opensanctions / opensanctions/poliloom

Track Meilisearch embedding batch size configurability

Open
#125 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

loom
Dominant language
Python
Stars
22
Forks
2
PR merge metrics
No merged PRs in 30d

Description

Context

When using Meilisearch's vector search with embedders, the embedding batch size is currently fixed at 10 documents per request. For our use case with relatively small documents, this results in many unnecessary embedding API requests.

Upstream Issue

The Meilisearch team has acknowledged the limitation and is exploring solutions. There's an architectural ceiling of 100 documents per batch due to internal processing constraints.

Action

Monitor the upstream issue and increase our embedding batch size when it becomes configurable in Meilisearch.

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 the linked Meilisearch issue 5966 to determine whether embedding batch-size configuration is available. Once upstream support exists, update this integration to increase the batch size, staying within the stated 100-document ceiling; completion requires the configured value to reduce requests without exceeding that limit.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
search
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.