Find answers from the community

Updated last year

For those pdf doc being embeddinged is

For those pdf /doc being embeddinged, is there any way to show the source of page numbers , apart from file name ? I saw one demo using langchain, can llamaindex support that feature ?

3 comments

LLogan M

If you set the metadata to include extra information, then that metadata will show up in the response source nodes

For example, if I have Doucment(text=text, metadata={"page_number": 2}) -- that information will be inherited to any nodes created from that document

aautratec

Is it an auto process to get correct page number included in the meta data or it is manual page by page setup ? Any sample code can be shared ? Thx

LLogan M

It depends on the document loader. Off the top of my head, I know the pdf loader adds page numbers to the Metadata for you automatically.

Other document types, you'll have to manage it yourself I think

Add a reply