RC 2024-05-03 00:55:32 -03:00
João Moura
b0e38c2a2d adding meomization to crewai project annotations 2024-05-03 00:49:37 -03:00
tarekadam
9b25b4c5bf Update LLM-Connections.md (#553)
fixes command to lower case
2024-05-03 00:25:03 -03:00
João Moura
68e1444ed8 updating manager llm pydantic error 2024-05-02 23:39:56 -03:00
João Moura
3f1fda6a63 curring new rc 2024-05-02 23:22:02 -03:00
João Moura
e14d457905 updating gitignore 2024-05-02 21:57:49 -03:00
João Moura
9648254ec7 Better json parsing for smaller models 2024-05-02 21:57:41 -03:00
João Moura
3360cad4cc updating git ignore 2024-05-02 20:52:43 -03:00
David Solito
e280e4a62a Update crew.py (#551)
Ad manager_agent description in crew docstring
2024-05-02 19:21:22 -03:00
João Moura
cf9d946969 new version 2024-05-02 05:00:29 -03:00
João Moura
d9124b333b cutting new version 2024-05-02 05:00:29 -03:00
João Moura
cbe53d9daf small improvements for i18n 2024-05-02 05:00:29 -03:00
João Moura
2c17ff3e9f new version 2024-05-02 05:00:29 -03:00
João Moura
7ad0357eaa adding initial support for external prompt file 2024-05-02 05:00:29 -03:00
Jason Schrader
b7d4c4843d fix typos in generated readme (#345)
small things I noticed while upgrading our setup!
2024-05-02 03:32:18 -03:00
Dmitri Khokhlov
5daa40b498 fix: TypeError: LongTermMemory.search() missing 1 required positional argument: 'latest_n' (#488)
Signed-off-by: Dmitri Khokhlov <dkhokhlov@gmail.com>
2024-05-02 03:28:36 -03:00
Ikko Eltociear Ashimine
93dc0874b5 fix typo (#489)
* Update test_crew_function_calling_llm.yaml

ouput -> output

* Update tool_usage.py

ouput -> output
2024-05-02 03:27:40 -03:00
Sarvajith Adyanthaya
cbe9404bb9 Changed "Inert" to "Innate" #470 (#490) 2024-05-02 03:27:09 -03:00
ftoppi
19fe093ce9 Update task.py: try to find json in task output using regex (#491)
* Update task.py: try to find json in task output using regex

Sometimes the model replies with a valid and additional text, let's try to extract and validate it first. It's cheaper than calling LLM for that.

* Update task.py

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-05-02 03:26:34 -03:00
Mosta
f7e856a16d Update PGSearchTool.md (#492)
typo on code snippet
2024-05-02 03:22:18 -03:00
Samuel Kocúr
75b495c544 fix db_storage_path handling to use env variable or cwd (#507) 2024-05-02 03:16:54 -03:00
Mish Ushakov
dfaf0700f1 Added Browserbase loader to the docs (#508)
* Create BrowserbaseLoadTool.md

* added browserbase loader
2024-05-02 03:15:59 -03:00
deadlious
e16b1f4a53 Tool name recognition based on string distance (#521)
* adding variations of ask question and delegate work tools

* Revert "adding variations of ask question and delegate work tools"

This reverts commit 38d4589be8.

* adding distance calculation for tool names.

* proper formatting

* remove brackets
2024-05-02 03:15:34 -03:00
Victor Carvalho Tavernari
3f16686627 Add conditional check for output file directory creation (#523)
This commit adds a conditional check to ensure that the output file directory exists before attempting to create it. This ensures that the code does not
fail in cases where the directory does not exist and needs to be created. The condition is added in the `_save_file` method of the `Task` class, ensuring
that the correct behavior is maintained for saving results to a file.
2024-05-02 03:13:51 -03:00
Jim Collins
48ad3d5a5a Update README.md (#525)
Reworded "If you want to also install crewai-tools, which is a package with tools that can be used by the agents, but more dependencies, you can install it with, example below uses it:" for clarity
2024-05-02 03:12:03 -03:00
Alex Fazio
d9043f0a0a fix to import statement PGSearchTool.md (#548)
fix to the import statement in PGSearchTool documentation
2024-05-02 03:10:43 -03:00
João Moura
2ae6fc4bd8 smal fixes and better guardrail for parsing small models tools usage 2024-05-02 02:21:59 -03:00
João Moura
84775373a6 Adding support for system, prompt and answe templates 2024-05-02 02:21:59 -03:00
João Moura
8360abd1c0 removing unnecessary test 2024-05-02 02:21:59 -03:00
João Moura
9d4dc1a081 unifying co-worker string 2024-05-02 02:21:59 -03:00
João Moura
6840fd8ffc remving blank line 2024-05-02 02:21:59 -03:00
João Moura
83596c1a32 Fixing task callback 2024-05-02 02:21:59 -03:00
João Moura
55fcda758a Revert "AgentOps Implementation (#411)"
This reverts commit bf436f885e.
2024-05-02 02:21:59 -03:00
Alex Fazio
51fced9913 docs fix to xml tool import statement (#546)
* docs fix to xml tool import statement

* Update XMLSearchTool.md
2024-05-01 12:53:49 -03:00
Braelyn Boynton
bf436f885e AgentOps Implementation (#411)
* implements agentops with a langchain handler, agent tracking and tool call recording

* track tool usage

* end session after completion

* track tool usage time

* better tool and llm tracking

* code cleanup

* make agentops optional

* optional dependency usage

* remove telemetry code

* optional agentops

* agentops version bump

* remove org key

* true dependency

* add crew org key to agentops

* cleanup

* Update pyproject.toml

* Revert "true dependency"

This reverts commit e52e8e9568.

* Revert "cleanup"

This reverts commit 7f5635fb9e.

* optional parent key

* agentops 0.1.5

* Revert "Revert "cleanup""

This reverts commit cea33d9a5d.

* Revert "Revert "true dependency""

This reverts commit 4d1b460b

* cleanup

* Forcing version 0.1.5

* Update pyproject.toml

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-20 12:20:13 -03:00
Elijas Dapšauskas
f7f9720ce8 Allow minor version patches to python-dotenv (#339)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-19 02:44:08 -03:00
Emmanuel Crown
61c745357d Fixed a typo in the main readme on the llm selection , options for an agent (#349) 2024-04-19 02:42:04 -03:00
Sajal Sharma
a49e3daaba Update LLM-Connections.md (#353)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-19 02:41:36 -03:00
Kaushal Powar
9cbc6f4531 Update GitHubSearchTool.md (#357)
GithubSearchTool was misspelled as GitHubSearchTool

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-19 02:40:38 -03:00
Selim Erhan
46f8d6c31e Update LLM-Connections.md (#359)
Created a short documentation on how to use Llama2 locally with crewAI thanks to the help of Ollama.

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-19 02:39:33 -03:00
Christian24
038c805c8c Fix lockfile (#477) 2024-04-18 11:28:06 -03:00
João Moura
be5c879697 Update README.md 2024-04-17 00:02:49 -03:00
João Moura
f3bfabb149 Adding manager llm 2024-04-16 16:50:44 -03:00
João Moura
60995e03d1 adding new installing crew docs 2024-04-16 16:50:44 -03:00
Joseph Bastulli
74f23ada73 fix: swapped the task callback assignment (#443) 2024-04-16 15:54:42 -03:00
Jack Hayter
e307da43c5 Prevent duplicate TokenCalcHandler callbacks on Agent (#475) 2024-04-16 15:54:02 -03:00
Alex Reibman
2bc0de8716 Incorrect documentation link for AgentOps (#458)
* remove .md

* made language more clear

* update images and documentation for spelling

* update typos and links

* update repo placement

* update wording

* clarify

* update wording

* Added clearer features

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-16 08:24:30 -03:00
Jonathan Morales Vélez
972b24eab7 fix link to observability (#461) 2024-04-16 08:22:11 -03:00
Preston Badeer
81bb91db14 Update LLM-Connections.md with up to date LM Studio instructions (#468)
Co-authored-by: Preston Badeer <467756+pbadeer@users.noreply.github.com>
2024-04-16 08:20:56 -03:00
Eivind Hyldmo
52f0d22784 Fixed typo in Tools.md (#472) 2024-04-16 08:20:25 -03:00
Lennart J. Kurzweg
19e0e3fcb4 Added optional manager_agent parameter (#474)
* Added optional manager_agent parameter

* Update crew.py

---------

Co-authored-by: Lennart J. Kurzweg (Nx2) <git@nx2.site>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-16 08:18:36 -03:00
João Moura
69964e005d cutting new version with updated cli template 2024-04-11 11:30:30 -03:00
João Moura
b0dfe95dae Preparing new version to use new version of crewai-tools 2024-04-10 11:52:12 -03:00
Cfomodz
c2a88018d8 Update README.md (#442) 2024-04-08 05:59:04 -03:00
João Moura
21ab621d02 preparring new version 2024-04-08 02:08:57 -03:00
João Moura
e2ad0efbed adding missing import 2024-04-08 02:08:43 -03:00
João Moura
abeb9bdac3 preparing new version 2024-04-08 01:39:22 -03:00
João Moura
ed1581dee5 removing unnecessary certificate 2024-04-08 01:39:11 -03:00
João Moura
be2afbe990 preparing new version 2024-04-07 14:55:45 -03:00
João Moura
0c717fb24a fixing long temr memory interpolation 2024-04-07 14:55:35 -03:00
João Moura
a0c4cea9f9 preping new verison with new tools package 2024-04-07 14:19:50 -03:00
João Moura
685130c18c preparing new version 2024-04-07 04:18:05 -03:00
rajib
b5ecb36b50 The suggestions were getting split at character level and not at sentence level (#436)
* fix the issue where the suggestions were split at character level

* Update contextual_memory.py

---------

Co-authored-by: rajib76 <rajib76@yahoo.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-07 02:57:23 -03:00
João Moura
61f3ad0662 Updating tool dependency 2024-04-05 22:46:32 -03:00
João Moura
428f8d2f05 preparing new version 2024-04-05 19:52:13 -03:00
shivam singh
8314591523 doc: Add documentation to Task model. (#363) 2024-04-05 19:49:36 -03:00
高璟琦
c1049a5d10 add solar example (#373)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-05 19:48:27 -03:00
Rueben Ramirez
80c1b6a2ee whitespace consistency across docs (#407)
I saw a rendedered whitespace inconsistency in the Tasks docs here:
c87d887efc/docs/core-concepts/Tasks.md (L173)

So I set out to patch that up to make it easier to read.  I then noticed
there were a few whitespace inconsistencies:
- 2 spaces
- 4 whitespaces
- tabs

It appears that the 4 whitespaces is the prevalent whitesapce usage, so
I overwrote other whitespace usages with that in this commit.

Co-authored-by: Rueben Ramirez <rramirez@ruebens-mbp.tail7c016.ts.net>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-05 19:47:09 -03:00
GabeKoga
289e12de5a Feature: Log files (#423)
* log_file

feature: added a new parameter for crew that creates a txt file to log agent execution

* unit tests and documentation

unit test if file is created but not what is inside the file
2024-04-05 19:44:50 -03:00
GabeKoga
459a404563 purple (#428)
changed from yellow to purple for visibility
2024-04-05 18:25:59 -03:00
João Moura
e7fcf5cd54 TYPO 2024-04-05 09:37:51 -03:00
João Moura
c47c288138 fixing memory docs 2024-04-05 08:59:54 -03:00
João Moura
9216f1d9b2 adding specific memmory docs 2024-04-05 08:59:20 -03:00
João Moura
f7fc61f043 Increasing default max inter 2024-04-05 08:36:09 -03:00
João Moura
4c274dbca7 updating tests 2024-04-05 08:33:31 -03:00
João Moura
9b37aab61a adding max execution time 2024-04-05 08:31:25 -03:00
João Moura
da72f4cfc8 preparing new version 2024-04-05 08:24:41 -03:00
João Moura
a0ba9a81b2 not overriding llm callbacks 2024-04-05 08:24:20 -03:00
João Moura
52963880ce fix docs 2024-04-04 17:36:50 -03:00
João Moura
748ab102c2 preparing new version 0.27.0 2024-04-04 15:29:45 -03:00
João Moura
fd12609330 Adding new test for crew memory 2024-04-04 15:29:45 -03:00
João Moura
86b8b3e9bc Adding link to agentops docs 2024-04-04 15:29:45 -03:00
João Moura
1ed5881b30 updating dependendies 2024-04-04 15:29:45 -03:00
João Moura
a1e1113101 Removing memory flag from agent in favor of crew memory 2024-04-04 15:29:45 -03:00
João Moura
c45d1c337c TYPO 2024-04-04 15:29:45 -03:00
João Moura
1fb9f9c585 updating tools dependency 2024-04-04 15:29:45 -03:00
João Moura
029b8796f9 Updating docs 2024-04-04 15:29:45 -03:00
Braelyn Boynton
9abbed2049 AgentOps Docs (#412)
Agentops documentation
2024-04-04 15:09:31 -03:00
ftoppi
ce9c343c0a tasks.py: don't call Converter when model response is valid (#406)
* tasks.py: don't call Converter when model response is valid

Try to convert the task output to the expected Pydantic model before sending it to Converter, maybe the model got it right.
2024-04-04 10:11:46 -03:00
ftoppi
2edc824b61 Update Creating-a-Crew-and-kick-it-off.md: add compatible python versions (#420)
* Update Creating-a-Crew-and-kick-it-off.md: add compatible python versions

