האם RAG תומך בקבצי PDF בעתיד?

[sam (Sam Saffron)]

This is now supported and basic documentation is up at:

PDF support in Discourse AI

This guide explains how to implement and use PDF processing capabilities within discourse-ai, including both basic text extraction and enhanced processing with LLM assistance. Required user level: Administrator Summary The discourse-ai plugin supports PDF processing for RAG (Retrieval-Augmented Generation) in two distinct modes: Basic text extraction Enhanced processing with LLM analysis Basic text extraction This mode provides fundamental PDF processing c…

Note, enhanced processing will require container changes at the moment as @featheredtoast / @tgxworld were in the midst of refactoring image magick support and we dropped ghostscript support by mistake.

This can be configured by hand but would is beyond the scope of what I can post here, it is fiddly steps, so those waiting of enhanced processing, give us a few weeks.

[Heliosurge (Dan DeMontmorency)]

@Saif

One of the challenges with the work behind this is supporting PDFs of all types. As you can imagine some PDFs are straight text and easy to parse. However, there are some with custom fonts, images, graphics, non-linearly formatted etc

Very valid points. Also some pdfs while have text in them. They are lazy scans as a graphic file vs a ctual text.