open-webui/backend
Classic298 aee7c47277
feat: Milvus hybrid search without a second text-only copy of every collection (#31660)
Native hybrid search on Milvus kept a second, text-only collection beside every Milvus collection and searched both. Each Milvus collection now holds its vectors, its text and its BM25 keyword index together, and results rank exactly as before, with the BM25 weight setting working the same way it does on pgvector. Existing data moves on the first start with ENABLE_DB_MIGRATIONS on: startup waits while every collection is copied once (vectors included, nothing is re-embedded) and the originals are only dropped after every copy succeeded, so a failed run changes nothing and is retried on the next start. The copy needs free disk space for a second copy of the data until it finishes, and on one 16-thread machine with Milvus's official docker compose setup it ran at 11 to 22 MB/s, so 200 GB takes about 2.5 to 5 hours depending on chunk size. Milvus servers older than 2.5 are detected and keep the existing hybrid search.
2026-10-01 03:07:50 +04:00
..
data refac: mv backend files to /open_webui dir 2024-09-04 16:54:48 +02:00
open_webui feat: Milvus hybrid search without a second text-only copy of every collection (#31660) 2026-10-01 03:07:50 +04:00
.dockerignore fix: litellm config issue 2024-02-24 22:35:11 -08:00
.gitignore refac 2024-09-06 04:59:20 +02:00
dev.sh perf: allow disabling websocket per-message-deflate (#28613) 2026-08-24 18:46:07 -04:00
requirements-slim.txt chore: bump pycrdt to 0.14.8 (#31636) 2026-09-30 19:00:23 +04:00
requirements.txt chore: bump pycrdt to 0.14.8 (#31636) 2026-09-30 19:00:23 +04:00
start.sh refac 2026-09-06 16:48:30 -04:00
start_windows.bat chore: drop nltk, unused at the pinned versions (#29725) 2026-09-06 16:39:05 -04:00