Find answers from the community

Updated 7 months ago

Hi! Maybe this question is stupid... but

Hi! Maybe this question is stupid... but imagine i have 200 docs and i want to make a RAG to retrieve the documents where an specific topic is talked about. Imagine i have 200 documents abouts cars, but in only 20 of those they talk about ferraris.
I would like to do something like document comparison but at large scale. how can i do this? I would like to do something like analytics of documents with rag. I though about this (https://docs.llamaindex.ai/en/stable/examples/agent/agent_runner/agent_around_query_pipeline_with_HyDE_for_PDFs/ and https://docs.llamaindex.ai/en/stable/examples/agent/multi_document_agents/ )

but I would like to know if someone has already worked on this topic. Thanks.
r
J
2 comments
Maybe just do a retrieval with a score threshold of the nodes and then get unique document ids of the retrieved nodes?
That's possible. We can save the document in vector database with index and just get the index of retrieved collections.
Add a reply
Sign up and join the conversation on Discord