Add LiteLLM router to FastAPI container #14
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Peter Muller <[email protected]>
|
I'll add a new commit to fix the failing tests. |
KyleLilly
reviewed
May 30, 2024
| @@ -30,6 +31,9 @@ | |||
| router.include_router(models.router, prefix="/v1", tags=["models"], dependencies=[Depends(security)]) | |||
| router.include_router(embeddings.router, prefix="/v1", tags=["embeddings"], dependencies=[Depends(security)]) | |||
| router.include_router(generation.router, prefix="/v1", tags=["generation"], dependencies=[Depends(security)]) | |||
| router.include_router( | |||
| litellm_passthrough.router, prefix="/v2/serve", tags=["litellm_passthrough"], dependencies=[Depends(security)] | |||
There was a problem hiding this comment.
I'm assuming this is /v2/serve because we're going to move the API GW stuff into /v2/ as well?
There was a problem hiding this comment.
Yes, that is correct. I'm also welcome to changing the name, but I wanted to avoid the situation of calling it "model" and having a url like the following when using it directly for the OpenAI list models call:
curl -X GET https://mydomain/v2/model/models
These changes address pul request feedback for adding comments for inter-file dependencies and updates to the README file. This also modifies the LiteLLM configuration to use the user-provided modelId if it exists, otherwise default back to the model name. This allows for users to use the same model and weights, but using two different containers.
estohlmann
reviewed
Jun 2, 2024
| @@ -30,6 +31,9 @@ | |||
| router.include_router(models.router, prefix="/v1", tags=["models"], dependencies=[Depends(security)]) | |||
There was a problem hiding this comment.
Are we going to be marking the v1 endpoints as depreciated?
There was a problem hiding this comment.
There's not going to be a lot of time between them being deprecated and us releasing the next revision, so I think for now, we can just leave as-is
estohlmann
approved these changes
Jun 2, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This set of changes adds a dependency on LiteLLM in our FastAPI container so that we may pass requests from the LISA Serve ALB directly to LiteLLM. This enables us to handle any form of OpenAI API spec implementation so long as LiteLLM also supports it.
Summary of changes:
Testing:
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.