quickwit-oss / quickwit-oss/quickwit
Multilang tokenizer is slow on long text in JPN/CMN/KOR
Open
Nobody has claimed this yet.
bug
- Dominant language
- Rust
- Stars
- 11.7k
- Forks
- 597
- Avg merge
- 2d 22h
- Merged PRs (30d)
- 37
Description
For short/medium texts, throughput is around a few MB/s, but for long Wikipedia articles, it goes under 1MB/s.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files, tests, or entry points. Start by reproducing throughput on long Wikipedia text in Japanese, Chinese, and Korean, then trace the multilang tokenizer path. Done means the long-text throughput bottleneck is addressed and the reported performance is verified without regressing short or medium texts.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- performance, search
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100