I have searched the existing issues and discussions.
Problem Description
I have already made the settings in the document section of the openwebui settings options. I want to implement RAG now, but I don't want to perform real-time document segmentation every time I implement RAG. If multiple documents are uploaded to the knowledge base in the workspace to obtain the knowledge base, and the custom model and knowledge base are bound in the model options. At this point, when I am asking a question, should the previously uploaded document be further cut or directly accessed from the knowledge base?
Desired Solution you'd like
I expect all files stored in the knowledge base to be split only once, avoiding splitting the document every time when implementing RAG and speeding up response times.
Alternatives Considered
No response
Additional Context
No response
Originally created by @xihaofei on GitHub (Apr 18, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13011
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Problem Description
I have already made the settings in the document section of the openwebui settings options. I want to implement RAG now, but I don't want to perform real-time document segmentation every time I implement RAG. If multiple documents are uploaded to the knowledge base in the workspace to obtain the knowledge base, and the custom model and knowledge base are bound in the model options. At this point, when I am asking a question, should the previously uploaded document be further cut or directly accessed from the knowledge base?
### Desired Solution you'd like
I expect all files stored in the knowledge base to be split only once, avoiding splitting the document every time when implementing RAG and speeding up response times.
### Alternatives Considered
_No response_
### Additional Context
_No response_
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @xihaofei on GitHub (Apr 18, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13011
Check Existing Issues
Problem Description
I have already made the settings in the document section of the openwebui settings options. I want to implement RAG now, but I don't want to perform real-time document segmentation every time I implement RAG. If multiple documents are uploaded to the knowledge base in the workspace to obtain the knowledge base, and the custom model and knowledge base are bound in the model options. At this point, when I am asking a question, should the previously uploaded document be further cut or directly accessed from the knowledge base?
Desired Solution you'd like
I expect all files stored in the knowledge base to be split only once, avoiding splitting the document every time when implementing RAG and speeding up response times.
Alternatives Considered
No response
Additional Context
No response