* Update Creating-a-Crew-and-kick-it-off.md

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-03 19:10:11 -03:00
João Moura
0b70c3e8db preparing new rc 2024-04-03 08:11:30 -03:00
João Moura
3c64626c67 setting fake openai key 2024-04-03 06:56:02 -03:00
João Moura
a368e53a02 updating dependencies 2024-04-03 06:03:18 -03:00
João Moura
c730d73c10 force reseting db in care of change in dimensions 2024-04-03 05:52:35 -03:00
João Moura
eb17e192c0 Fixing db path 2024-04-03 05:45:59 -03:00
João Moura
6532370c30 creating db file based on package name 2024-04-03 05:22:20 -03:00
João Moura
1da288de85 preparing new version 2024-04-03 05:04:26 -03:00
João Moura
17a47224f3 adding initial memory docs 2024-04-03 05:04:14 -03:00
João Moura
6129c908b8 updating gitignore 2024-04-03 05:04:00 -03:00
João Moura
35f6156ed4 checking crew before using memory 2024-04-03 05:03:43 -03:00
João Moura
4dcbcfe533 cutting new version, adding cache_function docs 2024-04-02 14:26:22 -03:00
João Moura
80fd67cdea updating specs 2024-04-02 13:51:16 -03:00
João Moura
0abfcedda8 updating db storage and dependencies 2024-04-02 13:51:05 -03:00
João Moura
244458a1c9 preparing RC 2024-04-01 14:38:26 -03:00
João Moura
c87d887efc update docs 2024-04-01 11:14:06 -03:00
João Moura
bbd4e58b65 Starting i18n language file support 2024-04-01 10:45:17 -03:00
João Moura
f85bf00409 Adding long term, short term, entity and contextual memory 2024-04-01 10:45:17 -03:00
João Moura
044fbbdbac updating gitignore 2024-04-01 10:45:17 -03:00
João Moura
ecb6a97dc4 updating dependencies 2024-04-01 10:45:17 -03:00
João Moura
b791df95d4 adding editor config 2024-04-01 10:45:17 -03:00
João Moura
3ef2df75fd using .casefold() instead of lower 2024-04-01 10:45:17 -03:00
João Moura
703f1378dc updating git ignore 2024-04-01 10:45:17 -03:00
João Moura
b7983ccd8f updating i18n to take on translation files 2024-04-01 10:45:17 -03:00
João Moura
66d0f448c4 improving agent tools descriptions 2024-04-01 10:45:17 -03:00
João Moura
13766e4339 updating gitignore 2024-04-01 10:45:17 -03:00
João Moura
5f65b7f7f4 improving original promtps 2024-04-01 10:45:14 -03:00
João Moura
d73dd08ef4 Adding custom caching 2024-04-01 10:43:05 -03:00
João Moura
2c359ca926 udpating dependencies 2024-04-01 10:43:05 -03:00
João Moura
a78d5156ac adding proper docs for crewAI 2024-04-01 10:43:05 -03:00
João Moura
81d5fe6fc6 Ability to disable cache at agent and crew level 2024-04-01 10:43:05 -03:00
João Moura
6d36f66a00 Adding HuggingFace docs 2024-04-01 10:43:05 -03:00
João Moura
45ba8d4bd2 fixing warnings 2024-04-01 10:43:05 -03:00
João Moura
6b2f7088a2 updating telemetry to use https 2024-04-01 10:43:05 -03:00
João Moura
b240568a9f Updating crewai-tools dependency 2024-04-01 10:43:05 -03:00
GabeKoga
eb98b8efad feature: human input per task (#395)
* feature: human input per task

* Update executor.py

* Update executor.py

* Update executor.py

* Update executor.py

* Update executor.py

* feat: change human input for unit testing
added documentation and unit test

* Create test_agent_human_input.yaml

add yaml for test

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-01 10:04:56 -03:00
Elle Neal
0c7594d3c2 Update LLM-Connections.md (#252)
Adding Cohere LLM

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-04-01 10:03:16 -03:00
sebestyenmiklos1
cb63c7360b Update Tasks.md (#240)
Fix example code of missing comma.

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-03-31 20:40:51 -03:00
Ken Jenney
4f3144f718 Update ScrapeWebsiteTool.md (#385) 2024-03-30 11:57:08 -03:00
chowderhead
eb27a8803a Update GitHubSearchTool.md (#390)
Import statement has a lower case h
2024-03-30 11:56:34 -03:00
Ikko Eltociear Ashimine
de3bc686c1 Update README.md (#391)
bellow -> below
2024-03-30 11:56:08 -03:00
Gui Vieira
27b3625cd1 Fix input interpolation bug (#369) 2024-03-22 03:08:54 -03:00
Gui Vieira
906c6598d6 Custom model docs (#368) 2024-03-22 03:01:34 -03:00
João Moura
19eaa62d4e adding auto flake 2024-03-11 23:27:19 -03:00
João Moura
6091db1948 cutting new version with proper imports 2024-03-11 23:27:04 -03:00
João Moura
10b4b09872 adding autoflake 2024-03-11 22:56:14 -03:00
João Moura
1295b9d604 cutting new version 2024-03-11 22:55:56 -03:00
João Moura
6b75f460cc preparring new version that autoloads env 2024-03-11 22:19:47 -03:00
João Moura
dd3784e0d0 preparring to cut new version 2024-03-11 19:54:27 -03:00
João Moura
e19993076c updating CLI template and guaranteeing tasks order 2024-03-11 19:53:34 -03:00
João Moura
5aa543f4d2 Preparing new version 2024-03-11 17:37:12 -03:00
João Moura
815606f4c2 Improving agent logging 2024-03-11 17:05:54 -03:00
João Moura
27914bd841 Improve tempalte readme 2024-03-11 17:05:20 -03:00
Abe Gong
711ef0e0f0 Fix typo in Tools.md (#300) 2024-03-11 16:45:28 -03:00
Selim Erhan
bbfb8cd8d7 Update Create-Custom-Tools.md (#311)
Added the langchain "Tool" functionality by creating a python function and then adding the functionality of that function to the tool by 'func' variable in the 'Tool' function.
2024-03-11 16:44:04 -03:00
Johan
6f03d239f3 Update Tools.md (#326)
* Update Tools.md

Fixing typo on the instantiation part

* Update Tools.md

Update tool naming
2024-03-11 16:41:14 -03:00
Bill Chambers
1ed3941e16 Update Crews.md (#331) 2024-03-11 16:40:45 -03:00
Chris Pang
7ce89b8741 added langchain callback to agents (#333)
Co-authored-by: Chris Pang <chris_pang@racv.com.au>
2024-03-11 16:40:10 -03:00
Merbin J Anselm
7d26bd1063 docs: fix formatting in Human-Input-on-Execution.md (#335) 2024-03-11 16:38:59 -03:00
João Moura
0a9404bb46 adding initial CLI support 2024-03-11 16:37:32 -03:00
João Moura
4503f1b9c1 removing double space on logs 2024-03-11 16:23:00 -03:00
João Moura
631fce5b7c Overridding classes __repr__ 2024-03-05 10:12:49 -03:00
João Moura
ef9f85f5d2 adding support for agents and tasks to be defined of configs 2024-03-05 01:26:07 -03:00
João Moura
14b800e2e4 fix readme 2024-03-05 00:31:52 -03:00
João Moura
bbf61fa368 udpatign readme example 2024-03-05 00:29:55 -03:00
João Moura
fd74f87b92 update serper doc 2024-03-04 11:15:49 -03:00
João Moura
0c77f57fd9 updating docs disclaimer 2024-03-04 09:59:01 -03:00
João Moura
dbd3639847 updating docs 2024-03-04 01:29:27 -03:00
João Moura
9105d963fc updating docs 2024-03-03 22:43:51 -03:00
João Moura
960ed03730 fix docs path 2024-03-03 22:18:48 -03:00
João Moura
9972a575a3 Adding tool specific docs 2024-03-03 22:14:53 -03:00
João Moura
2724662fc5 Updating dependencies, cutting new version 2024-03-03 21:23:42 -03:00
João Moura
4556accc62 Updating Docs 2024-03-03 20:54:15 -03:00
João Moura
14eb3c6e82 updating README 2024-03-03 20:54:15 -03:00
João Moura
0e24af9e00 preparing new version 2024-03-03 20:54:15 -03:00
João Moura
e98bce8c03 preparing 0.17.0rc0 2024-03-03 20:54:15 -03:00
João Moura
8468445e1d Update inner tool usage logic to support both regular and function calling 2024-03-03 20:54:15 -03:00
João Moura
c523fcdaab Small docs update 2024-03-03 20:54:15 -03:00
João Moura
475dcdfdbe updating tests 2024-03-03 20:54:15 -03:00
Jay Mathis
24ab2b8da5 Update README.md (#301)
Fix a very minor typo
2024-03-03 12:41:35 -03:00
heyfixit
42cc4a3d1e fix directory typo (#295) 2024-03-03 12:41:14 -03:00
João Moura
d2f8a30c96 cutting a new version addressin backward compatibility 2024-02-28 12:04:13 -03:00
Hongbo
69b43aafbb correct a typo in tool_usage.py (#276) 2024-02-28 09:25:27 -03:00
Gordon Stein
ae5847a845 Update en.json (#281) 2024-02-28 09:24:44 -03:00
Selim Erhan
3f75657a42 Update Tools.md (#283)
Added the link to LangChain built-in toolkits
2024-02-28 09:22:51 -03:00
João Moura
92b995b1bf cutting new versions that doens't include cli just yet 2024-02-28 09:16:13 -03:00
João Moura
1b63f1a2ab Fixing bug preparing new version 2024-02-28 09:09:37 -03:00
João Moura
ebc611740f removing logs and preping new version 2024-02-28 03:44:23 -03:00
João Moura
6d23dc6ad7 removing necessary crewai-tools dependency 2024-02-28 03:44:23 -03:00
João Moura
38ceb9d409 adding support for input interpolation for tasks and agents 2024-02-28 03:44:23 -03:00
João Moura
45ea5ccef0 fixing tests 2024-02-28 03:44:23 -03:00
João Moura
9435ff437a Adding ability to track tools_errors and delegations 2024-02-28 03:44:23 -03:00
João Moura
b6badbaf54 changing method naming to increment 2024-02-28 03:44:23 -03:00
João Moura
ed22fdd993 Adding overall usage_metrics to crew and not adding delegation tools if there no agents the allow delegation 2024-02-28 03:44:23 -03:00
João Moura
5d682a5d6c Adding initial formatting error counting and token counter 2024-02-28 03:44:23 -03:00
João Moura
46dbb77c8b Updating README 2024-02-28 03:44:23 -03:00
João Moura
542f0663cd Adding write job description example 2024-02-28 03:44:23 -03:00
BR
5d56c692ab Fix Creating-a-Crew-and-kick-it-off.md so it can run (#280)
* Fix Creating-a-Crew-and-kick-it-off.md

- Update deps to include `crewai[tools]`
- Remove invalid `max_inter` arg from Task constructor call

