* docs: Fix major memory system documentation issues - Remove misleading deprecation warnings, fix confusing comments, clearly separate three memory approaches, provide accurate examples that match implementation
* fix: Correct broken image paths in README - Update crewai_logo.png and asset.png paths to point to docs/images/ directory instead of docs/ directly
* docs: Add system prompt transparency and customization guide - Add 'Understanding Default System Instructions' section to address black-box concerns - Document what CrewAI automatically injects into prompts - Provide code examples to inspect complete system prompts - Show 3 methods to override default instructions - Include observability integration examples with Langfuse - Add best practices for production prompt management
* docs: Fix implementation accuracy issues in memory documentation - Fix Ollama embedding URL parameter and remove unsupported Cohere input_type parameter
* docs: Reference observability docs instead of showing specific tool examples
* docs: Reorganize knowledge documentation for better developer experience - Move quickstart examples right after overview for immediate hands-on experience - Create logical learning progression: basics → configuration → advanced → troubleshooting - Add comprehensive agent vs crew knowledge guide with working examples - Consolidate debugging and troubleshooting in dedicated section - Organize best practices by topic in accordion format - Improve content flow from simple concepts to advanced features - Ensure all examples are grounded in actual codebase implementation
* docs: enhance custom LLM documentation with comprehensive examples and accurate imports
* docs: reorganize observability tools into dedicated section with comprehensive overview and improved navigation
* docs: rename how-to section to learn and add comprehensive overview page
* docs: finalize documentation reorganization and update navigation labels
* docs: enhance README with comprehensive badges, navigation links, and getting started video
* feat: Add inject_date flag to Agent for automatic date injection
Co-Authored-By: Joe Moura <joao@crewai.com>
* feat: Add date_format parameter and error handling to inject_date feature
Co-Authored-By: Joe Moura <joao@crewai.com>
* fix: Update test implementation for inject_date feature
Co-Authored-By: Joe Moura <joao@crewai.com>
* fix: Add date format validation to prevent invalid formats
Co-Authored-By: Joe Moura <joao@crewai.com>
* docs: Update documentation for inject_date feature
Co-Authored-By: Joe Moura <joao@crewai.com>
* unnecesary
* new tests
---------
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>
* Add reasoning attribute to Agent class
Co-Authored-By: Joe Moura <joao@crewai.com>
* Address PR feedback: improve type hints, error handling, refactor reasoning handler, and enhance tests and docs
Co-Authored-By: Joe Moura <joao@crewai.com>
* Implement function calling for reasoning and move prompts to translations
Co-Authored-By: Joe Moura <joao@crewai.com>
* Simplify function calling implementation with better error handling
Co-Authored-By: Joe Moura <joao@crewai.com>
* Enhance system prompts to leverage agent context (role, goal, backstory)
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix lint and type-checker issues
Co-Authored-By: Joe Moura <joao@crewai.com>
* Enhance system prompts to better leverage agent context
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix backstory access in reasoning handler for Python 3.12 compatibility
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>
* CLI command added
* Added reset agent knowledge function
* Reduced verbose
* Added test cases
* Added docs
* Llama test case failing
* Changed _reset_agent_knowledge function
* Fixed new line error
* Added docs
* fixed the new line error
* Refractored
* Uncommmented some test cases
* ruff check fixed
* fixed run type checks
* fixed run type checks
* fixed run type checks
* Made reset_fn callable by casting to silence run type checks
* Changed the reset_knowledge as it expects only list of knowledge
* Fixed typo in docs
* Refractored the memory_system
* Minor Changes
* fixed test case
* Fixed linting issues
* Network test cases failing
---------
Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
The Gemini & Vertex sections were conflated and a little hard to
distingush, so I have put them in separate sections.
Also added the latest 2.5 and 2.0 flash-lite models, and added a note
that Gemma models work too.
