qdrant / qdrant/fastembed

[Feature]: Support Chinese Tokenization for BM25 using Jieba

Open
#610 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.2k
Forks
248
Avg merge
4d 8h
Merged PRs (30d)
4

Description

What feature would you like to request?

Currently, fastembed supports BM25 sparse embeddings, but it lacks optimized support for Chinese text. Standard whitespace tokenization is ineffective for Chinese, as the language does not use spaces between words. This leads to poor retrieval performance when using fastembed's BM25 implementation for Chinese datasets.

Is there any additional information you would like to provide?

No response

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 fastembed’s BM25 implementation and the current standard whitespace tokenization. Review how Jieba can be integrated for Chinese text, and verify that BM25 supports Chinese datasets with Jieba-based tokenization and improved retrieval behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
search
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.