* Update Creating-a-Crew-and-kick-it-off.md

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-02-27 14:23:19 -03:00
João Moura
a8aec58460 updating docs 2024-02-26 15:54:06 -03:00
João Moura
bf957cb5ca Cutting new version removing crewai-tool as a mandatory dependency 2024-02-26 15:27:04 -03:00
João Moura
6aedd2c392 updating telemetry timeout 2024-02-26 13:40:41 -03:00
João Moura
5ecdab0ebb updating docs 2024-02-26 13:38:14 -03:00
João Moura
90d1e6d5ea updating telemetry code and gitignore 2024-02-24 16:18:26 -03:00
João Moura
1df621fad0 make agents not have a memory by default 2024-02-24 03:33:05 -03:00
João Moura
de4e0e4219 preparing new version 2024-02-24 03:30:12 -03:00
João Moura
4ada52153c Avoid empty task outputs 2024-02-24 03:11:41 -03:00
João Moura
c5500987aa Adding support for agents without tools 2024-02-24 01:39:29 -03:00
João Moura
78fe769ea6 updating broken doc link 2024-02-24 01:38:16 -03:00
João Moura
3610f56475 startign support to crew docs 2024-02-24 01:38:04 -03:00
João Moura
8808328e7d reducing telemetry timeout 2024-02-23 16:02:24 -03:00
João Moura
68b8f0ec66 Reducing telemetry timeout 2024-02-23 15:54:22 -03:00
João Moura
b630b60ed0 preping new version 2024-02-23 15:24:16 -03:00
João Moura
74d0b70df4 bringing TaskOutput.result back to avoind breakign change 2024-02-23 15:23:58 -03:00
João Moura
a59b397172 preparing new version 0.14.0 2024-02-22 16:10:17 -03:00
João Moura
24fca5536c adding new converter logic 2024-02-22 15:16:17 -03:00
João Moura
b93b6c56f4 Updatign prompts 2024-02-22 15:13:41 -03:00
João Moura
81305c3639 preparing new RC 2024-02-20 17:56:55 -03:00
João Moura
c099776962 Improving inner prompts 2024-02-20 17:53:30 -03:00
João Moura
18978521c9 preparing new version 2024-02-20 10:40:57 -03:00
João Moura
c11723dc7f Updating tests 2024-02-20 10:40:37 -03:00
João Moura
9bd1dd4d01 bug fixing 2024-02-20 10:40:16 -03:00
João Moura
090d965af3 Preparing new version 2024-02-19 22:50:38 -03:00
João Moura
7334bec571 improving reliability for agent tools 2024-02-19 22:48:47 -03:00
João Moura
79a4bfbbc4 updating tests 2024-02-19 22:48:34 -03:00
João Moura
72dea5310e Increasing timeout for telemetry 2024-02-19 22:48:14 -03:00
João Moura
a649eb8555 Adding support to export tasks as json, pydantic objects, and save as file 2024-02-19 22:46:34 -03:00
João Moura
3cfc8dd4e0 Adding new tool usage and parsing logic 2024-02-19 22:43:10 -03:00
João Moura
6da94c1bba Updating docs 2024-02-19 22:01:09 -03:00
João Moura
a4836c2b03 adding more error logging and preparing new version 2024-02-15 23:49:30 -03:00
João Moura
430eb23448 Cutting new version with tool ussage bug fix 2024-02-15 23:19:12 -03:00
João Moura
0ee7189b82 preparing new version 2024-02-13 02:58:16 -08:00
João Moura
55c0c186d1 adding function calling llm support 2024-02-13 02:57:12 -08:00
João Moura
2410d0c531 updating readme 2024-02-13 01:50:23 -08:00
João Moura
256a2f1979 updating tests 2024-02-13 01:50:12 -08:00
João Moura
261c047803 renaming function for tools 2024-02-12 16:48:14 -08:00
João Moura
974bf0399c removing hostname from default telemetry 2024-02-12 16:11:15 -08:00
João Moura
46f7dc205e Crewating a tool output parser 2024-02-12 14:24:36 -08:00
João Moura
aef083ee53 adding regexp as dependency 2024-02-12 14:13:20 -08:00
João Moura
c2aa873d8f refactoring default agent tools 2024-02-12 13:27:02 -08:00
João Moura
830ddb18d9 allowing to set model naem through env var 2024-02-12 13:24:01 -08:00
João Moura
c11b7f0413 avoinding telemetry errors 2024-02-12 13:23:40 -08:00
João Moura
297cbd52d6 updating LLM connection docs 2024-02-12 13:21:43 -08:00
João Moura
4680d86586 updating versions and adding instructor 2024-02-12 13:20:28 -08:00
João Moura
c99c5be40a updating codeignore 2024-02-11 20:37:42 -08:00
João Moura
84a51a3ef4 counting for tool retries on the acutal usage 2024-02-10 13:14:00 -08:00
João Moura
21d1168943 Adding ability to remember instruction after using too many tools 2024-02-10 12:53:02 -08:00
João Moura
bbbd976fe3 refactoring task execution 2024-02-10 11:28:08 -08:00
João Moura
5a102251cf Revamping tool usage 2024-02-10 10:36:34 -08:00
João Moura
58bb181b48 updating translations 2024-02-10 01:08:04 -08:00
João Moura
422e36a995 Adding printer logic 2024-02-10 00:57:04 -08:00
João Moura
a6ff7effc0 updating dependencies 2024-02-10 00:56:25 -08:00
João Moura
989c3b66cf updating all cassettes 2024-02-10 00:55:40 -08:00
João Moura
3f4823257a avoind unnecesarry telemetry errors 2024-02-09 10:48:45 -08:00
João Moura
a9da07dc5d include agentFinish as part of step callback 2024-02-09 02:00:41 -08:00
João Moura
3613bbc9e8 recreating executor upon setting new step_callback 2024-02-09 01:52:28 -08:00
João Moura
6d8be72aa7 adding crew step_callback 2024-02-09 01:24:31 -08:00
João Moura
43542f226b adding support for step_callback 2024-02-08 23:56:13 -08:00
João Moura
c630857010 adding support for full_ouput in crews 2024-02-08 23:23:34 -08:00
João Moura
c5839b215e adding agent step callback 2024-02-08 23:01:30 -08:00
João Moura
ed0131b46f adding user the otpion to share all data of their crews 2024-02-08 23:01:02 -08:00
João Moura
5cf61cac22 preparing verison 0.5.5 2024-02-07 23:13:39 -08:00
João Moura
f727b3f5e2 fixing RPM controlelr being set unencessarily 2024-02-07 23:09:36 -08:00
João Moura
2740196c08 Adding new crew specific docs 2024-02-07 23:09:16 -08:00
João Moura
f9e2e0b4ac preparing version 0.5.4 2024-02-07 22:22:33 -08:00
João Moura
5247137ef8 adding initial telemetry 2024-02-07 22:21:44 -08:00
João Moura
e3e5b0b0fc preparing new version 0.5.3 2024-02-07 02:14:58 -08:00
João Moura
d4e33f9953 adding fix to hierarchical process 2024-02-07 02:13:19 -08:00
João Moura
435fc57feb preparing v0.5.2 2024-02-06 00:04:53 -08:00
João Moura
2c86f0d07c updating RPM and max_inter logic 2024-02-05 23:14:22 -08:00
João Moura
1eed3a0378 updating docs and readme 2024-02-05 23:13:10 -08:00
João Moura
d7f77b42bf adding manager_llm 2024-02-05 20:46:47 -08:00
João Moura
cb09f17fc7 updating readme 2024-02-04 13:13:42 -08:00
João Moura
d9c092552f moving dependencies 2024-02-04 12:11:11 -08:00
João Moura
a7c05d2e84 updating readme 2024-02-04 12:07:40 -08:00
João Moura
789a92bc2c preparing new version 0.5.0 2024-02-04 12:01:05 -08:00
João Moura
47e8a2cef6 installing mkdocs dependencies 2024-02-04 11:58:21 -08:00
João Moura
ef7ce29fe0 fixing dependencies for mkdocs 2024-02-04 11:51:44 -08:00
João Moura
e2f18e4ee5 adding new docs and smaller fixes 2024-02-04 11:47:49 -08:00
João Moura
e23773e5de Adding multi thread execution 2024-02-03 23:24:41 -08:00
João Moura
fd53df53cd updating docs 2024-02-03 23:23:47 -08:00
João Moura
20c729f0d6 Update README.md 2024-02-03 05:48:54 -03:00
João Moura
5724309e78 simplifying README 2024-02-03 00:04:33 -08:00
João Moura
4f38539b41 adding ability to pass context to tasks 2024-02-02 23:17:02 -08:00
João Moura
fa8626c5ab Update README.md 2024-02-03 02:26:10 -03:00
João Moura
02f9eb6e71 Update README.md 2024-02-03 01:33:59 -03:00
Ilya Sudakov
3c52c9ea92 Update README.md: new header, text clean up, fix broken links (#210)
* Update README.MD

* Update examples section in README.md
2024-02-03 01:29:04 -03:00
Gui Vieira
7efecd10ea Hierarchical process (#206)
* Hierarchical process +  Docs
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-02-02 13:56:35 -03:00
João Moura
a3af73b593 adding task callback 2024-01-30 22:46:20 -03:00
João Moura
c1f42f51eb Update README.md 2024-01-29 22:49:17 -03:00
Guilherme Vieira
e0d97b9916 Fix static typing errors (#187)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-01-29 19:52:14 -03:00
João Moura
66d66bddae Adding support for expected output 2024-01-29 00:11:30 -03:00
IT Lackey
0ddcc07224 Feature: Documentation Site (#188) 2024-01-28 23:43:23 -03:00
Eliad Cohen
e0c1dcd4b9 Addresses typo and clarifiction in comments (#191)
Minor changes include a typo fixed and enhancing
an example for using OpenAI as an agent model with Ollama
via langchain

Resolves #189 #190
2024-01-28 23:42:31 -03:00
João Moura
01bb7c82ed updating website for crewai 2024-01-28 23:36:39 -03:00
João Moura
11ecba745f Update README.md 2024-01-22 11:05:01 -03:00
scott------
5322cff6a9 Update agent.py (#161)
adding tools to the list of attribute descriptions
2024-01-21 16:56:19 -03:00
Greyson LaLonde
e8a31da05d Update some docstrings / typehints (#144) 2024-01-21 16:55:17 -03:00
Prabha Arivalagan
7a93124cdb Fixed the small typo (#168) 2024-01-21 16:54:19 -03:00
João Moura
75a4efc8ba cutting new version 2024-01-14 11:25:09 -03:00
João Moura
e27dd53c78 Add RPM control to both agents and crews (#133)
* moving file into utilities
* creating Logger and RPMController
* Adding support for RPM to agents and crew
2024-01-14 00:22:11 -03:00
João Moura
b0c5e24507 Update tests.yml 2024-01-14 00:11:53 -03:00
João Moura
cce9a8aff2 slightly improving prompts 2024-01-13 11:32:32 -03:00
Jimmy Kounelis
c3833e2ebb Adding Greek translation (#122)
* Adding Greek translation
Co-authored-by: JimJim12 <loljk@Madness>
2024-01-13 11:22:23 -03:00
João Moura
1fc806161f Adding support for Crew throttling using RPM (#124)
* Add translations
* fixing translations
* Adding support for Crew throttling with RPM
2024-01-13 11:20:30 -03:00
Greyson LaLonde
3c74fbf9ab Add github action for black (#116) 2024-01-12 22:06:13 -03:00
João Moura
b487136878 Adding support for translations (#120)
Add translations support
2024-01-12 14:49:36 -03:00
João Moura
70072b4e40 Revamp max iteration Logic (#111)
This now will allow to add a max_inter option to agents while also making sure to force the agent to give it's best final answer before running out of it's max_inter.
2024-01-11 12:32:54 -03:00
Greyson LaLonde
0fde1f6258 Bump to langchain0.1.0 (#108)
* Bump `langchain`, `openai`; add `langchain-openai`

* Update imports to fix warnings
2024-01-11 09:33:43 -03:00
João Moura
f6b9f85099 Update README.md 2024-01-11 09:31:45 -03:00
João Moura
4c1089d335 Update README.md 2024-01-10 21:00:37 -03:00
João Moura
7b5f2b24b3 starting to revamp docs 2024-01-10 13:12:31 -03:00
João Moura
0c2e348239 fixing github action 2024-01-10 12:24:37 -03:00
João Moura
339da3ee1a replacing circleci with github actions 2024-01-10 12:05:42 -03:00
Greyson LaLonde
d122d90df0 Move to src dir usage (#99) 2024-01-10 11:39:36 -03:00
João Moura
c601fbdc12 installing mkdocs as part of the github workflow 2024-01-10 00:46:56 -03:00
João Moura
e5f3e47ccb TYPO 2024-01-10 00:42:12 -03:00
João Moura
6721a0bc6d starting github actions for docs 2024-01-10 00:40:56 -03:00
João Moura
2fc1cc333f starting to setup new documentation 2024-01-10 00:30:18 -03:00
Greyson LaLonde
71f53e4c87 Add imports (#98) 2024-01-10 00:13:06 -03:00
João Moura
e525a28398 updating logo 2024-01-10 00:08:39 -03:00
SashaXser
f6de0928c4 Refractoring (#88)
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2024-01-10 00:04:13 -03:00
João Moura
ae385eca06 bringing output log 2024-01-09 23:57:35 -03:00
yanzz
e2685413ce improved readability (#90) 2024-01-09 23:29:50 -03:00
Chris
6e7bafd758 update example usage in README (#97) 2024-01-09 23:22:42 -03:00
João Moura
abca7f06d5 cutting new version v0.1.24 2024-01-07 21:36:14 -03:00
João Moura
e6805833c2 removing reference for pydantic v1 2024-01-07 21:35:30 -03:00
João Moura
4b802a15c3 Improving agent delegation prompt 2024-01-07 21:35:27 -03:00
Ikko Eltociear Ashimine
e7a201a2f6 Update README.md (#81)
bellow -> below
2024-01-07 13:37:30 -03:00
João Moura
2ef682edf3 Reliability improvements (#77)
* fixing identation for AgentTools
* updating gitignore to exclude quick test script
* startingprompt translation
* supporting individual task output
* adding agent to task output
* cutting new version
* Updating README example
2024-01-07 12:43:23 -03:00
João Moura
ca8c7266ed Tools cache and delegation improvements (#68)
* Fixing repeated tool usage treatment
* Improving agent delegation prompt
2024-01-06 11:46:34 -03:00
João Moura
7dcdde3ccb Update README.md 2024-01-06 01:36:00 -03:00
Chris Bruner
7adaa6b86a Updated the main example in README.md (#61)
Update Example to mention local LLMs
2024-01-06 00:34:28 -03:00
João Moura
0197b8d44c Update README.md 2024-01-06 00:03:03 -03:00
João Moura
6636b4cb8d Update README.md 2024-01-06 00:01:39 -03:00
João Moura
018bb18b6a Update README.md 2024-01-06 00:01:07 -03:00
João Moura
dfc965067a Update README.md 2024-01-05 16:06:48 -03:00
João Moura
db7e91248a Update README.md 2024-01-05 13:50:48 -03:00
João Moura
13bb3abf57 Better agent execution error handling (#54)
A few quality of life improvements around cache handling and repeated tool usage
2024-01-05 11:04:59 -03:00
João Moura
5602160caf Refactoring task cache to be a tool (#50)
* Refactoring task cache to be a tool

The previous implementation of the task caching system was early exiting
the agent executor due to the fact it was returning an AgentFinish object.

