run-llama / llama_index

LlamaIndex is a data framework for your LLM applications
https://docs.llamaindex.ai
MIT License
36.74k stars 5.27k forks source link

Feature/keywordsai llm #16860

Open jordanparker6 opened 1 week ago

jordanparker6 commented 1 week ago

Description

Due to some of the model validation of the LLMs, LLM proxy's that support an OpenAI like API like KeywordsAI required hacky solutions to override the error message when wrapped in OpenAI LLMs.

Currently in discussions with the founders of KeywordsAI to get a review of this so they are happy with the API.

Fixes # (issue)

This provides a KeywordsAI LLM provider that dynamically fetches the model configurations and allows for model params.

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

Type of Change

Please delete options that are not relevant.

How Has This Been Tested?

Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.

Suggested Checklist:

jordanparker6 commented 1 week ago

@logan-markewich just a heads up.

Looking to get a review on this by the founders of keywords to ensure they are happy with the API.

https://www.keywordsai.co/

logan-markewich commented 3 days ago

@jordanparker6 is this good to merge? (let me know if so, it seeeeeems ok?)

jordanparker6 commented 3 days ago

@logan-markewich let me quickly ping the keywords guys. There is an opportunity to add a better dev-x here for some of their features (e.g. adding a Customer ID / Thread ID to the LLM logs for observability in their UI). Shouldn't be a big add, just moving the params up to the model params rather than into the metadata param.