Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Disable strong cache in integration tests #96

Open
wants to merge 85 commits into
base: main
Choose a base branch
from
Open

Conversation

ViStefan
Copy link
Collaborator

No description provided.

whimo and others added 30 commits July 22, 2024 16:48
* add conversion from crewai tool to MotleyTool

* add agent_name parameter to MotleyAgentParent

* add processing of the arguments for launching the crewai tools

* fix to_crewai_tool method

* add test for crewai_tools

* Simplify the code a bit

* Update dependencies & fix config param in output handler _run

* Updates

* fix tests

---------

Co-authored-by: User <[email protected]>
Co-authored-by: whimo <[email protected]>
* minor tweaks

* Add a tool to call image models like flux and stable diffusion, through replicate.com

* Fix directory name in example code snippet
* Supply prompt prefix as a list of messages

* Update deps & tests data

* Fix tests

* update tests data

---------

Co-authored-by: Ubuntu <[email protected]>
* Isolate extra requirements

* Refactor workflows to use `poetry run` for installing extra dependencies.
…Index integration & workaround for Pydantic v1 compatibility (#74)
* Support Replicate-hosted LLMs

* Add support for Together, Groq, and Ollama LLMs in Langchain and LlamaIndex integration.

* Replace `OllamaLLM` with `ChatOllama` in `langchain_ollama_llm` function.

* Fix import path for ChatOllama in langchain_ollama_llm function.

* LLM-related docs & refactoring
…, major refactor (#76)

* Unify output handlers and regular tools, improve exception management, major refactor

* update tests data

* Add AuxPrompts class for handling auxiliary error messages in MotleyCrew.

* Refactor output handling and documentation in MotleyCrew, enhancing support for direct returns and exception reflection in tools and agents.

* Update tests data

* Update quickstart docs

* bump version
* Create new Lunary queue if running in a separate thread

* Agent call_as_tool explicit input schema

* Proper async invocation for Langchain and LlamaIndex agents
…g_cache

# Conflicts:
#	.github/workflows/integration_test.yml
#	.github/workflows/integration_test_minimal.yml
#	examples/Advanced output handling.ipynb
#	examples/Blog with Images.ipynb
#	examples/Multi-step research agent.ipynb
#	examples/Streaming agent output.ipynb
#	examples/Validating agent output.ipynb
#	requirements-extra.txt
#	tests/run_integration_tests.py
@ViStefan ViStefan deployed to integration_test December 13, 2024 02:34 — with GitHub Actions Active
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants