Find answers from the community

Updated last year

When pairing `SimpleWebPageReader` and

When pairing SimpleWebPageReader and TreeIndex more specifically from_documents where the documents are the load_data from SimpleWebPageReader. Also, including that the query engine update_prompts use a custom template as follows:

Plain Text

query_engine.update_prompts({
  "response_synthesizer:text_qa_template": qa_template
})

Can the response/answer include the document URL where the summary is based from at all?

2 comments

LLogan M

if the document had the URL in the metadata, you could either ask the LLM to include the URL, or you can inspect the metadata of the source nodes

For example

response.source_nodes[0].node.metadata

PPunkbit

@Logan M That's great, thanks a lot! I'll experiment with the metadata source

Add a reply