langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 12:05:30 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

[PR #5928] Feat: Workflow Knowledge Retrieval Node Support: Dynamic Dataset ID List Configuration and Document Metadata Filtering #25109

New Issue
Closed
opened 2026-02-21 20:24:18 -05:00 by yindo · 0 comments
yindo commented 2026-02-21 20:24:18 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langgenius/dify/pull/5928

State: closed
Merged: No

Checklist:

Important

Please review the checklist below before submitting your pull request.

  • Please open an issue before creating a PR or link to an existing issue
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

Description

Feat

Workflow Knowledge Retrieval Node Support:

  1. Dynamic Dataset ID List Configuration
  2. Document Metadata Filtering (Currently only supports qdrant vector database)

Testing Instructions

About workflow dynamic datasetIdList configuration instructions

  1. In the workflow, obtain the dataset id list that needs to be dynamically passed through the code node or tool node
  2. In the knowledge retrieval node, select the dynamic knowledge base drop-down box and specify the parameters of the corresponding datasetid list.
  3. This knowledge retrieval node will use the specified knowledge base and the dynamically passed knowledge base to perform recall at the same time.

About workflow document metadata filter instructions

  1. Set the metadata of the document in the knowledge base document, and this metadata will be stored in the payload of the vector database.
  2. Configure the corresponding metadata key, corresponding conditions and corresponding parameters in the knowledge retrieval node of the workflow.
  3. When executing recall, the metadata conditions will be added to the original basis to recall the knowledge base data (this function currently only supports qdrant).
image

image

**Original Pull Request:** https://github.com/langgenius/dify/pull/5928 **State:** closed **Merged:** No --- # Checklist: > [!IMPORTANT] > Please review the checklist below before submitting your pull request. - [x] Please open an issue before creating a PR or link to an existing issue - [x] I have performed a self-review of my own code - [x] I have commented my code, particularly in hard-to-understand areas - [x] I ran `dev/reformat`(backend) and `cd web && npx lint-staged`(frontend) to appease the lint gods # Description ## Feat Workflow Knowledge Retrieval Node Support: 1. Dynamic Dataset ID List Configuration 2. Document Metadata Filtering (Currently only supports qdrant vector database) # Testing Instructions ## About workflow dynamic datasetIdList configuration instructions 1. In the workflow, obtain the dataset id list that needs to be dynamically passed through the code node or tool node 2. In the knowledge retrieval node, select the dynamic knowledge base drop-down box and specify the parameters of the corresponding datasetid list. 4. This knowledge retrieval node will use the specified knowledge base and the dynamically passed knowledge base to perform recall at the same time. ## About workflow document metadata filter instructions 1. Set the metadata of the document in the knowledge base document, and this metadata will be stored in the payload of the vector database. 2. Configure the corresponding metadata key, corresponding conditions and corresponding parameters in the knowledge retrieval node of the workflow. 4. When executing recall, the metadata conditions will be added to the original basis to recall the knowledge base data (this function currently only supports qdrant). <img width="1051" alt="image" src="https://github.com/langgenius/dify/assets/31267466/50b23421-8069-4c90-b275-f5504602d02f"> ![image](https://github.com/langgenius/dify/assets/31267466/b4a43a12-2059-4548-a23d-5e3e21e4e081)
yindo added the pull-request label 2026-02-21 20:24:18 -05:00
yindo closed this issue 2026-02-21 20:24:18 -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#25109
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?