8 Commits

Author	SHA1	Message	Date
yichuan-w	07afe546ea	reproduce docvqa results	2025-11-14 10:22:42 +00:00
yichuan-w	ae3b8af3df	update vidore	2025-11-14 07:31:24 +00:00
yichuan-w	a9c014df9e	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>	2025-11-10 21:13:17 +00:00
yichuan-w	3766ad1fd2	robust multi-vector	2025-11-09 02:34:53 +00:00
yichuan-w	dc6c9f696e	update some search in copali	2025-11-08 08:53:03 +00:00
yichuan520030910320	01475c10a0	add img	2025-09-23 23:25:05 -07:00
yichuan520030910320	576beb13db	add doc about multimodal	2025-09-23 23:21:03 -07:00
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