A document will have many paragraphs.
You create embedings for each line.
Pinecone will send the top 100 matching lines.
lines will have the metadata of which paragrah its part of
You do a group_by on the paragraph_ids.
take the top 5 para and their nearby paras
pass this to gpt.
A document will have many paragraphs.
You create embedings for each line.
Pinecone will send the top 100 matching lines.
lines will have the metadata of which paragrah its part of
You do a group_by on the paragraph_ids.
take the top 5 para and their nearby paras
pass this to gpt.