* 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>
* 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>
* 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
* 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
* 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
* 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
* 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>
* 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
* 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
* 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
* 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
* Sync with deep copy working now
* async working!!
* Clean up code for review
* Fix naming
---------
Co-authored-by: João Moura <joaomdmoura@gmail.com>
* 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
* 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
