lm-sys / lm-sys/FastChat

Fast chat as an OpenAI client

Open
#2,604 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

We have the OpenAI api server, which allows us to connect our fastchat to clients of the OpenAI api, such as langchain.

On the other hand, there are models which could be served by other applications, and one would still be able to access them via fastchat’s frontends.

Something like a model adapter, but with an OpenAI api client. The model adapter would be a worker which would give the heartbeat to fastchat controller, and talk to the model via normal api requests.

Does that make sense?

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

No files or tests are named. Start by reading the existing OpenAI API server, model adapter, worker, heartbeat, controller, and frontend entry points to understand their interfaces. Define the external model API contract and integration scope; done should include a worker that registers with the controller and serves FastChat frontends through normal API requests.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, api, backend
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.