simonw / simonw/llm

[Question] Is it possible to use cutom embedding model?

Open
#762 0 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

I have configured extra-openai-models.yaml as,

- model_id: azure-text-embedding-3-large
  model_name: azure-text-embedding-3-large
  api_base: "http://10.16.136.20:4100"

but when I try to set it as default embed model I get error as,

llm embed-models default azure-text-embedding-3-large
Error: Unknown embedding model: azure-text-embedding-3-large
> llm embed-models                                     
OpenAIEmbeddingModel: text-embedding-ada-002 (aliases: ada, ada-002)
OpenAIEmbeddingModel: text-embedding-3-small (aliases: 3-small)
OpenAIEmbeddingModel: text-embedding-3-large (aliases: 3-large)
OpenAIEmbeddingModel: text-embedding-3-small-512 (aliases: 3-small-512)
OpenAIEmbeddingModel: text-embedding-3-large-256 (aliases: 3-large-256)
OpenAIEmbeddingModel: text-embedding-3-large-1024 (aliases: 3-large-1024)

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 by reviewing extra-openai-models.yaml and the llm embed-models command output to understand how embedding models are discovered. Trace why azure-text-embedding-3-large is not recognized, then determine the scope needed for custom embedding-model support. Done means the configured model can be recognized and selected as the default embedding model.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, cli
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.