Yichuan Wang
af5cff01db
Revert "[Multi-vector]Add timing instrumentation and multi-dataset support fo…"
...
This reverts commit 00770aebbb
2025-12-03 01:09:08 -08:00
Yichuan Wang and Claude
00770aebbb
[Multi-vector]Add timing instrumentation and multi-dataset support for multi-vector… ( #161 )
...
* Add timing instrumentation and multi-dataset support for multi-vector retrieval
- Add timing measurements for search operations (load and core time)
- Increase embedding batch size from 1 to 32 for better performance
- Add explicit memory cleanup with del all_embeddings
- Support loading and merging multiple datasets with different splits
- Add CLI arguments for search method selection (ann/exact/exact-all)
- Auto-detect image field names across different dataset structures
- Print candidate doc counts for performance monitoring
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
* update vidore
* reproduce docvqa results
* reproduce docvqa results and add debug file
---------
Co-authored-by: Claude <noreply@anthropic.com >
2025-12-03 00:55:42 -08:00
Yichuan Wang
edde0cdeb2
[Feat] ColQwen intergration ( #111 )
...
* add colqwen stuff
* add colqwen stuff and pass ruff
* remove ipynb
2025-09-23 17:51:29 -07:00
Yichuan Wang
3b8dc6368e
Ast fork ( #92 )
2025-09-08 18:43:31 -07:00
Yichuan Wang
d41e467df9
[CLI] More robust leann list and leann build ( #84 )
...
* chore(submodule): bump faiss to latest storage-efficient build
* [chore] add slack to share use case
* [cli] better gitignore / better leann list
* [cli] fix # 81
2025-09-01 18:36:27 -07:00
Yichuan Wang and yichuan-w
dde2221513
[EXP] Update the benchmark code ( #71 )
...
* chore(hnsw): reorder imports to satisfy ruff I001
* chore: sync changes; fix Ruff import order; update examples, benchmarks, and dependencies
- Fix import order in packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py (Ruff I001)
- Update benchmarks/run_evaluation.py
- Update apps/base_rag_example.py and leann-core API usage
- Add benchmarks/data/README.md
- Update uv.lock
- Misc cleanup
- Note: added paru-bin as an embedded git repo; consider making it a submodule (git rm --cached paru-bin) if unintended
* chore: remove unintended embedded repo paru-bin and ignore it
Fix CI: avoid missing .gitmodules entry by removing gitlink and adding to .gitignore.
* ci: retrigger after removing unintended gitlink (paru-bin)
* feat(benchmarks): add --batch-size option and plumb through to HNSW search (default 0)
* feat(hnsw): add batch_size to LeannSearcher.search and LeannChat.ask; forward only for HNSW backend
* chore(logging): surface recompute and batching params; enable INFO logging in benchmark
* feat(embeddings): add optional manual tokenization path (HF tokenizer+model) with mean pooling; default remains SentenceTransformer.encode
* fix micro bench and fix pre commit
* update readme
---------
Co-authored-by: yichuan-w <yichuan-w@users.noreply.github.com >
2025-08-20 17:31:46 -07:00
Yichuan Wang
2dcfca19ff
style: apply ruff format ( #56 )
2025-08-15 17:48:33 -07:00
Yichuan Wang
bee2167ee3
docs: update READMEs (MCP docs + conclusion polish)
...
- Polish conclusion in packages/leann-mcp/README.md
- Sync root README wording and links
2025-08-15 17:21:23 -07:00
Yichuan Wang
eab13434ef
feat: support multiple input formats for --docs argument ( #39 )
2025-08-12 10:30:31 -07:00
Yichuan Wang