This now refactors it to use a cache specific tool that is dynamically
added and forced into the agent in case of a task execution that was
already executed with the same input.
2024-01-04 21:29:42 -03:00
João Moura
35f4169d6a Update README.md 2024-01-04 10:06:08 -03:00
João Moura
c82e29afe0 Update README.md 2024-01-04 10:04:56 -03:00
João Moura
4837f6bbfb Update README.md 2024-01-04 10:04:31 -03:00
João Moura
3f9a0cfd5c Proper README example (#48) 2024-01-04 10:03:23 -03:00
João Moura
c91fe15f6f Update README.md 2024-01-03 20:21:59 -03:00
João Moura
d489c85bf9 bumping langchain version and cutting new version 2024-01-03 18:58:45 -03:00
João Moura
a2cd2d6f48 Updating README example 2024-01-03 18:58:45 -03:00
Scott Stoltzman
f13d117afc Change "agent" to "openhermes" in Ollama example (#33) 2024-01-03 10:38:14 -03:00
SuperMalinge
77e3af6603 Update output_parser.py (#42) 2024-01-02 20:52:12 -03:00
João Moura
8df6cec4e5 Update README.md 2024-01-02 18:51:44 -03:00
João Moura
cb9c31a7b5 Update README.md 2023-12-31 17:41:50 -03:00
Greyson LaLonde
e41844334e Remove model inheritance (#30) 2023-12-31 10:52:08 -03:00
Greyson LaLonde
1f0001b644 Implement CrewAIBaseModel and Update to ConfigDict (#29)
New CrewAIBaseModel:

Base for Agent, Crew, Task.
Includes generated, frozen UUID.
Adds hashing capability
Migrate to ConfigDict:

Replaces class Config with model_config, see this deprecation note .
Benefits:
Adds auditing capability with frozen UUIDs.
2023-12-30 21:52:04 -03:00
Ikko Eltociear Ashimine
469874d858 Update README.md (#27)
Documention -> Documentation
2023-12-30 21:49:20 -03:00
João Moura
c0853ec37d Cutting a new version 0.1.14 2023-12-30 11:03:03 -03:00
João Moura
8547d4651b Small updates to the code formatting 2023-12-30 10:53:10 -03:00
João Moura
2b06dd263f Adding verbose levels 2023-12-30 07:41:38 -03:00
Greyson LaLonde
ed61f467b1 Update to use absolute imports (#17)
Update to use absolute imports
2023-12-29 22:39:59 -03:00
João Moura
d3ecd1d490 Adding tool caching a loop execution prevention. (#25)
* Adding tool caching a loop execution prevention.

This adds some guardrails, to both prevent the same tool to be used
consecutively and also caching tool's results across the entire crew
so it cuts down execution time and eventual LLM calls.

This plays a huge role for smaller opensource models that usually fall
into those behaviors patterns.

It also includes some smaller improvements around the tool prompt and
agent tools, all with the same intention of guiding models into
better conform with agent instructions.
2023-12-29 22:35:23 -03:00
Greyson LaLonde
d214100f0a Refactor Codebase to Use Pydantic v2 and Enhance Type Hints, Documentation (#24)
Update to Pydantic v2:

Transitioned all references from pydantic.v1 to pydantic (v2), ensuring compatibility with the latest Pydantic features and improvements.
Affected components include agent tools, prompts, crew, and task modules.
Refactoring & Alignment with Pydantic Standards:

Refactored the agent module away from traditional __init__ to align more closely with Pydantic best practices.
Updated the crew module to Pydantic v2 and enhanced configurations, allowing JSON and dictionary inputs. Additionally, some (not all) exceptions have been migrated to leverage Pydantic's error-handling capabilities.
Enhancements to Validators and Typings:

Improved validators and type annotations across multiple modules, enhancing code readability and maintainability.
Streamlined the validation process in line with Pydantic v2's methodologies.
Import and Configuration Adjustments:

Updated to test-related absolute imports due to issues with Pytest finding packages through relative imports.
2023-12-29 21:24:30 -03:00
João Moura
8638c328b4 Add .circleci/config.yml (#26)
* Add .circleci/config.yml

---------

Co-authored-by: João Moura <joaomdmoura@mgail.com>
2023-12-29 21:14:15 -03:00
João Moura
ddab457422 Merge pull request #15 from greysonlalonde/gl/devops/ci-code-formatting-enhancements
Update Python to 3.9, Add Code Quality Tools, & Update Lockfile
2023-12-27 17:34:56 -03:00
Greyson Lalonde
1547986b69 Make tools a subpackage 2023-12-27 15:13:42 -05:00
Greyson Lalonde
73716f35fc Run pre-commit hooks
In the title !
2023-12-27 15:13:42 -05:00
Greyson Lalonde
9f78e45cf6 Update autoflake args
This wont format automatically unless --in-place is passed and will remove init imports when missing --ignore-init-module-imports
2023-12-27 15:09:05 -05:00
Greyson Lalonde
ff46294882 Update readme to reflect pre-commit 2023-12-27 15:09:05 -05:00
Greyson Lalonde
d8661afb5f Add pre-commit config w/ new dev deps 2023-12-27 15:09:05 -05:00
Greyson Lalonde
517437ec78 Bump min py to 3.9; add formatting deps
Increased minimum Python version from 3.81 to 3.9 - most projects align with this; added pre-commit hooks, isort, black, & autoflake for code quality; updated lock file.
2023-12-27 15:09:05 -05:00
João Moura
f00e7e89f4 removing AgentVote class 2023-12-27 16:18:08 -03:00
João Moura
de343f3bd0 allowing cassetes to eb versioned 2023-12-27 16:18:08 -03:00
João Moura
d8c26f9579 Adding VCr and cassetes 2023-12-27 16:18:08 -03:00
João Moura
6d11766fbf Merge pull request #14 from jerryjliu/jerry/fix_typo
fix prompt typo
2023-12-27 15:05:50 -03:00
Jerry Liu
fdb94450d6 cr 2023-12-27 09:27:15 -08:00
João Moura
fb511a6488 small updates 2023-12-25 11:18:47 -03:00
João Moura
aa45edd913 Updating readme 2023-12-25 11:17:11 -03:00
João Moura
9e03b5d50e adding more specific guidelines to agent delegation tools 2023-12-25 11:13:46 -03:00
João Moura
78f04f5c95 Merge pull request #12 from JamesChannel1/main
Update agent.py
2023-12-25 09:25:01 -03:00
JamesChannel1
571da68fab Update agent.py
updated docstring
2023-12-25 00:38:21 +00:00
João Moura
c5a191b5c3 Update README.md 2023-12-23 10:18:10 -03:00
João Moura
1e66315eb7 Merge pull request #9 from llxxxll/develop
Update README.md
2023-12-22 10:24:35 -03:00
LiuYongFeng
f9754c9f1f Update README.md
This example can be run faster for openai users.
2023-12-22 11:40:22 +08:00
LiuYongFeng
c01abc9567 Update README.md
Fix the 'SyntaxError: invalid syntax. Perhaps you forgot a comma?' error in this code
2023-12-22 11:35:06 +08:00
João Moura
2bd15411da Updating openai version 2023-12-20 17:21:48 -03:00
João Moura
e0270d6a68 updating specs 2023-12-20 17:20:55 -03:00
João Moura
8c785b2c72 Adding proper support to memory-less agents 2023-12-20 11:30:56 -03:00
João Moura
37e8e99a48 cutting new version 2023-12-19 20:00:50 -03:00
Joao Moura
7e47614a93 Updating to the latest version of langchain 2023-12-19 20:00:50 -03:00
João Moura
0c92a7bd05 Update README.md 2023-12-19 11:06:27 -03:00
João Moura
80206f55d8 Merge pull request #7 from shreyaskarnik/main
Fix typo in readme for valid syntax in example code.
2023-12-18 01:10:49 -03:00
Joao Moura
c7003f0f49 rolling back verison upgrade for now 2023-12-18 01:10:02 -03:00
Joao Moura
7b6af93f63 adding allow_delegation=False to the readme example 2023-12-18 01:09:34 -03:00
Joao Moura
0e09d38020 fixing readme 2023-12-18 01:05:03 -03:00
Shreyas Karnik
ef275bf6f1 Fix typo in readme for valid syntax in example code. 2023-12-09 22:46:33 +00:00
Joao Moura
cb2be30949 rolling back prompt with --- 2023-12-05 00:09:44 -08:00
Joao Moura
cd30e2a5ba Making config optional with default value as it's WIP and Adding new treatment for wrong agent tool calls 2023-12-04 23:58:48 -08:00
Joao Moura
7dfbf71c4d Preparing to cut new version 2023-12-04 00:13:42 -08:00
Joao Moura
601b35acc8 slightly modifications on prompt 2023-12-04 00:12:36 -08:00
Joao Moura
78e833e626 cutting enw version 2023-11-24 17:09:43 -03:00
Joao Moura
c9b2e898ee Allwoing to use other LLM that are not OpenAI 2023-11-24 17:09:06 -03:00
Joao Moura
707bcce402 adding index to README 2023-11-20 18:37:42 -03:00
Joao Moura
7b66df22b1 Preparing to cut new version 2023-11-18 22:11:10 -03:00
João Moura
c7c2c32c8d Merge pull request #3 from manuel-soria/fix-typo-in-readme
fix typo in quickstart snippet
2023-11-17 15:56:13 -03:00
Manuel Soria
7c4c877681 another missing comma 2023-11-17 15:13:31 -03:00
Manuel Soria
d6202e35fe fix typo in quickstart snippet 2023-11-17 15:11:31 -03:00
João Moura
5507c4a366 Merge pull request #2 from joaomdmoura/joaomdmoura/adding-crew-specific-verbose-logs
Adding crew specific verbose logs
2023-11-16 19:17:11 -03:00
João Moura
f52b10be26 Merge branch 'main' into joaomdmoura/adding-crew-specific-verbose-logs 2023-11-16 19:17:04 -03:00
João Moura
4c9bd18a45 Merge pull request #1 from franzejr/patch-1
Fix tiny typo
2023-11-16 18:48:56 -03:00
Franze M
ed93059ec3 Update README.md 2023-11-16 08:17:18 -03:00
12 changed files with 346 additions and 2358 deletions

View File

@@ -11,7 +11,7 @@ dependencies = [
# Core Dependencies
"pydantic>=2.4.2",
"openai>=1.13.3",
"litellm>=1.56.4",
"litellm>=1.44.22",
"instructor>=1.3.3",
# Text Processing

View File

@@ -1457,7 +1457,7 @@ def test_agent_with_ollama_llama3():
assert agent.llm.model == "ollama/llama3.2:3b"
assert agent.llm.base_url == "http://localhost:11434"
task = "Respond in 20 words. Who are you?"
task = "Respond in 20 words. Which model are you?"
response = agent.llm.call([{"role": "user", "content": task}])
assert response
@@ -1473,7 +1473,9 @@ def test_llm_call_with_ollama_llama3():
temperature=0.7,
max_tokens=30,
)
messages = [{"role": "user", "content": "Respond in 20 words. Who are you?"}]
messages = [
{"role": "user", "content": "Respond in 20 words. Which model are you?"}
]
response = llm.call(messages)

