Find answers from the community

Updated 3 months ago

I have 10 transcripts in an index. Each

I have 10 transcripts in an index. Each one has a file with <transcript id>.txt as the name, and the id is also in the file along with the file name.

When I say "Summarize file <file id>.txt" or "Summarize the transcript with id: <id>" it always gets nodes from a different file. Is there a way to get the retrieval to return the correct file summary or do I need to create indexes for each file if I want to do extraction from each?

5 comments

LLogan M

Yea theres a few ways

index per document (would need some way to route queries per use-case/document, like a router, agent, or something else)
get the llm to write metadata filters on the fly to filter

OOrion Pax

Does the metadata filter require that one of the top k that are returned include that value?

OOrion Pax

or does it filter prior to that step?

OOrion Pax

Doing separate index worked well

LLogan M

Glad to hear!

Yea for filtering, it filters out prior to getting the top k

Add a reply