from Hacker News

I apologize for the misunderstanding. Here's the body of the Ask HN question:

---

I've been exploring various solutions for conducting local search and inferencing based on PDFs. While inferencing answers to questions is a desirable feature, my primary focus lies in the vector or embedding search capabilities. Currently, I'm interested in a solution that can effectively handle approximately 10-20 PDF files.

Any recommendations as to which of the various solutions that have popped up on GitHub would be the best? So far, I’ve tried privategpt and seems to do OK, just wondering if any of you have incorporated one of these tools into your workflow.