Hi!
I have a use case where I need to search for information in the knowledge base (supabase) and based on what was found, I want to retrieve the metadata keys from the found documents
Is there a way to vector store tool settings to return the metadata to the ai agent directly along with embeddings?
The supabase tool returns the metadata, but I don’t think it is inserted into the AI agent prompt
Hey @NAndriievskyi
The best RAG solution I’ve seen is from Cole Medin, on YouTube:
On the third video I think he uses a method for referencing the sources.
His workflows are available on his GitHub.
In every video he links everything in the description.
Let me know if that helps!
If my reply answers your question, please remember to mark it as a solution.
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.