View File

@@ -12,862 +12,34 @@ interactions:
available and give your best Final Answer, your job depends on it!\n\nThought:\n\n",
"options": {"stop": ["\nObservation:"]}, "stream": false}'
headers:
accept:
Accept:
- '*/*'
accept-encoding:
Accept-Encoding:
- gzip, deflate
connection:
Connection:
- keep-alive
content-length:
Content-Length:
- '839'
host:
- localhost:11434
user-agent:
- litellm/1.56.4
Content-Type:
- application/json
User-Agent:
- python-requests/2.32.3
method: POST
uri: http://localhost:11434/api/generate
response:
content: '{"model":"llama3.2:3b","created_at":"2024-12-31T16:56:15.759718Z","response":"Final
Answer: Artificial Intelligence (AI) refers to the development of computer systems
able to perform tasks that typically require human intelligence, including learning,
problem-solving, decision-making, and perception.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,2675,527,1296,3560,13,1296,93371,198,7927,4443,5915,374,25,1296,5915,198,1271,3041,856,1888,4686,1620,4320,311,279,3465,1005,279,4839,2768,3645,1473,85269,25,358,1457,649,3041,264,2294,4320,198,19918,22559,25,4718,1620,4320,2011,387,279,2294,323,279,1455,4686,439,3284,11,433,2011,387,15632,7633,382,40,28832,1005,1521,20447,11,856,2683,14117,389,433,2268,14711,2724,1473,5520,5546,25,83017,1148,15592,374,304,832,11914,271,2028,374,279,1755,13186,369,701,1620,4320,25,362,832,1355,18886,16540,315,15592,198,9514,28832,471,279,5150,4686,2262,439,279,1620,4320,11,539,264,12399,382,11382,0,1115,374,48174,3062,311,499,11,1005,279,7526,2561,323,3041,701,1888,13321,22559,11,701,2683,14117,389,433,2268,85269,1473,128009,128006,78191,128007,271,19918,22559,25,59294,22107,320,15836,8,19813,311,279,4500,315,6500,6067,3025,311,2804,9256,430,11383,1397,3823,11478,11,2737,6975,11,3575,99246,11,5597,28846,11,323,21063,13],"total_duration":1156303250,"load_duration":35999125,"prompt_eval_count":181,"prompt_eval_duration":408000000,"eval_count":38,"eval_duration":711000000}'
body:
string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:05:52.24992Z","response":"Final
Answer: Artificial Intelligence (AI) refers to the development of computer
systems capable of performing tasks that typically require human intelligence,
such as learning, problem-solving, decision-making, and perception.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,2675,527,1296,3560,13,1296,93371,198,7927,4443,5915,374,25,1296,5915,198,1271,3041,856,1888,4686,1620,4320,311,279,3465,1005,279,4839,2768,3645,1473,85269,25,358,1457,649,3041,264,2294,4320,198,19918,22559,25,4718,1620,4320,2011,387,279,2294,323,279,1455,4686,439,3284,11,433,2011,387,15632,7633,382,40,28832,1005,1521,20447,11,856,2683,14117,389,433,2268,14711,2724,1473,5520,5546,25,83017,1148,15592,374,304,832,11914,271,2028,374,279,1755,13186,369,701,1620,4320,25,362,832,1355,18886,16540,315,15592,198,9514,28832,471,279,5150,4686,2262,439,279,1620,4320,11,539,264,12399,382,11382,0,1115,374,48174,3062,311,499,11,1005,279,7526,2561,323,3041,701,1888,13321,22559,11,701,2683,14117,389,433,2268,85269,1473,128009,128006,78191,128007,271,19918,22559,25,59294,22107,320,15836,8,19813,311,279,4500,315,6500,6067,13171,315,16785,9256,430,11383,1397,3823,11478,11,1778,439,6975,11,3575,99246,11,5597,28846,11,323,21063,13],"total_duration":1461909875,"load_duration":39886208,"prompt_eval_count":181,"prompt_eval_duration":701000000,"eval_count":39,"eval_duration":719000000}'
headers:
Content-Length:
- '1528'
- '1537'
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 31 Dec 2024 16:56:15 GMT
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.56.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 31 Dec 2024 16:56:15 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.56.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 31 Dec 2024 16:56:15 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
- Thu, 02 Jan 2025 20:05:52 GMT
status:
code: 200
message: OK
version: 1

View File

@@ -1,863 +1,36 @@
interactions:
- request:
body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Who
are you?\n\n", "options": {"stop": ["\nObservation:"]}, "stream": false}'
which model are you?\n\n", "options": {"stop": ["\nObservation:"]}, "stream":
false}'
headers:
accept:
Accept:
- '*/*'
accept-encoding:
Accept-Encoding:
- gzip, deflate
connection:
Connection:
- keep-alive
content-length:
- '144'
host:
- localhost:11434
user-agent:
- litellm/1.56.4
Content-Length:
- '156'
Content-Type:
- application/json
User-Agent:
- python-requests/2.32.3
method: POST
uri: http://localhost:11434/api/generate
response:
content: '{"model":"llama3.2:3b","created_at":"2024-12-31T16:57:54.063894Z","response":"I''m
an AI designed to provide information and assist with inquiries, while maintaining
a neutral and respectful tone always.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,6319,311,3493,2038,323,7945,449,44983,11,1418,20958,264,21277,323,49150,16630,2744,13],"total_duration":651386042,"load_duration":41061917,"prompt_eval_count":38,"prompt_eval_duration":204000000,"eval_count":23,"eval_duration":405000000}'
body:
string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:07:07.623404Z","response":"I''m
an AI designed to assist and communicate with users, utilizing a combination
of natural language processing models.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,902,1646,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,6319,311,7945,323,19570,449,3932,11,35988,264,10824,315,5933,4221,8863,4211,13],"total_duration":1076617833,"load_duration":46505416,"prompt_eval_count":40,"prompt_eval_duration":626000000,"eval_count":22,"eval_duration":399000000}'
headers:
Content-Length:
- '692'
- '690'
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 31 Dec 2024 16:57:54 GMT
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.56.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 31 Dec 2024 16:57:54 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.56.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 31 Dec 2024 16:57:54 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
- Thu, 02 Jan 2025 20:07:07 GMT
status:
code: 200
message: OK
version: 1

View File

@@ -1,449 +1,36 @@
interactions:
- request:
body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Who
are you?\n\n", "options": {"temperature": 0.7, "num_predict": 30}, "stream":
body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Which
model are you??\n\n", "options": {"num_predict": 30, "temperature": 0.7}, "stream":
false}'
headers:
accept:
Accept:
- '*/*'
accept-encoding:
Accept-Encoding:
- gzip, deflate
connection:
Connection:
- keep-alive
content-length:
- '155'
host:
- localhost:11434
user-agent:
- litellm/1.56.4
Content-Length:
- '164'
Content-Type:
- application/json
User-Agent:
- python-requests/2.32.3
method: POST
uri: http://localhost:11434/api/generate
response:
content: '{"model":"llama3.2:3b","created_at":"2024-12-31T17:00:06.295261Z","response":"I''m
an AI assistant, here to provide information and answer questions to the best
of my abilities and knowledge.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,18328,11,1618,311,3493,2038,323,4320,4860,311,279,1888,315,856,18000,323,6677,13],"total_duration":826912750,"load_duration":32648125,"prompt_eval_count":38,"prompt_eval_duration":389000000,"eval_count":23,"eval_duration":404000000}'
body:
string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:24:24.812595Z","response":"I''m
an AI, specifically a large language model, designed to understand and respond
to user queries with accuracy.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,16299,1646,527,499,71291,128009,128006,78191,128007,271,40,2846,459,15592,11,11951,264,3544,4221,1646,11,6319,311,3619,323,6013,311,1217,20126,449,13708,13],"total_duration":827817584,"load_duration":41560542,"prompt_eval_count":39,"prompt_eval_duration":384000000,"eval_count":23,"eval_duration":400000000}'
headers:
Content-Length:
- '675'
- '683'
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 31 Dec 2024 17:00:06 GMT
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"name": "llama3.2:3b"}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '23'
content-type:
- application/json
host:
- localhost:11434
user-agent:
- litellm/1.56.4
method: POST
uri: http://localhost:11434/api/show
response:
content: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
and conditions for use, reproduction, distribution \\nand modification of the
Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\n**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed
to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
\\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
\\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
for use, reproduction, distribution \\nand modification of the Llama Materials
set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications, manuals
and documentation accompanying Llama 3.2\\ndistributed by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
or \u201Cyou\u201D means you, or your employer or any other person or entity
(if you are \\nentering into this Agreement on such person or entity\u2019s
behalf), of the age required under\\napplicable laws, rules or regulations to
provide legal consent and that has legal authority\\nto bind your employer or
such other person or entity if you are entering in this Agreement\\non their
behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language models
and software and algorithms, including\\nmachine-learning model code, trained
model weights, inference-enabling code, training-enabling code,\\nfine-tuning
enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and Documentation
(and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located in
or, \\nif you are an entity, your principal place of business is in the EEA
or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside of the
EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below or by using
or distributing any portion or element of the Llama Materials,\\nyou agree to
be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
\ a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
and royalty-free limited license under Meta\u2019s intellectual property or
other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works \\nof, and make modifications to the
Llama Materials. \\n\\n b. Redistribution and Use. \\n\\n i. If
you distribute or make available the Llama Materials (or any derivative works
thereof), \\nor a product or service (including another AI model) that contains
any of them, you shall (A) provide\\na copy of this Agreement with any such
Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
a related website, user interface, blogpost, about page, or product documentation.
If you use the\\nLlama Materials or any outputs or results of the Llama Materials
to create, train, fine tune, or\\notherwise improve an AI model, which is distributed
or made available, you shall also include \u201CLlama\u201D\\nat the beginning
of any such AI model name.\\n\\n ii. If you receive Llama Materials,
or any derivative works thereof, from a Licensee as part\\nof an integrated
end user product, then Section 2 of this Agreement will not apply to you. \\n\\n
\ iii. You must retain in all copies of the Llama Materials that you distribute
the \\nfollowing attribution notice within a \u201CNotice\u201D text file distributed
as a part of such copies: \\n\u201CLlama 3.2 is licensed under the Llama 3.2
Community License, Copyright \xA9 Meta Platforms,\\nInc. All Rights Reserved.\u201D\\n\\n
\ iv. Your use of the Llama Materials must comply with applicable laws
and regulations\\n(including trade compliance laws and regulations) and adhere
to the Acceptable Use Policy for\\nthe Llama Materials (available at https://www.llama.com/llama3_2/use-policy),
which is hereby \\nincorporated by reference into this Agreement.\\n \\n2.
Additional Commercial Terms. If, on the Llama 3.2 version release date, the
monthly active users\\nof the products or services made available by or for
Licensee, or Licensee\u2019s affiliates, \\nis greater than 700 million monthly
active users in the preceding calendar month, you must request \\na license
from Meta, which Meta may grant to you in its sole discretion, and you are not
authorized to\\nexercise any of the rights under this Agreement unless or until
Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer of Warranty.
UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND \\nRESULTS
THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS, WITHOUT WARRANTIES OF
ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND
IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF TITLE, NON-INFRINGEMENT,
MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE\\nFOR
DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS
AND ASSUME ANY RISKS ASSOCIATED\\nWITH YOUR USE OF THE LLAMA MATERIALS AND ANY
OUTPUT AND RESULTS.\\n\\n4. Limitation of Liability. IN NO EVENT WILL META OR
ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, \\nWHETHER IN CONTRACT,
TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
\\nFOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,
EXEMPLARY OR PUNITIVE DAMAGES, EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED
OF THE POSSIBILITY OF ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n
\ a. No trademark licenses are granted under this Agreement, and in connection
with the Llama Materials, \\nneither Meta nor Licensee may use any name or mark
owned by or associated with the other or any of its affiliates, \\nexcept as
required for reasonable and customary use in describing and redistributing the
Llama Materials or as \\nset forth in this Section 5(a). Meta hereby grants
you a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
\\nto comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s
brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
All goodwill arising out of your use of the Mark \\nwill inure to the benefit
of Meta.\\n\\n b. Subject to Meta\u2019s ownership of Llama Materials and
derivatives made by or for Meta, with respect to any\\n derivative works
and modifications of the Llama Materials that are made by you, as between you
and Meta,\\n you are and will be the owner of such derivative works and modifications.\\n\\n
\ c. If you institute litigation or other proceedings against Meta or any
entity (including a cross-claim or\\n counterclaim in a lawsuit) alleging
that the Llama Materials or Llama 3.2 outputs or results, or any portion\\n
\ of any of the foregoing, constitutes infringement of intellectual property
or other rights owned or licensable\\n by you, then any licenses granted
to you under this Agreement shall terminate as of the date such litigation or\\n
\ claim is filed or instituted. You will indemnify and hold harmless Meta
from and against any claim by any third\\n party arising out of or related
to your use or distribution of the Llama Materials.\\n\\n6. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
or access\\nto the Llama Materials and will continue in full force and effect
until terminated in accordance with the terms\\nand conditions herein. Meta
may terminate this Agreement if you are in breach of any term or condition of
this\\nAgreement. Upon termination of this Agreement, you shall delete and cease
use of the Llama Materials. Sections 3,\\n4 and 7 shall survive the termination
of this Agreement. \\n\\n7. Governing Law and Jurisdiction. This Agreement will
be governed and construed under the laws of the State of \\nCalifornia without
regard to choice of law principles, and the UN Convention on Contracts for the
International\\nSale of Goods does not apply to this Agreement. The courts of
California shall have exclusive jurisdiction of\\nany dispute arising out of
this Agreement.\\\"\\nLICENSE \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta
is committed to promoting safe and fair use of its tools and features, including
Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use
Policy (\u201C**Policy**\u201D). The most recent copy of this policy can be
found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You agree
you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1. Violate
the law or others\u2019 rights, including to:\\n 1. Engage in, promote, generate,
contribute to, encourage, plan, incite, or further illegal or unlawful activity
or content, such as:\\n 1. Violence or terrorism\\n 2. Exploitation
or harm to children, including the solicitation, creation, acquisition, or dissemination
of child exploitative content or failure to report Child Sexual Abuse Material\\n
\ 3. Human trafficking, exploitation, and sexual violence\\n 4.
The illegal distribution of information or materials to minors, including obscene
materials, or failure to employ legally required age-gating in connection with
such information or materials.\\n 5. Sexual solicitation\\n 6.
Any other criminal activity\\n 1. Engage in, promote, incite, or facilitate
the harassment, abuse, threatening, or bullying of individuals or groups of
individuals\\n 2. Engage in, promote, incite, or facilitate discrimination
or other unlawful or harmful conduct in the provision of employment, employment
benefits, credit, housing, other economic benefits, or other essential goods
and services\\n 3. Engage in the unauthorized or unlicensed practice of any
profession including, but not limited to, financial, legal, medical/health,
or related professional practices\\n 4. Collect, process, disclose, generate,
or infer private or sensitive information about individuals, including information
about individuals\u2019 identity, health, or demographic information, unless
you have obtained the right to do so in accordance with applicable law\\n 5.
Engage in or facilitate any action or generate any content that infringes, misappropriates,
or otherwise violates any third-party rights, including the outputs or results
of any products or services using the Llama Materials\\n 6. Create, generate,
or facilitate the creation of malicious code, malware, computer viruses or do
anything else that could disable, overburden, interfere with or impair the proper
working, integrity, operation or appearance of a website or computer system\\n
\ 7. Engage in any action, or facilitate any action, to intentionally circumvent
or remove usage restrictions or other safety measures, or to enable functionality
disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in the
planning or development of activities that present a risk of death or bodily
harm to individuals, including use of Llama 3.2 related to the following:\\n
\ 8. Military, warfare, nuclear industries or applications, espionage, use
for materials or activities that are subject to the International Traffic Arms
Regulations (ITAR) maintained by the United States Department of State or to
the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons
Convention Implementation Act of 1997\\n 9. Guns and illegal weapons (including
weapon development)\\n 10. Illegal drugs and regulated/controlled substances\\n
\ 11. Operation of critical infrastructure, transportation technologies, or
heavy machinery\\n 12. Self-harm or harm to others, including suicide, cutting,
and eating disorders\\n 13. Any content intended to incite or promote violence,
abuse, or any infliction of bodily harm to an individual\\n3. Intentionally
deceive or mislead others, including use of Llama 3.2 related to the following:\\n
\ 14. Generating, promoting, or furthering fraud or the creation or promotion
of disinformation\\n 15. Generating, promoting, or furthering defamatory
content, including the creation of defamatory statements, images, or other content\\n
\ 16. Generating, promoting, or further distributing spam\\n 17. Impersonating
another individual without consent, authorization, or legal right\\n 18.
Representing that the use of Llama 3.2 or outputs are human-generated\\n 19.
Generating or facilitating false online engagement, including fake reviews and
other means of fake online engagement\\n4. Fail to appropriately disclose to
end users any known dangers of your AI system\\n5. Interact with third party
tools, models, or software designed to generate unlawful content or engage in
unlawful or harmful conduct and/or represent that the outputs of such tools,
models, or software are associated with Meta or Llama 3.2\\n\\nWith respect
to any multimodal models included in Llama 3.2, the rights granted under Section
1(a) of the Llama 3.2 Community License Agreement are not being granted to you
if you are an individual domiciled in, or a company with a principal place of
business in, the European Union. This restriction does not apply to end users
of a product or service that incorporates any such multimodal models.\\n\\nPlease
report any violation of this Policy, software \u201Cbug,\u201D or other problems
that could lead to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
\ \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
if .Tools }}When you receive a tool call response, use the output to format
an answer to the orginal user question.\\n\\nYou are a helpful assistant with
tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range $i,
$_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
if and $.Tools $last }}\\n\\nGiven the following functions, please respond with
a JSON for a function call with its proper arguments that best answers the given
prompt.\\n\\nRespond in the format {\\\"name\\\": function name, \\\"parameters\\\":
dictionary of argument name and its value}. Do not use variables.\\n\\n{{ range
$.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
}}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else }}\\n\\n{{
.Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
.Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
headers:
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 31 Dec 2024 17:00:06 GMT
Transfer-Encoding:
- chunked
http_version: HTTP/1.1
status_code: 200
- Thu, 02 Jan 2025 20:24:24 GMT
status:
code: 200
message: OK
version: 1

View File

@@ -28,9 +28,10 @@ def test_create_success(mock_subprocess):
with in_temp_dir():
tool_command = ToolCommand()
with patch.object(tool_command, "login") as mock_login, patch(
"sys.stdout", new=StringIO()
) as fake_out:
with (
patch.object(tool_command, "login") as mock_login,
patch("sys.stdout", new=StringIO()) as fake_out,
):
tool_command.create("test-tool")
output = fake_out.getvalue()
@@ -82,7 +83,7 @@ def test_install_success(mock_get, mock_subprocess_run):
capture_output=False,
text=True,
check=True,
env=unittest.mock.ANY
env=unittest.mock.ANY,
)
assert "Successfully installed sample-tool" in output

View File

@@ -333,16 +333,16 @@ def test_manager_agent_delegating_to_assigned_task_agent():
)
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
# which sets the output attribute of the task
task.output = mock_task_output
with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Verify execute_sync was called once
@@ -350,12 +350,20 @@ def test_manager_agent_delegating_to_assigned_task_agent():
# Get the tools argument from the call
_, kwargs = mock_execute_sync.call_args
tools = kwargs['tools']
tools = kwargs["tools"]
# Verify the delegation tools were passed correctly
assert len(tools) == 2
assert any("Delegate a specific task to one of the following coworkers: Researcher" in tool.description for tool in tools)
assert any("Ask a specific question to one of the following coworkers: Researcher" in tool.description for tool in tools)
assert any(
"Delegate a specific task to one of the following coworkers: Researcher"
in tool.description
for tool in tools
)
assert any(
"Ask a specific question to one of the following coworkers: Researcher"
in tool.description
for tool in tools
)
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -404,7 +412,7 @@ def test_manager_agent_delegates_with_varied_role_cases():
backstory="A researcher with spaces in role name",
allow_delegation=False,
)
writer_caps = Agent(
role="SENIOR WRITER", # All caps
goal="Write with caps in role",
@@ -426,13 +434,13 @@ def test_manager_agent_delegates_with_varied_role_cases():
)
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
task.output = mock_task_output
with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Verify execute_sync was called once
@@ -440,20 +448,32 @@ def test_manager_agent_delegates_with_varied_role_cases():
# Get the tools argument from the call
_, kwargs = mock_execute_sync.call_args
tools = kwargs['tools']
tools = kwargs["tools"]
# Verify the delegation tools were passed correctly and can handle case/whitespace variations
assert len(tools) == 2
# Check delegation tool descriptions (should work despite case/whitespace differences)
delegation_tool = tools[0]
question_tool = tools[1]
assert "Delegate a specific task to one of the following coworkers:" in delegation_tool.description
assert " Researcher " in delegation_tool.description or "SENIOR WRITER" in delegation_tool.description
assert "Ask a specific question to one of the following coworkers:" in question_tool.description
assert " Researcher " in question_tool.description or "SENIOR WRITER" in question_tool.description
assert (
"Delegate a specific task to one of the following coworkers:"
in delegation_tool.description
)
assert (
" Researcher " in delegation_tool.description
or "SENIOR WRITER" in delegation_tool.description
)
assert (
"Ask a specific question to one of the following coworkers:"
in question_tool.description
)
assert (
" Researcher " in question_tool.description
or "SENIOR WRITER" in question_tool.description
)
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -479,6 +499,7 @@ def test_crew_with_delegating_agents():
== "In the rapidly evolving landscape of technology, AI agents have emerged as formidable tools, revolutionizing how we interact with data and automate tasks. These sophisticated systems leverage machine learning and natural language processing to perform a myriad of functions, from virtual personal assistants to complex decision-making companions in industries such as finance, healthcare, and education. By mimicking human intelligence, AI agents can analyze massive data sets at unparalleled speeds, enabling businesses to uncover valuable insights, enhance productivity, and elevate user experiences to unprecedented levels.\n\nOne of the most striking aspects of AI agents is their adaptability; they learn from their interactions and continuously improve their performance over time. This feature is particularly valuable in customer service where AI agents can address inquiries, resolve issues, and provide personalized recommendations without the limitations of human fatigue. Moreover, with intuitive interfaces, AI agents enhance user interactions, making technology more accessible and user-friendly, thereby breaking down barriers that have historically hindered digital engagement.\n\nDespite their immense potential, the deployment of AI agents raises important ethical and practical considerations. Issues related to privacy, data security, and the potential for job displacement necessitate thoughtful dialogue and proactive measures. Striking a balance between technological innovation and societal impact will be crucial as organizations integrate these agents into their operations. Additionally, ensuring transparency in AI decision-making processes is vital to maintain public trust as AI agents become an integral part of daily life.\n\nLooking ahead, the future of AI agents appears bright, with ongoing advancements promising even greater capabilities. As we continue to harness the power of AI, we can expect these agents to play a transformative role in shaping various sectors—streamlining workflows, enabling smarter decision-making, and fostering more personalized experiences. Embracing this technology responsibly can lead to a future where AI agents not only augment human effort but also inspire creativity and efficiency across the board, ultimately redefining our interaction with the digital world."
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_delegating_agents_should_not_override_task_tools():
from typing import Type
@@ -489,6 +510,7 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
class TestToolInput(BaseModel):
"""Input schema for TestTool."""
query: str = Field(..., description="Query to process")
class TestTool(BaseTool):
@@ -516,24 +538,29 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
)
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
# which sets the output attribute of the task
tasks[0].output = mock_task_output
with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Execute the task and verify both tools are present
_, kwargs = mock_execute_sync.call_args
tools = kwargs['tools']
tools = kwargs["tools"]
assert any(
isinstance(tool, TestTool) for tool in tools
), "TestTool should be present"
assert any(
"delegate" in tool.name.lower() for tool in tools
), "Delegation tool should be present"
assert any(isinstance(tool, TestTool) for tool in tools), "TestTool should be present"
assert any("delegate" in tool.name.lower() for tool in tools), "Delegation tool should be present"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_delegating_agents_should_not_override_agent_tools():
@@ -545,6 +572,7 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
class TestToolInput(BaseModel):
"""Input schema for TestTool."""
query: str = Field(..., description="Query to process")
class TestTool(BaseTool):
@@ -563,7 +591,7 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
Task(
description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
expected_output="A 4 paragraph article about AI.",
agent=new_ceo
agent=new_ceo,
)
]
@@ -574,24 +602,29 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
)
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
# which sets the output attribute of the task
tasks[0].output = mock_task_output
with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Execute the task and verify both tools are present
_, kwargs = mock_execute_sync.call_args
tools = kwargs['tools']
tools = kwargs["tools"]
assert any(
isinstance(tool, TestTool) for tool in new_ceo.tools
), "TestTool should be present"
assert any(
"delegate" in tool.name.lower() for tool in tools
), "Delegation tool should be present"
assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), "TestTool should be present"
assert any("delegate" in tool.name.lower() for tool in tools), "Delegation tool should be present"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_tools_override_agent_tools():
@@ -603,6 +636,7 @@ def test_task_tools_override_agent_tools():
class TestToolInput(BaseModel):
"""Input schema for TestTool."""
query: str = Field(..., description="Query to process")
class TestTool(BaseTool):
@@ -630,14 +664,10 @@ def test_task_tools_override_agent_tools():
description="Write a test task",
expected_output="Test output",
agent=new_researcher,
tools=[AnotherTestTool()]
tools=[AnotherTestTool()],
)
crew = Crew(
agents=[new_researcher],
tasks=[task],
process=Process.sequential
)
crew = Crew(agents=[new_researcher], tasks=[task], process=Process.sequential)
crew.kickoff()
@@ -650,6 +680,7 @@ def test_task_tools_override_agent_tools():
assert len(new_researcher.tools) == 1
assert isinstance(new_researcher.tools[0], TestTool)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_tools_override_agent_tools_with_allow_delegation():
"""
@@ -702,13 +733,13 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
)
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# We mock execute_sync to verify which tools get used at runtime
with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Inspect the call kwargs to verify the actual tools passed to execution
@@ -716,16 +747,23 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
used_tools = kwargs["tools"]
# Confirm AnotherTestTool is present but TestTool is not
assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), "AnotherTestTool should be present"
assert not any(isinstance(tool, TestTool) for tool in used_tools), "TestTool should not be present among used tools"
assert any(
isinstance(tool, AnotherTestTool) for tool in used_tools
), "AnotherTestTool should be present"
assert not any(
isinstance(tool, TestTool) for tool in used_tools
), "TestTool should not be present among used tools"
# Confirm delegation tool(s) are present
assert any("delegate" in tool.name.lower() for tool in used_tools), "Delegation tool should be present"
assert any(
"delegate" in tool.name.lower() for tool in used_tools
), "Delegation tool should be present"
# Finally, make sure the agent's original tools remain unchanged
assert len(researcher_with_delegation.tools) == 1
assert isinstance(researcher_with_delegation.tools[0], TestTool)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_verbose_output(capsys):
tasks = [
@@ -1012,8 +1050,8 @@ def test_three_task_with_async_execution():
)
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.asyncio
@pytest.mark.vcr(filter_headers=["authorization"])
async def test_crew_async_kickoff():
inputs = [
{"topic": "dog"},
@@ -1060,8 +1098,9 @@ async def test_crew_async_kickoff():
assert result[0].token_usage.successful_requests > 0 # type: ignore
@pytest.mark.asyncio
@pytest.mark.vcr(filter_headers=["authorization"])
def test_async_task_execution_call_count():
async def test_async_task_execution_call_count():
from unittest.mock import MagicMock, patch
list_ideas = Task(
@@ -1188,7 +1227,6 @@ def test_kickoff_for_each_empty_input():
assert results == []
@pytest.mark.vcr(filter_headers=["authorization"])
def test_kickoff_for_each_invalid_input():
"""Tests if kickoff_for_each raises TypeError for invalid input types."""
@@ -1211,7 +1249,6 @@ def test_kickoff_for_each_invalid_input():
crew.kickoff_for_each("invalid input")
@pytest.mark.vcr(filter_headers=["authorization"])
def test_kickoff_for_each_error_handling():
"""Tests error handling in kickoff_for_each when kickoff raises an error."""
from unittest.mock import patch
@@ -1248,7 +1285,6 @@ def test_kickoff_for_each_error_handling():
crew.kickoff_for_each(inputs=inputs)
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.asyncio
async def test_kickoff_async_basic_functionality_and_output():
"""Tests the basic functionality and output of kickoff_async."""
@@ -1283,7 +1319,6 @@ async def test_kickoff_async_basic_functionality_and_output():
mock_kickoff.assert_called_once_with(inputs)
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.asyncio
async def test_async_kickoff_for_each_async_basic_functionality_and_output():
"""Tests the basic functionality and output of kickoff_for_each_async."""
@@ -1330,7 +1365,6 @@ async def test_async_kickoff_for_each_async_basic_functionality_and_output():
mock_kickoff_async.assert_any_call(inputs=input_data)
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.asyncio
async def test_async_kickoff_for_each_async_empty_input():
"""Tests if akickoff_for_each_async handles an empty input list."""
@@ -1514,12 +1548,12 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
crew = Crew(agents=[programmer], tasks=[task])
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Get the tools that were actually used in execution
@@ -1528,7 +1562,10 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
# Verify that exactly one tool was used and it was a CodeInterpreterTool
assert len(used_tools) == 1, "Should have exactly one tool"
assert isinstance(used_tools[0], CodeInterpreterTool), "Tool should be CodeInterpreterTool"
assert isinstance(
used_tools[0], CodeInterpreterTool
), "Tool should be CodeInterpreterTool"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_delegation_is_not_enabled_if_there_are_only_one_agent():
@@ -1639,16 +1676,16 @@ def test_hierarchical_crew_creation_tasks_with_agents():
)
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
