simonw / simonw/llm

Add metadata field to collections table in embeddings schema

Open
#342 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
12.5k
Forks
991
Avg merge
3d 13h
Merged PRs (30d)
10

Description

if the collections table were to have a metadata TEXT field, same as embeddings, this would allow for tagging of useful metadata at the collection level (e.g. "description": "my pelicans database", "version": "1.0.0", ...). I think this would also effectively give the same level of expressivity as chromadb (I'd like to swap out my slow chromadb with a simple light sqlite database).

Happy to try a PR for this (including migrations) if it's in scope

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

Locate the embeddings schema and the existing migration mechanism, then compare the collections table with the embeddings table's metadata field. Check how collection records are created and read, and verify that a migration adds collection-level metadata without disrupting existing databases. Done means collections can store and retrieve metadata such as description and version.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, sqlite
Domain
databases
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.