You don't. You use a full-text indexer and normal search tools. A chatbot is only going to decrease the integrity of query results.
Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
21–30 of 92 posts
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#22You don't. You use a full-text indexer and normal search tools. A chatbot is only going to decrease the integrity of query results.
You wouldn't use a chatbot for the same query you'd use normal search tools for (and on a side note your answer would be much more useful with an example of what those tools would be, it's not really actionable). A vague natural language question over data whose structure you haven't fully understood using terms that might be inexact is not as likely to provide good results with normal search tools as with an llm based tool.
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#23You can tabulate the info 90% of your info will be from single source. There are online tools that sort costco and walmart bills !!
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#24You don't. You use a full-text indexer and normal search tools. A chatbot is only going to decrease the integrity of query results.
You wouldn't use a chatbot for the same query you'd use normal search tools for (and on a side note your answer would be much more useful with an example of what those tools would be, it's not really actionable). A vague natural language question over data whose structure you haven't fully understood using terms that might be inexact is not as likely to provide good results with normal search tools as with an llm bas…
> your answer would be much more useful with an example of what those tools would be
Paperless, DevonThink, even Calibre (the ebook manager) can do it.
You only need a day or two to categorize the documents. No need for huge amounts of RAM, or privacy concerns, or hallucinated answers.
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#25I use Curiosity AI. Good interface.
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#26Earlier quoted context omitted.
You wouldn't use a chatbot for the same query you'd use normal search tools for (and on a side note your answer would be much more useful with an example of what those tools would be, it's not really actionable). A vague natural language question over data whose structure you haven't fully understood using terms that might be inexact is not as likely to provide good results with normal search tools as with an llm bas…
> your answer would be much more useful with an example of what those tools would be Paperless, DevonThink, even Calibre (the ebook manager) can do it. You only need a day or two to categorize the documents. No need for huge amounts of RAM, or privacy concerns, or hallucinated answers.
> You only need a day or two
A recent example, maybe not the best example but recent, was the query "What do the three headed dog from the Harry Potter books and the cat from Alien have in common"
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#27RAG cli from llamaindex, allow you to do it 100% locally when used with ollama or llamacpp instead of OpenAI. https://docs.llamaindex.ai/en/stable/getting_started/starter...
Does the llamaindex PDF indexer correctly deal with multi-column PDFs? Most I've seen don't, and you get very odd results because of this.
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#28Using python to dump the PDF to text then use llama3 (8B) to parse
The "Using python to dump the PDF to text" dramatically underestimates how hard this is.
Tables and especially multi-column PDFs often need one-off handling and - worse - you don't know when one is being misparsed until you start getting weird search results. At that point you need to debug your entire search pipeline, which isn't fun!
Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#29Earlier quoted context omitted.
> your answer would be much more useful with an example of what those tools would be Paperless, DevonThink, even Calibre (the ebook manager) can do it. You only need a day or two to categorize the documents. No need for huge amounts of RAM, or privacy concerns, or hallucinated answers.
> You only need a day or two For some of us, for some types of data, huge amounts of RAM, or even privacy concerns, or even the occasional hallucinated answer, is an easier pill to swallow. A recent example, maybe not the best example but recent, was the query "What do the three headed dog from the Harry Potter books and the cat from Alien have in common"
They are fictional.Re: Ask HN: I have many PDFs – what is the best local way to leverage AI for search?
#30Earlier quoted context omitted.
You wouldn't use a chatbot for the same query you'd use normal search tools for (and on a side note your answer would be much more useful with an example of what those tools would be, it's not really actionable). A vague natural language question over data whose structure you haven't fully understood using terms that might be inexact is not as likely to provide good results with normal search tools as with an llm bas…
> your answer would be much more useful with an example of what those tools would be Paperless, DevonThink, even Calibre (the ebook manager) can do it. You only need a day or two to categorize the documents. No need for huge amounts of RAM, or privacy concerns, or hallucinated answers.
I never want to categorize stuff. I want it done for me.