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
I might be wrong about this, but if I understand correctly, the code passes your question, as a user conversing with a "chat bot AI", straight to the embedding db search.
Is that understanding correct?
I suspect this format will generally be sub-optimal as a search phrase, even if it is good as a query to the LLM.
Would it make sense to have the LLM instructed to rephrase the user query in a manner more optimised for the embedding search?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I might be wrong about this, but if I understand correctly, the code passes your question, as a user conversing with a "chat bot AI", straight to the embedding db search.
Is that understanding correct?
I suspect this format will generally be sub-optimal as a search phrase, even if it is good as a query to the LLM.
Would it make sense to have the LLM instructed to rephrase the user query in a manner more optimised for the embedding search?
Beta Was this translation helpful? Give feedback.
All reactions