Any recommendations on a system that will need to ingest 22,000 pdfs to search for specific information and organize it in a spreadsheet? I was thinking a simple rag would likely get bogged down by all the noise.
I’ve been playing around with the build a bit and your advice has been very helpful! I’m putting it on pause for a moment while I wait on the client to confirm my understanding of the project scope through the PRD I developed. I anticipate I’ll be wrapping it up next week 🤙 I’ll reach out if I hit a snag.