qdrant / qdrant/fastembed

Bm25: Expanding keywords & custom vector space

Open
#351 1 comment 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 happened?

Is it possible to expand keywords via the current BM25 impelemtation?
Or even better, build the bm25 vector space on the documents?

Very often the corpus of documents is pre-determined and largely static, so the custom vector space & keyword extension (maybe via dense vectors?) would potentially improve BM25 performance

What Python version are you on? e.g. python --version

Python3.11 with pyenv

Version

0.2.7 (Latest)

What os are you seeing the problem on?

No response

Relevant stack traces and/or logs

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

Start by locating the current BM25 implementation and reviewing how it builds its keyword space from documents. The request raises several possible directions—keyword expansion, a corpus-derived vector space, or dense vectors—so clarify the intended scope before implementation. Done should include a defined approach and tests demonstrating improved or extended BM25 behavior.

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
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.