Co-authored-by: Tony Kipkemboi <iamtonykipkemboi@gmail.com>
* feat: implement knowledge retrieval events in Agent
This commit introduces a series of knowledge retrieval events in the Agent class, enhancing its ability to handle knowledge queries. New events include KnowledgeRetrievalStartedEvent, KnowledgeRetrievalCompletedEvent, KnowledgeQueryGeneratedEvent, KnowledgeQueryFailedEvent, and KnowledgeSearchQueryCompletedEvent. The Agent now emits these events during knowledge retrieval processes, allowing for better tracking and handling of knowledge queries. Additionally, the console formatter has been updated to handle these new events, providing visual feedback during knowledge retrieval operations.
* refactor: update knowledge query handling in Agent
This commit refines the knowledge query processing in the Agent class by renaming variables for clarity and optimizing the query rewriting logic. The system prompt has been updated in the translation file to enhance clarity and context for the query rewriting process. These changes aim to improve the overall readability and maintainability of the code.
* fix: add missing newline at end of en.json file
* fix broken tests
* refactor: rename knowledge query events and enhance retrieval handling
This commit renames the KnowledgeQueryGeneratedEvent to KnowledgeQueryStartedEvent to better reflect its purpose. It also updates the event handling in the EventListener and ConsoleFormatter classes to accommodate the new event structure. Additionally, the retrieval knowledge is now included in the KnowledgeRetrievalCompletedEvent, improving the overall knowledge retrieval process.
* docs for transparancy
* refactor: improve error handling in knowledge query processing
This commit refactors the knowledge query handling in the Agent class by changing the order of checks for LLM compatibility. It now logs a warning and emits a failure event if the LLM is not an instance of BaseLLM before attempting to call the LLM. Additionally, the task_prompt attribute has been removed from the KnowledgeQueryFailedEvent, simplifying the event structure.
* test: add unit test for knowledge search query and VCR cassette
This commit introduces a new test, `test_get_knowledge_search_query`, to verify that the `_get_knowledge_search_query` method in the Agent class correctly interacts with the LLM using the appropriate prompts. Additionally, a VCR cassette is added to record the interactions with the OpenAI API for this test, ensuring consistent and reliable test results.
This removes any specific model from the "Setting up your LLM" guide,
but provides examples for the top-3 providers.
This section also conflated "model selection" with "model
configuration", where configuration is provider-specific, so I've
focused this first section on just model selection, deferring the config
to the "provider" section that follows.
Co-authored-by: Tony Kipkemboi <iamtonykipkemboi@gmail.com>
* feat: support to define a guardrail task no-code
* feat: add auto-discovery for Guardrail code execution mode
* feat: handle malformed or invalid response from CodeInterpreterTool
* feat: allow to set unsafe_mode from Guardrail task
* feat: renaming GuardrailTask to TaskGuardrail
* feat: ensure guardrail is callable while initializing Task
* feat: remove Docker availability check from TaskGuardrail
The CodeInterpreterTool already ensures compliance with this requirement.
* refactor: replace if/raise with assert
For this use case `assert` is more appropriate choice
* test: remove useless or duplicated test
* fix: attempt to fix type-checker
* feat: support to define a task guardrail using YAML config
* refactor: simplify TaskGuardrail to use LLM for validation, no code generation
* docs: update TaskGuardrail doc strings
* refactor: drop task paramenter from TaskGuardrail
This parameter was used to get the model from the `task.agent` which is a quite bit redudant since we could propagate the llm directly
* Fix issue #2402: Handle missing templates gracefully
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix import sorting in test files
Co-Authored-By: Joe Moura <joao@crewai.com>
* Bluit in top of devin-ai integration
* Fixed test cases
* Fixed test cases
* fixed linting issue
* Added docs
---------
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Joe Moura <joao@crewai.com>
* Enhance knowledge management in CrewAI
- Added `KnowledgeConfig` class to configure knowledge retrieval parameters such as `limit` and `score_threshold`.
- Updated `Agent` and `Crew` classes to utilize the new knowledge configuration for querying knowledge sources.
