As the title says, I have many PDFs - mostly scans via Scansnap - but also non-scans. These are sensitive in nature, e.g. bills, documents, etc. I would like a local-first AI solution that allows me to say things like: "show me all tax documents for August 2023" or "show my home title". Ideally it is Mac software that can access iCloud too, since that where I store it all. I would prefer to not do any tagging. I would like to optimize on recall over precision, so False Positives in the search results are ok. What are modern approaches to do this, without hacking one up on my own?
Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
1–10 of 92 posts
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#2getcody.ai
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#3I tried Google's NotebookLM for this use case and was very pleased with the experience.
If you trust Google that is.
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#4getcody.ai
the op wanted a local method, and this does not seem to be local
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#5Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#6OCR and pattern matching on text are computationally cheap and incredibly easy to do. For example, tax documents often bear the name of your government's tax authority, which presumably you are familiar with and can search for. They also tend to have years on them.
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#7Paperless supports OCR + full text indexing: https://docs.paperless-ngx.com/
As far as AI goes, not sure.
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#8I tried Google's NotebookLM for this use case and was very pleased with the experience. If you trust Google that is.
NotebookLM is currently US only, limited to 20 documents (sorry, 'sources') per notebook, and only works with Google Drive.
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#9For macOS, there's this: https://pdfsearch.app/
Without AI, but searching the PDF content, I use Recoll (https://www.recoll.org/) or ripgrep-all (https://github.com/phiresky/ripgrep-all)
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#10Devonthink would do this with a tiny model to translate your natural length search prompts into its syntax and your folder/tag tree.
If you're okay with some false positives, Devonthink would work as is, actually.