# which sets the output attribute of the task
task.output = mock_task_output
with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync:
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Verify execute_sync was called once
@@ -1656,12 +1693,20 @@ def test_hierarchical_crew_creation_tasks_with_agents():
# Get the tools argument from the call
_, kwargs = mock_execute_sync.call_args
tools = kwargs['tools']
tools = kwargs["tools"]
# Verify the delegation tools were passed correctly
assert len(tools) == 2
assert any("Delegate a specific task to one of the following coworkers: Senior Writer" in tool.description for tool in tools)
assert any("Ask a specific question to one of the following coworkers: Senior Writer" in tool.description for tool in tools)
assert any(
"Delegate a specific task to one of the following coworkers: Senior Writer"
in tool.description
for tool in tools
)
assert any(
"Ask a specific question to one of the following coworkers: Senior Writer"
in tool.description
for tool in tools
)
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -1684,9 +1729,7 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
)
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Create a mock Future that returns our TaskOutput
@@ -1697,7 +1740,9 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
# which sets the output attribute of the task
task.output = mock_task_output
with patch.object(Task, 'execute_async', return_value=mock_future) as mock_execute_async:
with patch.object(
Task, "execute_async", return_value=mock_future
) as mock_execute_async:
crew.kickoff()
# Verify execute_async was called once
@@ -1705,12 +1750,20 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
# Get the tools argument from the call
_, kwargs = mock_execute_async.call_args
tools = kwargs['tools']
tools = kwargs["tools"]
# Verify the delegation tools were passed correctly
assert len(tools) == 2
assert any("Delegate a specific task to one of the following coworkers: Senior Writer\n" in tool.description for tool in tools)
assert any("Ask a specific question to one of the following coworkers: Senior Writer\n" in tool.description for tool in tools)
assert any(
"Delegate a specific task to one of the following coworkers: Senior Writer\n"
in tool.description
for tool in tools
)
assert any(
"Ask a specific question to one of the following coworkers: Senior Writer\n"
in tool.description
for tool in tools
)
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -2039,7 +2092,6 @@ def test_crew_output_file_end_to_end(tmp_path):
assert expected_file.exists(), f"Output file {expected_file} was not created"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_output_file_validation_failures():
"""Test output file validation failures in a crew context."""
agent = Agent(
@@ -2055,7 +2107,7 @@ def test_crew_output_file_validation_failures():
description="Analyze data",
expected_output="Analysis results",
agent=agent,
output_file="../output.txt"
output_file="../output.txt",
)
Crew(agents=[agent], tasks=[task]).kickoff()
@@ -2065,7 +2117,7 @@ def test_crew_output_file_validation_failures():
description="Analyze data",
expected_output="Analysis results",
agent=agent,
output_file="output.txt | rm -rf /"
output_file="output.txt | rm -rf /",
)
Crew(agents=[agent], tasks=[task]).kickoff()
@@ -2075,7 +2127,7 @@ def test_crew_output_file_validation_failures():
description="Analyze data",
expected_output="Analysis results",
agent=agent,
output_file="~/output.txt"
output_file="~/output.txt",
)
Crew(agents=[agent], tasks=[task]).kickoff()
@@ -2085,12 +2137,11 @@ def test_crew_output_file_validation_failures():
description="Analyze data",
expected_output="Analysis results",
agent=agent,
output_file="{invalid-name}/output.txt"
output_file="{invalid-name}/output.txt",
)
Crew(agents=[agent], tasks=[task]).kickoff()
@pytest.mark.vcr(filter_headers=["authorization"])
def test_manager_agent():
from unittest.mock import patch
@@ -3049,6 +3100,7 @@ def test_task_tools_preserve_code_execution_tools():
class TestToolInput(BaseModel):
"""Input schema for TestTool."""
query: str = Field(..., description="Query to process")
class TestTool(BaseTool):
@@ -3082,7 +3134,7 @@ def test_task_tools_preserve_code_execution_tools():
description="Write a program to calculate fibonacci numbers.",
expected_output="A working fibonacci calculator.",
agent=programmer,
tools=[TestTool()]
tools=[TestTool()],
)
crew = Crew(
@@ -3092,12 +3144,12 @@ def test_task_tools_preserve_code_execution_tools():
)
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Get the tools that were actually used in execution
@@ -3105,12 +3157,21 @@ def test_task_tools_preserve_code_execution_tools():
used_tools = kwargs["tools"]
# Verify all expected tools are present
assert any(isinstance(tool, TestTool) for tool in used_tools), "Task's TestTool should be present"
assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), "CodeInterpreterTool should be present"
assert any("delegate" in tool.name.lower() for tool in used_tools), "Delegation tool should be present"
assert any(
isinstance(tool, TestTool) for tool in used_tools
), "Task's TestTool should be present"
assert any(
isinstance(tool, CodeInterpreterTool) for tool in used_tools
), "CodeInterpreterTool should be present"
assert any(
"delegate" in tool.name.lower() for tool in used_tools
), "Delegation tool should be present"
# Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
assert len(used_tools) == 4, "Should have TestTool, CodeInterpreter, and 2 delegation tools"
assert (
len(used_tools) == 4
), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multimodal_flag_adds_multimodal_tools():
@@ -3139,13 +3200,13 @@ def test_multimodal_flag_adds_multimodal_tools():
crew = Crew(agents=[multimodal_agent], tasks=[task], process=Process.sequential)
mock_task_output = TaskOutput(
description="Mock description",
raw="mocked output",
agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Mock execute_sync to verify the tools passed at runtime
with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync:
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Get the tools that were actually used in execution
@@ -3153,13 +3214,14 @@ def test_multimodal_flag_adds_multimodal_tools():
used_tools = kwargs["tools"]
# Check that the multimodal tool was added
assert any(isinstance(tool, AddImageTool) for tool in used_tools), (
"AddImageTool should be present when agent is multimodal"
)
assert any(
isinstance(tool, AddImageTool) for tool in used_tools
), "AddImageTool should be present when agent is multimodal"
# Verify we have exactly one tool (just the AddImageTool)
assert len(used_tools) == 1, "Should only have the AddImageTool"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multimodal_agent_image_tool_handling():
"""
@@ -3201,10 +3263,10 @@ def test_multimodal_agent_image_tool_handling():
mock_task_output = TaskOutput(
description="Mock description",
raw="A detailed analysis of the image",
agent="Image Analyst"
agent="Image Analyst",
)
with patch.object(Task, 'execute_sync') as mock_execute_sync:
with patch.object(Task, "execute_sync") as mock_execute_sync:
# Set up the mock to return our task output
mock_execute_sync.return_value = mock_task_output
@@ -3213,7 +3275,7 @@ def test_multimodal_agent_image_tool_handling():
# Get the tools that were passed to execute_sync
_, kwargs = mock_execute_sync.call_args
tools = kwargs['tools']
tools = kwargs["tools"]
# Verify the AddImageTool is present and properly configured
image_tools = [tool for tool in tools if tool.name == "Add image to content"]
@@ -3223,7 +3285,7 @@ def test_multimodal_agent_image_tool_handling():
image_tool = image_tools[0]
result = image_tool._run(
image_url="https://example.com/test-image.jpg",
action="Please analyze this image"
action="Please analyze this image",
)
# Verify the tool returns the expected format
@@ -3233,6 +3295,7 @@ def test_multimodal_agent_image_tool_handling():
assert result["content"][0]["type"] == "text"
assert result["content"][1]["type"] == "image_url"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multimodal_agent_live_image_analysis():
"""
@@ -3246,7 +3309,7 @@ def test_multimodal_agent_live_image_analysis():
allow_delegation=False,
multimodal=True,
verbose=True,
llm="gpt-4o"
llm="gpt-4o",
)
# Create a task for image analysis
@@ -3257,19 +3320,18 @@ def test_multimodal_agent_live_image_analysis():
Image: {image_url}
""",
expected_output="A comprehensive description of the image contents.",
agent=image_analyst
agent=image_analyst,
)
# Create and run the crew
crew = Crew(
agents=[image_analyst],
tasks=[analyze_image]
)
crew = Crew(agents=[image_analyst], tasks=[analyze_image])
# Execute with an image URL
result = crew.kickoff(inputs={
"image_url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="
})
result = crew.kickoff(
inputs={
"image_url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="
}
)
# Verify we got a meaningful response
assert isinstance(result.raw, str)

View File

@@ -578,14 +578,6 @@ def test_multiple_docling_sources():
assert docling_source.content is not None
def test_docling_source_with_local_file():
current_dir = Path(__file__).parent
pdf_path = current_dir / "crewai_quickstart.pdf"
docling_source = CrewDoclingSource(file_paths=[pdf_path])
assert docling_source.file_paths == [pdf_path]
assert docling_source.content is not None
def test_file_path_validation():
"""Test file path validation for knowledge sources."""
current_dir = Path(__file__).parent
@@ -606,6 +598,6 @@ def test_file_path_validation():
# Test neither file_path nor file_paths provided
with pytest.raises(
ValueError,
match="file_path/file_paths must be a Path, str, or a list of these types"
match="file_path/file_paths must be a Path, str, or a list of these types",
):
PDFKnowledgeSource()

View File

@@ -719,7 +719,7 @@ def test_interpolate_inputs():
task = Task(
description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 interesting ideas about {topic}.",
output_file="/tmp/{topic}/output_{date}.txt"
output_file="/tmp/{topic}/output_{date}.txt",
)
task.interpolate_inputs(inputs={"topic": "AI", "date": "2024"})
@@ -742,41 +742,35 @@ def test_interpolate_inputs():
def test_interpolate_only():
"""Test the interpolate_only method for various scenarios including JSON structure preservation."""
task = Task(
description="Unused in this test",
expected_output="Unused in this test"
description="Unused in this test", expected_output="Unused in this test"
)
# Test JSON structure preservation
json_string = '{"info": "Look at {placeholder}", "nested": {"val": "{nestedVal}"}}'
result = task.interpolate_only(
input_string=json_string,
inputs={"placeholder": "the data", "nestedVal": "something else"}
inputs={"placeholder": "the data", "nestedVal": "something else"},
)
assert '"info": "Look at the data"' in result
assert '"val": "something else"' in result
assert "{placeholder}" not in result
assert "{nestedVal}" not in result
# Test normal string interpolation
normal_string = "Hello {name}, welcome to {place}!"
result = task.interpolate_only(
input_string=normal_string,
inputs={"name": "John", "place": "CrewAI"}
input_string=normal_string, inputs={"name": "John", "place": "CrewAI"}
)
assert result == "Hello John, welcome to CrewAI!"
# Test empty string
result = task.interpolate_only(
input_string="",
inputs={"unused": "value"}
)
result = task.interpolate_only(input_string="", inputs={"unused": "value"})
assert result == ""
# Test string with no placeholders
no_placeholders = "Hello, this is a test"
result = task.interpolate_only(
input_string=no_placeholders,
inputs={"unused": "value"}
input_string=no_placeholders, inputs={"unused": "value"}
)
assert result == no_placeholders
@@ -880,56 +874,65 @@ def test_key():
def test_output_file_validation():
"""Test output file path validation."""
# Valid paths
assert Task(
description="Test task",
expected_output="Test output",
output_file="output.txt"
).output_file == "output.txt"
assert Task(
description="Test task",
expected_output="Test output",
output_file="/tmp/output.txt"
).output_file == "tmp/output.txt"
assert Task(
description="Test task",
expected_output="Test output",
output_file="{dir}/output_{date}.txt"
).output_file == "{dir}/output_{date}.txt"
assert (
Task(
description="Test task",
expected_output="Test output",
output_file="output.txt",
).output_file
== "output.txt"
)
assert (
Task(
description="Test task",
expected_output="Test output",
output_file="/tmp/output.txt",
).output_file
== "tmp/output.txt"
)
assert (
Task(
description="Test task",
expected_output="Test output",
output_file="{dir}/output_{date}.txt",
).output_file
== "{dir}/output_{date}.txt"
)
# Invalid paths
with pytest.raises(ValueError, match="Path traversal"):
Task(
description="Test task",
expected_output="Test output",
output_file="../output.txt"
output_file="../output.txt",
)
with pytest.raises(ValueError, match="Path traversal"):
Task(
description="Test task",
expected_output="Test output",
output_file="folder/../output.txt"
output_file="folder/../output.txt",
)
with pytest.raises(ValueError, match="Shell special characters"):
Task(
description="Test task",
expected_output="Test output",
output_file="output.txt | rm -rf /"
output_file="output.txt | rm -rf /",
)
with pytest.raises(ValueError, match="Shell expansion"):
Task(
description="Test task",
expected_output="Test output",
output_file="~/output.txt"
output_file="~/output.txt",
)
with pytest.raises(ValueError, match="Shell expansion"):
Task(
description="Test task",
expected_output="Test output",
output_file="$HOME/output.txt"
output_file="$HOME/output.txt",
)
with pytest.raises(ValueError, match="Invalid template variable"):
Task(
description="Test task",
expected_output="Test output",
output_file="{invalid-name}/output.txt"
output_file="{invalid-name}/output.txt",
)

