Commit Graph

116 Commits

Author SHA1 Message Date
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