simonw / simonw/llm

Extract OpenAI support out of core and into a plugin

Open
#335 7 comments 5 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement refactor
Dominant language
Python
Stars
12.5k
Forks
998
Avg merge
3d 13h
Merged PRs (30d)
10

Description

The OpenAI plugin is currently included in LLM core:

https://github.com/simonw/llm/blob/0.12/llm/default_plugins/openai_models.py

This means it's not possible to ship an improvement to OpenAI support without releasing a new version of LLM.

With the recent changes from OpenAI DevDay I'm finding a need to iterate on OpenAI much more rapidly. Extracting it into a separate llm-openai plugin would make this a lot easier.

It would also mean I can add dependencies like tiktoken in the future without them becoming dependencies of core - they'll only be pulled in if you install llm-openai itself.

Contributor guide

Open the contributing guide

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 with llm/default_plugins/openai_models.py and inspect how the core package currently includes the OpenAI plugin. Define the extraction boundary for a separate llm-openai plugin, including its optional dependencies, then verify that OpenAI support is no longer shipped in core while remaining available through the plugin.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
cli
Issue type
Refactor
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.