Commit Graph

1275 Commits

Author SHA1 Message Date
Lorenze Jay
773da3f994 Remove unused stream method from BaseLLM class to enhance code clarity and maintainability. 2025-03-24 14:07:10 -07:00
Lorenze Jay
ae7f7468d7 Merge branch 'main' of github.com:crewAIInc/crewAI into devin/1741108142-custom-llm-support 2025-03-24 14:02:49 -07:00
Lorenze Jay
782ae12694 Merge branch 'devin/1741108142-custom-llm-support' of github.com:crewAIInc/crewAI into devin/1741108142-custom-llm-support 2025-03-24 13:56:27 -07:00
Lorenze Jay
e659c352df Refactor Crew class and LLM hierarchy for improved type handling and code clarity
- Update Crew class methods to enhance readability with consistent formatting and type hints.
- Change LLM class to inherit from BaseLLM for better structure.
- Remove unnecessary type checks and streamline tool handling in CrewAgentExecutor.
- Adjust BaseLLM to provide default implementations for stop words and context window size methods.
- Clean up AISuiteLLM by removing unused methods related to stop words and context window size.
2025-03-24 13:56:23 -07:00
Tony Kipkemboi
bdc92deade docs: update changelog dates (#2437)
* docs: update changelog dates

* docs: add aws bedrock tools docs

* docs: fix incorrect respect_context_window parameter in Crew example
2025-03-24 12:06:50 -04:00
Brandon Hancock (bhancock_ai)
ed1f009c64 Feat/improve yaml extraction (#2428)
* Support wildcard handling in `emit()`

Change `emit()` to call handlers registered for parent classes using
`isinstance()`. Ensures that base event handlers receive derived
events.

* Fix failing test

* Remove unused variable

* update interpolation to work with example response types in yaml docs

* make tests

* fix circular deps

* Fixing interpolation imports

* Improve test

---------

Co-authored-by: Vinicius Brasil <vini@hey.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2025-03-21 18:59:55 -07:00
Matisse
bb3829a9ed docs: Update model reference in LLM configuration (#2267)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-21 15:12:26 -04:00
Fernando Galves
0a116202f0 Update the context window size for Amazon Bedrock FM- llm.py (#2304)
Update the context window size for Amazon Bedrock Foundation Models.

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2025-03-21 14:48:25 -04:00
Stefano Baccianella
4daa88fa59 As explained in https://github.com/mangiucugna/json_repair?tab=readme-ov-file#performance-considerations we can skip a wasteful json.loads() here and save quite some time (#2397)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
2025-03-21 14:25:19 -04:00
Parth Patel
53067f8b92 add Mem0 OSS support (#2429)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-21 13:57:24 -04:00
Saurabh Misra
d3a09c3180 ️ Speed up method CrewAgentParser._clean_action by 427,565% (#2382)
Here is the optimized version of the program.

Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-21 13:51:14 -04:00
Saurabh Misra
4d7aacb5f2 ️ Speed up method Repository.is_git_repo by 72,270% (#2381)
Here is the optimized version of the `Repository` class.

Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-21 13:43:48 -04:00
Julio Peixoto
6b1cf78e41 docs: add detailed docstrings to Telemetry class methods (#2377)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-21 13:34:16 -04:00
Patcher
80f1a88b63 Upgrade OTel SDK version to 1.30.0 (#2375)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-21 13:26:50 -04:00
Jorge Gonzalez
32da76a2ca Use task in the note about how methods names need to match task names (#2355)
The note is about the task but mentions the agent incorrectly.

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-21 13:17:43 -04:00
Gustavo Satheler
3aa48dcd58 fix: move agent tools for a variable instead of use format (#2319)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-21 12:32:54 -04:00
Tony Kipkemboi
03f1d57463 Merge pull request #2430 from crewAIInc/update-llm-docs
docs: add documentation for Local NVIDIA NIM with WSL2
2025-03-20 12:57:37 -07:00
Tony Kipkemboi
4725d0de0d Merge branch 'main' into update-llm-docs 2025-03-20 12:50:06 -07:00
Arthur Chien
b766af75f2 fix the _extract_thought (#2398)
* fix the _extract_thought

the regex string should be same with prompt in en.json:129
...\nThought: I now know the final answer\nFinal Answer: the...