View File

@@ -8,48 +8,49 @@ from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
class TestAgentTool(BaseAgentTool):
"""Concrete implementation of BaseAgentTool for testing."""
def _run(self, *args, **kwargs):
"""Implement required _run method."""
return "Test response"
@pytest.mark.parametrize("role_name,should_match", [
('Futel Official Infopoint', True), # exact match
(' "Futel Official Infopoint" ', True), # extra quotes and spaces
('Futel Official Infopoint\n', True), # trailing newline
('"Futel Official Infopoint"', True), # embedded quotes
(' FUTEL\nOFFICIAL INFOPOINT ', True), # multiple whitespace and newline
('futel official infopoint', True), # lowercase
('FUTEL OFFICIAL INFOPOINT', True), # uppercase
('Non Existent Agent', False), # non-existent agent
(None, False), # None agent name
])
@pytest.mark.parametrize(
"role_name,should_match",
[
("Futel Official Infopoint", True), # exact match
(' "Futel Official Infopoint" ', True), # extra quotes and spaces
("Futel Official Infopoint\n", True), # trailing newline
('"Futel Official Infopoint"', True), # embedded quotes
(" FUTEL\nOFFICIAL INFOPOINT ", True), # multiple whitespace and newline
("futel official infopoint", True), # lowercase
("FUTEL OFFICIAL INFOPOINT", True), # uppercase
("Non Existent Agent", False), # non-existent agent
(None, False), # None agent name
],
)
def test_agent_tool_role_matching(role_name, should_match):
"""Test that agent tools can match roles regardless of case, whitespace, and special characters."""
# Create test agent
test_agent = Agent(
role='Futel Official Infopoint',
goal='Answer questions about Futel',
backstory='Futel Football Club info',
allow_delegation=False
role="Futel Official Infopoint",
goal="Answer questions about Futel",
backstory="Futel Football Club info",
allow_delegation=False,
)
# Create test agent tool
agent_tool = TestAgentTool(
name="test_tool",
description="Test tool",
agents=[test_agent]
name="test_tool", description="Test tool", agents=[test_agent]
)
# Test role matching
result = agent_tool._execute(
agent_name=role_name,
task='Test task',
context=None
)
result = agent_tool._execute(agent_name=role_name, task="Test task", context=None)
if should_match:
assert "coworker mentioned not found" not in result.lower(), \
f"Should find agent with role name: {role_name}"
assert (
"coworker mentioned not found" not in result.lower()
), f"Should find agent with role name: {role_name}"
else:
assert "coworker mentioned not found" in result.lower(), \
f"Should not find agent with role name: {role_name}"
assert (
"coworker mentioned not found" in result.lower()
), f"Should not find agent with role name: {role_name}"

View File

@@ -15,10 +15,7 @@ def test_task_without_guardrail():
agent.execute_task.return_value = "test result"
agent.crew = None
task = Task(
description="Test task",
expected_output="Output"
)
task = Task(description="Test task", expected_output="Output")
result = task.execute_sync(agent=agent)
assert isinstance(result, TaskOutput)
@@ -27,6 +24,7 @@ def test_task_without_guardrail():
def test_task_with_successful_guardrail():
"""Test that successful guardrail validation passes transformed result."""
def guardrail(result: TaskOutput):
return (True, result.raw.upper())
@@ -35,11 +33,7 @@ def test_task_with_successful_guardrail():
agent.execute_task.return_value = "test result"
agent.crew = None
task = Task(
description="Test task",
expected_output="Output",
guardrail=guardrail
)
task = Task(description="Test task", expected_output="Output", guardrail=guardrail)
result = task.execute_sync(agent=agent)
assert isinstance(result, TaskOutput)
@@ -48,22 +42,20 @@ def test_task_with_successful_guardrail():
def test_task_with_failing_guardrail():
"""Test that failing guardrail triggers retry with error context."""
def guardrail(result: TaskOutput):
return (False, "Invalid format")
agent = Mock()
agent.role = "test_agent"
agent.execute_task.side_effect = [
"bad result",
"good result"
]
agent.execute_task.side_effect = ["bad result", "good result"]
agent.crew = None
task = Task(
description="Test task",
expected_output="Output",
guardrail=guardrail,
max_retries=1
max_retries=1,
)
# First execution fails guardrail, second succeeds
@@ -77,6 +69,7 @@ def test_task_with_failing_guardrail():
def test_task_with_guardrail_retries():
"""Test that guardrail respects max_retries configuration."""
def guardrail(result: TaskOutput):
return (False, "Invalid format")
@@ -89,7 +82,7 @@ def test_task_with_guardrail_retries():
description="Test task",
expected_output="Output",
guardrail=guardrail,
max_retries=2
max_retries=2,
)
with pytest.raises(Exception) as exc_info:
@@ -102,6 +95,7 @@ def test_task_with_guardrail_retries():
def test_guardrail_error_in_context():
"""Test that guardrail error is passed in context for retry."""
def guardrail(result: TaskOutput):
return (False, "Expected JSON, got string")
@@ -113,11 +107,12 @@ def test_guardrail_error_in_context():
description="Test task",
expected_output="Output",
guardrail=guardrail,
max_retries=1
max_retries=1,
)
# Mock execute_task to succeed on second attempt
first_call = True
def execute_task(task, context, tools):
nonlocal first_call
if first_call:

52
uv.lock generated
View File

@@ -1,18 +1,18 @@
version = 1
requires-python = ">=3.10, <3.13"
resolution-markers = [
"python_full_version < '3.11' and platform_system == 'Darwin'",
"python_full_version < '3.11' and platform_machine == 'aarch64' and platform_system == 'Linux'",
"(python_full_version < '3.11' and platform_machine != 'aarch64' and platform_system != 'Darwin') or (python_full_version < '3.11' and platform_system != 'Darwin' and platform_system != 'Linux')",
"python_full_version == '3.11.*' and platform_system == 'Darwin'",
"python_full_version == '3.11.*' and platform_machine == 'aarch64' and platform_system == 'Linux'",
"(python_full_version == '3.11.*' and platform_machine != 'aarch64' and platform_system != 'Darwin') or (python_full_version == '3.11.*' and platform_system != 'Darwin' and platform_system != 'Linux')",
"python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system == 'Darwin'",
"python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux'",
"(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux')",
"python_full_version >= '3.12.4' and platform_system == 'Darwin'",
"python_full_version >= '3.12.4' and platform_machine == 'aarch64' and platform_system == 'Linux'",
"(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system != 'Darwin') or (python_full_version >= '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux')",
"python_full_version < '3.11' and sys_platform == 'darwin'",
"python_full_version < '3.11' and platform_machine == 'aarch64' and sys_platform == 'linux'",
"(python_full_version < '3.11' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.11' and sys_platform != 'darwin' and sys_platform != 'linux')",
"python_full_version == '3.11.*' and sys_platform == 'darwin'",
"python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'",
"(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform != 'darwin' and sys_platform != 'linux')",
"python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform == 'darwin'",
"python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
"(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
"python_full_version >= '3.12.4' and sys_platform == 'darwin'",
"python_full_version >= '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'",
"(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
]
[[package]]
@@ -683,7 +683,7 @@ requires-dist = [
{ name = "instructor", specifier = ">=1.3.3" },
{ name = "json-repair", specifier = ">=0.25.2" },
{ name = "jsonref", specifier = ">=1.1.0" },
{ name = "litellm", specifier = ">=1.56.4" },
{ name = "litellm", specifier = ">=1.44.22" },
{ name = "mem0ai", marker = "extra == 'mem0'", specifier = ">=0.1.29" },
{ name = "openai", specifier = ">=1.13.3" },
{ name = "openpyxl", specifier = ">=3.1.5" },
@@ -2229,24 +2229,24 @@ wheels = [
[[package]]
name = "litellm"
version = "1.56.4"
version = "1.50.2"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "aiohttp" },
{ name = "click" },
{ name = "httpx" },
{ name = "importlib-metadata" },
{ name = "jinja2" },
{ name = "jsonschema" },
{ name = "openai" },
{ name = "pydantic" },
{ name = "python-dotenv" },
{ name = "requests" },
{ name = "tiktoken" },
{ name = "tokenizers" },
]
sdist = { url = "https://files.pythonhosted.org/packages/83/ea/2c51d16c244a64dd3f0bdb1757aef798cf943b92e5695da04e3e42ba09e0/litellm-1.56.4.tar.gz", hash = "sha256:2808ca21878d200f7676a3d11e5bf2b5e3349ae504628f279cd7297c7dbd2038", size = 6284983 }
sdist = { url = "https://files.pythonhosted.org/packages/a7/45/4d54617b267a96f1f7c17c0010ea1aba20e30a3672b873fe92a6001e5952/litellm-1.50.2.tar.gz", hash = "sha256:b244c9a0e069cc626b85fb9f5cc252114aaff1225500da30ce0940f841aef8ea", size = 6096949 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/8f/25/2fd7b28a270b2963e8fa0ecf6aab4db47c54d932cc5aac8bc87e7ebc3755/litellm-1.56.4-py3-none-any.whl", hash = "sha256:699a8db46f7de045069a77c435e13244b5fdaf5df1c8cb5e6ad675ef7e104ccd", size = 6564370 },
{ url = "https://files.pythonhosted.org/packages/22/f3/89a4d65d1b9286eb5ac6a6e92dd93523d92f3142a832e60c00d5cad64176/litellm-1.50.2-py3-none-any.whl", hash = "sha256:99cac60c78037946ab809b7cfbbadad53507bb2db8ae39391b4be215a0869fdd", size = 6318265 },
]
[[package]]
@@ -2900,7 +2900,7 @@ name = "nvidia-cudnn-cu12"
version = "9.1.0.70"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
{ name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 },
@@ -2927,9 +2927,9 @@ name = "nvidia-cusolver-cu12"
version = "11.4.5.107"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
{ name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
{ name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
{ name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
{ name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
{ name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/bc/1d/8de1e5c67099015c834315e333911273a8c6aaba78923dd1d1e25fc5f217/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd", size = 124161928 },
@@ -2940,7 +2940,7 @@ name = "nvidia-cusparse-cu12"
version = "12.1.0.106"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
{ name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/65/5b/cfaeebf25cd9fdec14338ccb16f6b2c4c7fa9163aefcf057d86b9cc248bb/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c", size = 195958278 },
@@ -3040,7 +3040,7 @@ wheels = [
[[package]]
name = "openai"
version = "1.58.1"
version = "1.52.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "anyio" },
@@ -3052,9 +3052,9 @@ dependencies = [
{ name = "tqdm" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/27/3c/b1ecce430ed56fa3ac1b0676966d3250aab9c70a408232b71e419ea62148/openai-1.58.1.tar.gz", hash = "sha256:f5a035fd01e141fc743f4b0e02c41ca49be8fab0866d3b67f5f29b4f4d3c0973", size = 343411 }
sdist = { url = "https://files.pythonhosted.org/packages/80/ac/54c76352d493866637756b7c0ecec44f0b5bafb8fe753d98472cf6cfe4ce/openai-1.52.1.tar.gz", hash = "sha256:383b96c7e937cbec23cad5bf5718085381e4313ca33c5c5896b54f8e1b19d144", size = 310069 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/8e/5a/d22cd07f1a99b9e8b3c92ee0c1959188db4318828a3d88c9daac120bdd69/openai-1.58.1-py3-none-any.whl", hash = "sha256:e2910b1170a6b7f88ef491ac3a42c387f08bd3db533411f7ee391d166571d63c", size = 454279 },
{ url = "https://files.pythonhosted.org/packages/ad/31/28a83e124e9f9dd04c83b5aeb6f8b1770f45addde4dd3d34d9a9091590ad/openai-1.52.1-py3-none-any.whl", hash = "sha256:f23e83df5ba04ee0e82c8562571e8cb596cd88f9a84ab783e6c6259e5ffbfb4a", size = 386945 },
]
[[package]]
@@ -5165,7 +5165,7 @@ name = "triton"
version = "3.0.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" },
{ name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/45/27/14cc3101409b9b4b9241d2ba7deaa93535a217a211c86c4cc7151fb12181/triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e1efef76935b2febc365bfadf74bcb65a6f959a9872e5bddf44cc9e0adce1e1a", size = 209376304 },