Right now, the RAG process is really unintuitive. It's spread out across multiple settings and chat pages and gets really confusing unless you really know what you're doing. And most RAG operations are lost the minute the chat is exited. Like if I add links into OpenWebUI using the pound sign syntax, it doesn't retain any of that as knowledge.
Describe the solution you'd like
Streamline the RAG options in Settings and in Chat/Knowledge. Allow users to copy/paste links into the Knowledge section to have them trained as RAG material (similar to how Continue AI trains on code documentation).
Describe alternatives you've considered
I am unaware of any alternatives in existence.
Originally created by @dabockster on GitHub (Feb 7, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9623
# Feature Request
**Is your feature request related to a problem? Please describe.**
https://docs.openwebui.com/features/rag/
Right now, the RAG process is really unintuitive. It's spread out across multiple settings and chat pages and gets really confusing unless you really know what you're doing. And most RAG operations are lost the minute the chat is exited. Like if I add links into OpenWebUI using the pound sign syntax, it doesn't retain any of that as knowledge.
**Describe the solution you'd like**
Streamline the RAG options in Settings and in Chat/Knowledge. Allow users to copy/paste links into the Knowledge section to have them trained as RAG material (similar to how Continue AI trains on code documentation).
**Describe alternatives you've considered**
I am unaware of any alternatives in existence.
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 @dabockster on GitHub (Feb 7, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9623
Feature Request
Is your feature request related to a problem? Please describe.
https://docs.openwebui.com/features/rag/
Right now, the RAG process is really unintuitive. It's spread out across multiple settings and chat pages and gets really confusing unless you really know what you're doing. And most RAG operations are lost the minute the chat is exited. Like if I add links into OpenWebUI using the pound sign syntax, it doesn't retain any of that as knowledge.
Describe the solution you'd like
Streamline the RAG options in Settings and in Chat/Knowledge. Allow users to copy/paste links into the Knowledge section to have them trained as RAG material (similar to how Continue AI trains on code documentation).
Describe alternatives you've considered
I am unaware of any alternatives in existence.