Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

enh: confusing LLM feedback when no retrieval happened because of high RAG_RELEVANCE_THRESHOLD #3518

Open
Robinsane opened this issue Jun 29, 2024 · 0 comments

Comments

@Robinsane
Copy link

Is your feature request related to a problem? Please describe.
When no RAG context is used because all results were lower than the value in RAG_RELEVANCE_THRESHOLD, the user is made to think no file is provided (based on how the LLMs respond).

Describe the solution you'd like
I think it would be very nice to provide a hard coded context that explains the situation in these cases, so the LLM's response will be adjusted and relevant.
hard coded context example.:
"No context was added to this prompt. It's possible that a file was added correctly, but no text was relevant enough according to the setting RAG_RELEVANCE_THRESHOLD."

Additional context
openwebui_relevance_treshold_too_high

@tjbck tjbck changed the title confusing LLM feedback when no retrieval happened because of high RAG_RELEVANCE_THRESHOLD enh: confusing LLM feedback when no retrieval happened because of high RAG_RELEVANCE_THRESHOLD Jun 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant