Pinned issues
Issues
- 1
Index out of bounds errors in 0.2.0 and 0.2.1
#60 opened by hantusk - 6
[feature request] Implement BMX algorithm
#40 opened by logan-markewich - 3
ImportError: cannot import name 'Tokenizer' from 'bm25s.tokenization' (/usr/local/lib/python3.10/dist-packages/bm25s/tokenization.py)
#55 opened by hanxu49 - 0
Add tests for BM25.retrieve in different scenario (tokenized, ids/vocab tuple, object with ids and vocab attributes, ids, strings)
#52 opened by xhluca - 1
On-the-fly stemming
#31 opened by xhluca - 3
[Feature request] Document metadata and filtering
#35 opened by dl423 - 1
- 1
- 2
Other language than english for the stopwords list
#32 opened by bm777 - 3
Thread safe search
#37 opened by okhat - 2
- 0
🚨Before submitting an issue, read this 🚨
#27 opened by xhluca - 0
Can you query without a tokenization step?
#21 opened by snewcomer - 0
可以增量更新索引吗?
#22 opened by bojone - 0
how to dynamic add/delete documents
#19 opened by luoyangen - 3
- 0
Not Working for langchain Documents
#16 opened by pradhandebasish2046 - 14
Updating an index for batch indexing
#5 opened by fabiannagel - 1
- 3
Using with postgres?
#7 opened by Tejaswgupta - 0
Pre-computed TF-IDF
#9 opened by celsofranssa - 2
- 4