mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-01-19 11:45:10 +08:00
### What problem does this PR solve? when a kb contains many documents, say 50000, and the retrieval is only made against some kb without specifying any doc ids, the query for all docs from the db is not necessary, and can be omitted to improve performance. ### Type of change - [x] Performance Improvement