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.

Sign up for GitHub

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

Jump to bottom

WIP: Auto mode rework #48

Closed
wants to merge 15 commits into from
Closed

WIP: Auto mode rework #48

wants to merge 15 commits into from

Commits on Sep 16, 2024

  1. WIP: Auto mode rework

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    d11139e View commit details
    Browse the repository at this point in the history

  2. Avoid using dot imports

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    f1af862 View commit details
    Browse the repository at this point in the history

  3. Get rid of redundant transformers library 

    It's never used except in a function which was never used either (in the old code)
    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    0d9a021 View commit details
    Browse the repository at this point in the history

  4. Add litellm and llama-cpp (with openai style response now)

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    826ea9a View commit details
    Browse the repository at this point in the history

  5. Add openapi to longchain providers

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    2e5d457 View commit details
    Browse the repository at this point in the history

  6. Fix some openai issues introduces in litellm commit

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    db24771 View commit details
    Browse the repository at this point in the history

  7. Add llm.chat_format environment

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    43344bb View commit details
    Browse the repository at this point in the history

  8. TEST: Add memory

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    93b65a9 View commit details
    Browse the repository at this point in the history

  9. Disable streaming for llm-cpp as it's not supported with auto tools c… 

    …hoice
    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    2968667 View commit details
    Browse the repository at this point in the history

  10. Drop instructor in favour of using our own OpenAISchema model 

    This was the only thing we used from it anyway
    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    3d176c6 View commit details
    Browse the repository at this point in the history

  11. Add env to change tool choice to support llm-cpp streaming

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    1a0eb41 View commit details
    Browse the repository at this point in the history

  12. Add deps-cuda to build llama-cpp with cuda support

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    04c513b View commit details
    Browse the repository at this point in the history

  13. Modify OpenAISchema to reasamble old format

    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    6dc3fc5 View commit details
    Browse the repository at this point in the history

  14. Disable chunking (temporary), fix llama-cpp tools 

    Might break openai? Can't test it right now, but I hope I can make both
happy with a unified sollution instead of patching everything for each
model
    @nitanmarcel
    nitanmarcel committed Sep 16, 2024
    Configuration menu
    Copy the full SHA
    7dbb064 View commit details
    Browse the repository at this point in the history

Commits on Sep 17, 2024

  1. Fix cuda deps installation

    @nitanmarcel
    nitanmarcel authored Sep 17, 2024
    Configuration menu
    Copy the full SHA
    9a91635 View commit details
    Browse the repository at this point in the history