lm-sys / lm-sys/RouteLLM

Ability to Incorporate Open Source Embeddings for Router to Remove OpenAI dependency

Open
#62 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
5.5k
Forks
433
PR merge metrics
No merged PRs in 30d

Description

As the title suggests, I want to be able to utilize an open source embedding model from huggingface such that I don't require openAI or any other api driven embedding model for the actual routing done in mf routing. I'm able to dig into the source code in the routellm package and accomplish this by modifying the matrix_factorization.model.py file as well as controller.py and routers.py, but it would be great if this option was already available

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading routellm's matrix_factorization.model.py, controller.py, and routers.py, then trace how embeddings are selected and used for routing. Done means an open-source Hugging Face embedding model can be used for MF routing without requiring OpenAI or another API-based embedding provider.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
ai, backend
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.