* fix Action match

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-20 15:44:44 -04:00
Tony Kipkemboi
b2c8779f4c Add documentation for Local NVIDIA NIM with WSL2 2025-03-20 12:39:37 -07:00
Tony Kipkemboi
df266bda01 Update documentation: Add changelog, fix formatting issues, replace mint.json with docs.json (#2400) 2025-03-20 14:44:21 -04:00
Lorenze Jay
2155acb3a3 docs: Update JSONSearchTool and RagTool configuration parameter from 'embedder' to 'embedding_model' (#2311)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-20 13:11:37 -04:00
Sir Qasim
794574957e Add note to create ./knowldge folder for source file management (#2297)
This update includes a note in the documentation instructing users to create a ./knowldge folder. All source files (such as .txt, .pdf, .xlsx, .json) should be placed in this folder for centralized management. This change aims to streamline file organization and improve accessibility across projects.

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-20 12:54:17 -04:00
Sir Qasim
66b19311a7 Fix crewai run Command Issue for Flow Projects and Cloud Deployment (#2291)
This PR addresses an issue with the crewai run command following the creation of a flow project. Previously, the update command interfered with execution, causing it not to work as expected. With these changes, the command now runs according to the instructions in the readme.md, and it also improves deployment support when using CrewAI Cloud.

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-20 12:48:02 -04:00
devin-ai-integration[bot]
9fc84fc1ac Fix incorrect import statement in memory examples documentation (fixes #2395) (#2396)
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>
2025-03-20 12:17:26 -04:00
Amine Saihi
f8f9df6d1d update doc SpaceNewsKnowledgeSource code snippet (#2275)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-20 12:06:21 -04:00
João Moura
6e94edb777 TYPO 2025-03-20 08:21:17 -07:00
Vini Brasil
bbe896d48c Support wildcard handling in emit() (#2424)
* Support wildcard handling in `emit()`

Change `emit()` to call handlers registered for parent classes using
`isinstance()`. Ensures that base event handlers receive derived
events.

* Fix failing test

* Remove unused variable
2025-03-20 09:59:17 -04:00
Seyed Mostafa Meshkati
9298054436 docs: add base_url env for anthropic llm example (#2204)
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-20 09:48:11 -04:00
Fernando Galves
90b7937796 Update documentation (#2199)
* Update llms.mdx

Update Amazon Bedrock section with more information about the foundation models available.

* Update llms.mdx

fix the description of Amazon Bedrock section

* Update llms.mdx

Remove the incorrect </tab> tag

* Update llms.mdx

Add Claude 3.7 Sonnet to the Amazon Bedrock list

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-20 09:42:23 -04:00
elda27
520933b4c5 Fix: More comfortable validation #2177 (#2178)
* Fix: More confortable validation

* Fix: union type support

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-20 09:28:31 -04:00
Vini Brasil
fe0813e831 Improve MethodExecutionFailedEvent.error typing (#2401) 2025-03-18 12:52:23 -04:00
Brandon Hancock (bhancock_ai)
33cebea15b spelling and tab fix (#2394) 2025-03-17 16:31:23 -04:00
João Moura
e723e5ca3f preparign new version 0.108.0 2025-03-17 09:13:21 -07:00
Jakub Kopecký
24f1a19310 feat: add docs for ApifyActorsTool (#2254)
* add docs for ApifyActorsTool

* improve readme, add link to template

* format

* improve tool docs

* improve readme

* Update apifyactorstool.mdx (#1)

* Update apifyactorstool.mdx

* Update apifyactorstool.mdx

* dans suggestions

* custom apify icon

* update descripton

* Update apifyactorstool.mdx

---------

Co-authored-by: Jan Čurn <jan.curn@gmail.com>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-16 12:29:57 -04:00
João Moura
9fc7d2de0a Merge branch 'main' into devin/1741108142-custom-llm-support 2025-03-14 03:11:33 -03:00
devin-ai-integration[bot]
d0959573dc Fix type check error: Remove duplicate @property decorator for fingerprint in Crew class (#2369)
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>
2025-03-14 03:08:55 -03:00
Vivek Soundrapandi
939afd5f82 Bug fix in document (#2370)
A bug is in the document, where the wirte section task method is not invoked before passing on to context. This results in an error as expectaion in utlitities is a dict but a function gets passed.

this is discussed clearly here: https://community.crewai.com/t/attribute-error-str-object-has-no-attribute-get/1079/16
2025-03-14 03:02:38 -03:00
João Moura
d42e58e199 adding fingerprints (#2332)
* adding fingerprints