- Enhanced documentation to clarify the addition of knowledge sources at both agent and crew levels.
- Introduced new tips in documentation to guide users on knowledge source management and configuration.
* Refactor knowledge configuration parameters in CrewAI
- Renamed `limit` to `results_limit` in `KnowledgeConfig`, `query_knowledge`, and `query` methods for consistency and clarity.
- Updated related documentation to reflect the new parameter name, ensuring users understand the configuration options for knowledge retrieval.
* Refactor agent tests to utilize mock knowledge storage
- Updated test cases in `agent_test.py` to use `KnowledgeStorage` for mocking knowledge sources, enhancing test reliability and clarity.
- Renamed `limit` to `results_limit` in `KnowledgeConfig` for consistency with recent changes.
- Ensured that knowledge queries are properly mocked to return expected results during tests.
* Add VCR support for agent tests with query limits and score thresholds
- Introduced `@pytest.mark.vcr` decorator in `agent_test.py` for tests involving knowledge sources, ensuring consistent recording of HTTP interactions.
- Added new YAML cassette files for `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold` and `test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default`, capturing the expected API responses for these tests.
- Enhanced test reliability by utilizing VCR to manage external API calls during testing.
* Update documentation to format parameter names in code style
- Changed the formatting of `results_limit` and `score_threshold` in the documentation to use code style for better clarity and emphasis.
- Ensured consistency in documentation presentation to enhance user understanding of configuration options.
* Enhance KnowledgeConfig with field descriptions
- Updated `results_limit` and `score_threshold` in `KnowledgeConfig` to use Pydantic's `Field` for improved documentation and clarity.
- Added descriptions to both parameters to provide better context for their usage in knowledge retrieval configuration.
* docstrings added
* Fix#2551: Add Huggingface to provider list in CLI
Co-Authored-By: Joe Moura <joao@crewai.com>
* Update Huggingface API key name to HF_TOKEN and remove base URL prompt
Co-Authored-By: Joe Moura <joao@crewai.com>
* Update Huggingface API key name to HF_TOKEN in documentation
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix import sorting in test_constants.py
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix import order in test_constants.py
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix import formatting in test_constants.py
Co-Authored-By: Joe Moura <joao@crewai.com>
* Skip failing tests in Python 3.11 due to VCR cassette issues
Co-Authored-By: Joe Moura <joao@crewai.com>
* Fix import order in knowledge_test.py
Co-Authored-By: Joe Moura <joao@crewai.com>
* Revert skip decorators to check if tests are flaky
Co-Authored-By: Joe Moura <joao@crewai.com>
* Restore skip decorators for tests with VCR cassette issues in Python 3.11
Co-Authored-By: Joe Moura <joao@crewai.com>
* revert skip pytest decorators
* Remove import sys and skip decorators from test files
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: Lucas Gomide <lucaslg200@gmail.com>
* feat: support defining any memory in an isolated way
This change makes it easier to use a specific memory type without unintentionally enabling all others.
Previously, setting memory=True would implicitly configure all available memories (like LTM and STM), which might not be ideal in all cases. For example, when building a chatbot that only needs an external memory, users were forced to also configure LTM and STM — which rely on default OpenAPI embeddings — even if they weren’t needed.
With this update, users can now define a single memory in isolation, making the configuration process simpler and more flexible.
* feat: add tests to ensure we are able to use contextual memory by set individual memories
* docs: enhance memory documentation
* feat: warn when long-term memory is defined but entity memory is not
* KISS: Refactor LiteAgent integration in flows to use Agents instead. Update documentation and examples to reflect changes in class usage, including async support and structured output handling. Enhance tests for Agent functionality and ensure compatibility with new features.
