Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Local Deep Research – ArXiv, wiki and other searches included

github.com

Post reply on HN
Print view View original

21–30 of 35 posts

Re: Local Deep Research – ArXiv, wiki and other searches included

#21

Post by ein0p »

Is there some kind of a tool which would provide AI search experience _and mix in the contents from my bookmarks_ (that is, fetch/cache/index/RAG the contents of pages those bookmarks point to) when creating the report? Bookmarking is an useless dumpster fire right now. This could make it useful again.

Currently the failure mode I see quite often in e.g. OpenAIs deep research is it sources its answer from an obviously low-authority source and provides a reference to that as if it's a scientific journal. The answer gets screwed up by that as well, because such sources rarely contain anything of value, and even if other sources are high quality, low quality source(s) mess everything up.

Emphasizing the content I've already curated (via bookmarks) could significantly boost the SNR.

Re: Local Deep Research – ArXiv, wiki and other searches included

#22

Post by learningcircuit »

throwaway24681 wrote: post #18
learningcircuit wrote: post #15

Earlier quoted context omitted.

Give me a question and I can give you the output? So you can compare.

I tried it myself. It looks like this can do a lot more than open-webui's web search in terms of detail, which sounds useful, thanks for making it open source. It seems to have a weird behavior of specifying a date when I didn't ask for it, is this expected? Also, I feel like searching "questions" is not optimal for most search engines, and it should instead search in terms of keywords. Also, I wish there can be a mo…

Very good ideas I will try to include them.

Thinking models... You can use them. In fact I started the project with them but not sure they help too much for this task. They definitely make it slower

Re: Local Deep Research – ArXiv, wiki and other searches included

#23

Post by nhggfu »

jeffreyw128 wrote: post #16

This is cool! If you want to add embeddings over internet as a source, you should try out exa.ai. Includes: wikipedia, tens of thousands of news feeds, Github, 70M+ papers including all of arxiv, etc. disclaimer: I am one of the founders (:

looks siiiick. congrats + good luck

Re: Local Deep Research – ArXiv, wiki and other searches included

#24

Post by TeMPOraL »

mentalgear wrote: post #5

I applaud the effort for the local (lo-fi) space ! Yet, reading over the example linked in the docs (which does not seem cheery-picked, kudos for that!), my impression is that the document is a rather messy outcome [1]. I think what's missing is one (or more) step in-between, possible a graph database (eg[2]), which the LLM can place all it's information in, see relevant interconnections, query to question itself, an…

> I think what's missing is one (or more) step in-between, possible a graph database (eg[2]), which the LLM can place all it's information in, see relevant interconnections, query to question itself, and then generate the final report.

Quickly, productize this (and call it DeepRAG, or DERP) before it explodes in late 2025 - you may just beat the market to it!

See: https://news.ycombinator.com/item?id=43267539

Re: Local Deep Research – ArXiv, wiki and other searches included

#25

Post by learningcircuit »

jeffreyw128 wrote: post #16

This is cool! If you want to add embeddings over internet as a source, you should try out exa.ai. Includes: wikipedia, tens of thousands of news feeds, Github, 70M+ papers including all of arxiv, etc. disclaimer: I am one of the founders (:

I will add it. Its very easy to integrate new search engines.

Re: Local Deep Research – ArXiv, wiki and other searches included

#26

Post by learningcircuit »

ein0p wrote: post #21

Is there some kind of a tool which would provide AI search experience _and mix in the contents from my bookmarks_ (that is, fetch/cache/index/RAG the contents of pages those bookmarks point to) when creating the report? Bookmarking is an useless dumpster fire right now. This could make it useful again. Currently the failure mode I see quite often in e.g. OpenAIs deep research is it sources its answer from an obviousl…

If you have PDF collection you could include it into the local search and give it very high relevance?

Re: Local Deep Research – ArXiv, wiki and other searches included

#27

Post by ein0p »

learningcircuit wrote: post #26
ein0p wrote: post #21

Is there some kind of a tool which would provide AI search experience _and mix in the contents from my bookmarks_ (that is, fetch/cache/index/RAG the contents of pages those bookmarks point to) when creating the report? Bookmarking is an useless dumpster fire right now. This could make it useful again. Currently the failure mode I see quite often in e.g. OpenAIs deep research is it sources its answer from an obviousl…

If you have PDF collection you could include it into the local search and give it very high relevance?

I don't care what form it takes, all I care is that curation of my knowledge base is as easy as managing a set of bookmarks.

Re: Local Deep Research – ArXiv, wiki and other searches included

#28

Post by wahnfrieden »

suprjami wrote: post #7
wahnfrieden wrote: post #6

Is anyone using (local) LLMs to directly search for (by scanning over) relevant materials from a corpus rather than relying on vector search?

Generally this fails. Most LLMs lose the ability to track facts over about 20k words of content, the best can manage maybe 40k words. Look for "needle" benchmark tests, as in needle-in-haystack. Not to mention the memory requirements of such a huge context like 128k or 1M tokens. Only people with enterprise servers at home could run that locally.

What about scanning over chunks of data to collect matches iteratively - that’s what I meant rather than loading full context limits

Re: Local Deep Research – ArXiv, wiki and other searches included

#30

Post by Der_Einzige »

antonkar wrote: post #14

I think the guy who’ll make the 3D game-like GUI for LLMs is the next Jobs/Gates/Musk and Nobel Prize Winner (I think it’ll solve alignment by having millions of eyes on the internals of LLMs), because computers became popular only after the OS with a GUI appeared, current chatbots are a bit like a command line in comparison. I just started ASK HN to let people and me share their AI safety ideas, both crazy and not:…

You are 100000% correct. It's telling that shitty gradio webuis like oobabooga or automatic1111 got SO many github stars.

ComfyUI is huge despite literally just bringing the node based editor paradigm to Stable Diffusion.

UI/UX for LLMs and GenAI is so hilariously shit right now. So many investors want to invest in yet another LLMops company instead of a meaningful competitor to the terrible LM-studio.

Post reply on HN