* fixed

* fix

* Fix Pydantic v2 compatibility in SecurityConfig and Fingerprint classes (#2335)

* Fix Pydantic v2 compatibility in SecurityConfig and Fingerprint classes

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

* Fix type-checker errors in fingerprint properties

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

* Enhance security validation in Fingerprint and SecurityConfig classes

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>

* incorporate small improvements / changes

* Expect different

* Remove redundant null check in Crew.fingerprint property (#2342)

* Remove redundant null check in Crew.fingerprint property and add security module

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

* Enhance security module with type hints, improved UUID namespace, metadata validation, and versioning

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>

---------

Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
2025-03-14 03:00:30 -03:00
Lorenze Jay
7cae76a631 Remove unused tool_calls handling in AISuiteLLM chat completion method for cleaner code. 2025-03-13 11:59:20 -07:00
Lorenze Jay
21cbbd790c Merge branch 'main' of github.com:crewAIInc/crewAI into devin/1741108142-custom-llm-support 2025-03-13 11:56:08 -07:00
Lorenze Jay
000bab4cf5 Enhance Event Listener with Rich Visualization and Improved Logging (#2321)
* Enhance Event Listener with Rich Visualization and Improved Logging

* Add verbose flag to EventListener for controlled logging

* Update crew test to set EventListener verbose flag

* Refactor EventListener logging and visualization with improved tool usage tracking

* Improve task logging with task ID display in EventListener

* Fix EventListener tool branch removal and type hinting

* Add type hints to EventListener class attributes

* Simplify EventListener import in Crew class

* Refactor EventListener tree node creation and remove unused method

* Refactor EventListener to utilize ConsoleFormatter for improved logging and visualization

* Enhance EventListener with property setters for crew, task, agent, tool, flow, and method branches to streamline state management

* Refactor crew test to instantiate EventListener and set verbose flags for improved clarity in logging

* Keep private parts private

* Remove unused import and clean up type hints in EventListener

* Enhance flow logging in EventListener and ConsoleFormatter by including flow ID in tree creation and status updates for better traceability.

---------

Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>
Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
2025-03-13 11:07:32 -07:00
Lorenze Jay
144b96986e Refactor AISuiteLLM to include tools parameter in completion methods
- Update the _prepare_completion_params method to accept an optional tools parameter
- Modify the chat completion method to utilize the new tools parameter for enhanced functionality
- Clean up print statements for better code clarity
2025-03-13 08:10:33 -07:00
Tony Kipkemboi
8df1042180 docs: add instructions for upgrading crewAI with uv tool (#2363) 2025-03-13 10:38:32 -04:00
Lorenze Jay
9a70528296 Update type hint for initialize_chat_llm to support BaseLLM
- Modify the return type of initialize_chat_llm function to allow for both LLM and BaseLLM instances
- Ensure compatibility with recent changes in create_llm function
2025-03-12 14:59:37 -07:00
Lorenze Jay
80c31fb55b Enhance create_llm function to support BaseLLM type
- Update the create_llm function to accept both LLM and BaseLLM instances
- Ensure compatibility with existing LLM handling logic
2025-03-12 14:56:47 -07:00
Lorenze Jay
902c330113 Enhance CustomLLM and JWTAuthLLM initialization with model parameter
- Update CustomLLM to accept a model parameter during initialization
- Modify test cases to include the new model argument
- Ensure JWTAuthLLM and TimeoutHandlingLLM also utilize the model parameter in their constructors
- Update type hints in create_llm function to support both LLM and BaseLLM types
2025-03-12 08:16:59 -07:00
Lorenze Jay
b305ef8f48 Remove abstract method set_callbacks from BaseLLM class 2025-03-12 08:16:35 -07:00
Lorenze Jay
afe220d3e8 Improve stop words handling in CrewAgentExecutor
- Add support for handling existing stop words in LLM configuration
- Ensure stop words are correctly merged and deduplicated
- Update type hints to support both LLM and BaseLLM types
2025-03-12 08:15:30 -07:00
Lorenze Jay
7cb3c8bb4b Update LLM imports and type hints across multiple files
- Modify imports in crew_chat.py to use LLM instead of BaseLLM
- Update type hints in llm_utils.py to use LLM type
- Add optional `stop` parameter to BaseLLM initialization
- Refactor type handling for LLM creation and usage
2025-03-11 16:01:10 -07:00