* lint fix
* dropped for clarity
* fix: surfacing properly supported types by Mem0Storage
* feat: prepare Mem0Storage to accept config paramenter
We're planning to remove `memory_config` soon. This commit kindly prepare this storage to accept the config provided directly
* feat: add external memory
* fix: cleanup Mem0 warning while adding messages to the memory
* feat: support set the current crew in memory
This can be useful when a memory is initialized before the crew, but the crew might still be a very relevant attribute
* fix: allow to reset only an external_memory from crew
* test: add external memory test
* test: ensure the config takes precedence over memory_config when setting mem0
* fix: support to provide a custom storage to External Memory
* docs: add docs about external memory
* chore: add warning messages about the deprecation of UserMemory
* fix: fix typing check
---------
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
* WIP
* WIP
* wip
* wip
* WIP
* More WIP
* Its working but needs a massive clean up
* output type works now
* Usage metrics fixed
* more testing
* WIP
* cleaning up
* Update logger
* 99% done. Need to make docs match new example
* cleanup
* drop hard coded examples
* docs
* Clean up
* Fix errors
* Trying to fix CI issues
* more type checker fixes
* More type checking fixes
* Update LiteAgent documentation for clarity and consistency; replace WebsiteSearchTool with SerperDevTool, and improve formatting in examples.
* fix fingerprinting issues
* fix type-checker
* Fix type-checker issue by adding type ignore comment for cache read in ToolUsage class
* Add optional agent parameter to CrewAgentParser and enhance action handling logic
* Remove unused parameters from ToolUsage instantiation in tests and clean up debug print statement in CrewAgentParser.
* Remove deprecated test files and examples for LiteAgent; add comprehensive tests for LiteAgent functionality, including tool usage and structured output handling.
* Remove unused variable 'result' from ToolUsage class to clean up code.
* Add initialization for 'result' variable in ToolUsage class to resolve type-checker warnings
* Refactor agent_utils.py by removing unused event imports and adding missing commas in function definitions. Update test_events.py to reflect changes in expected event counts and adjust assertions accordingly. Modify test_tools_emits_error_events.yaml to include new headers and update response content for consistency with recent API changes.
* Enhance tests in crew_test.py by verifying cache behavior in test_tools_with_custom_caching and ensuring proper agent initialization with added commas in test_crew_kickoff_for_each_works_with_manager_agent_copy.
* Update agent tests to reflect changes in expected call counts and improve response formatting in YAML cassette. Adjusted mock call count from 2 to 3 and refined interaction formats for clarity and consistency.
* Refactor agent tests to update model versions and improve response formatting in YAML cassettes. Changed model references from 'o1-preview' to 'o3-mini' and adjusted interaction formats for consistency. Enhanced error handling in context length tests and refined mock setups for better clarity.
* Update tool usage logging to ensure tool arguments are consistently formatted as strings. Adjust agent test cases to reflect changes in maximum iterations and expected outputs, enhancing clarity in assertions. Update YAML cassettes to align with new response formats and improve overall consistency across tests.
* Update YAML cassette for LLM tests to reflect changes in response structure and model version. Adjusted request and response headers, including updated content length and user agent. Enhanced token limits and request counts for improved testing accuracy.
* Update tool usage logging to store tool arguments as native types instead of strings, enhancing data integrity and usability.
* Refactor agent tests by removing outdated test cases and updating YAML cassettes to reflect changes in tool usage and response formats. Adjusted request and response headers, including user agent and content length, for improved accuracy in testing. Enhanced interaction formats for consistency across tests.
* Add Excalidraw diagram file for visual representation of input-output flow
Created a new Excalidraw file that includes a diagram illustrating the input box, database, and output box with connecting arrows. This visual aid enhances understanding of the data flow within the application.
* Remove redundant error handling for action and final answer in CrewAgentParser. Update tests to reflect this change by deleting the corresponding test case.
---------
Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>
Co-authored-by: Lorenze Jay <lorenzejaytech@gmail.com>
- Renamed `CrewEvent` to `BaseEvent` across the codebase for consistency
- Created a `CrewBaseEvent` that automatically identifies fingerprints for DRY
- Added a new `to_json()` method for serializing events
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>
