You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is this your first time submitting a feature request?
I have searched the existing issues, and I could not find an existing issue for this feature
I am requesting a straightforward extension of existing functionality
Describe the feature
Right now, when the OpenAI model knows the answer to a question, it's unclear when RAG is or is not working on the RAG side of teh application, since the RAG side also simply outputs the OpenAI model's answer. It would be immediately understood when RAG wasn't working (e.g. fetch from Pinecone not working) if the user were able to see what context was being retrieved from Pinecone.
Describe alternatives you've considered
n/a
Who will this benefit?
End users
Are you interested in contributing this feature?
Sure!
Anything else?
No response
The text was updated successfully, but these errors were encountered:
We have a "low score" state when it's not working. If there's some type of status messaging you're thinking about, let me know. We can add more states.
Is this your first time submitting a feature request?
Describe the feature
Right now, when the OpenAI model knows the answer to a question, it's unclear when RAG is or is not working on the RAG side of teh application, since the RAG side also simply outputs the OpenAI model's answer. It would be immediately understood when RAG wasn't working (e.g. fetch from Pinecone not working) if the user were able to see what context was being retrieved from Pinecone.
Describe alternatives you've considered
n/a
Who will this benefit?
End users
Are you interested in contributing this feature?
Sure!
Anything else?
No response
The text was updated successfully, but these errors were encountered: