langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 20:15:31 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

[PR #31658] feat(qdrant): implement full-text search with multi-keyword support #33341

New Issue
Closed
opened 2026-02-21 20:53:06 -05:00 by yindo · 0 comments
yindo commented 2026-02-21 20:53:06 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langgenius/dify/pull/31658

State: closed
Merged: Yes

Resolve #31657

Summary

When using Qdrant's search_by_full_text method with multiple keywords (e.g., "apple banana"), the search only returns documents containing all keywords instead of documents containing any keyword.

For example:

Searching "apple" returns documents A (with "apple")
Searching "banana" returns documents B (with "banana")
Searching "apple banana" only returns documents containing both keywords, missing A and B

This happens because Qdrant's MatchText uses AND logic by default, unlike Elasticsearch/OpenSearch which use OR logic for multi-word match queries.

Root Cause:

Qdrant's MatchText with multiple words uses AND logic (all words must match)

The original docstring incorrectly stated "BM25" - Qdrant < 1.10 doesn't support native BM25

Current Qdrant image is langgenius/qdrant:v1.8.3

Solution:

Search each keyword separately and merge results with deduplication

This aligns with the behavior of other vector databases (ES/OpenSearch)

Screenshots

uv run --project api pytest api/tests/integration_tests/vdb/qdrant/test_qdrant.py

Before After
Test fail: Searching "apple banana" returns only docs with both keywords Test success: Searching "apple banana" returns docs with any keyword (union of results)

Checklist

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran make lint and make type-check (backend) and cd web && npx lint-staged (frontend) to appease the lint gods
**Original Pull Request:** https://github.com/langgenius/dify/pull/31658 **State:** closed **Merged:** Yes --- Resolve #31657 ## Summary When using Qdrant's search_by_full_text method with multiple keywords (e.g., "apple banana"), the search only returns documents containing all keywords instead of documents containing any keyword. For example: Searching "apple" returns documents A (with "apple") Searching "banana" returns documents B (with "banana") Searching "apple banana" only returns documents containing both keywords, missing A and B This happens because Qdrant's MatchText uses AND logic by default, unlike Elasticsearch/OpenSearch which use OR logic for multi-word match queries. #### Root Cause: Qdrant's MatchText with multiple words uses AND logic (all words must match) The original docstring incorrectly stated "BM25" - Qdrant < 1.10 doesn't support native BM25 Current Qdrant image is `langgenius/qdrant:v1.8.3` ### Solution: Search each keyword separately and merge results with deduplication This aligns with the behavior of other vector databases (ES/OpenSearch) ## Screenshots `uv run --project api pytest api/tests/integration_tests/vdb/qdrant/test_qdrant.py ` | Before | After | |--------|-------| | Test fail: Searching "apple banana" returns only docs with both keywords | Test success: Searching "apple banana" returns docs with any keyword (union of results) | ## Checklist - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs) - [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!) - [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change. - [x] I've updated the documentation accordingly. - [x] I ran `make lint` and `make type-check` (backend) and `cd web && npx lint-staged` (frontend) to appease the lint gods
yindo added the pull-request label 2026-02-21 20:53:06 -05:00
yindo closed this issue 2026-02-21 20:53:06 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#33341
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?