Local Deep Research – ArXiv, wiki and other searches included • Hacker News Board

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

#31

Post by antonkar » Wed, Mar 12, 2025, 4:40 PM UTC

Der_Einzige wrote: post #30

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.

Yep, there is also the “Multiversal Typewritter” idea https://x.com/MelonUsks/status/1899809021277671681

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

#32

Post by HashedViking » Mon, Mar 17, 2025, 8:40 AM UTC

Hello there,

I'm the coauthor of this project (UI part). I've joined this project when it was below 100 stars (a week ago), motivated by the 'local' sentiment. I think all of those 'open' alternatives are just wrappers around PAID 'Open'AI APIs, which just undermines the 'Open' term. My vision for this repo is a system independent of LLM providers (and middlemen) and overpriced web-search services (5$ per 1000 search requests at Google is just insane). Initially, I just wanted to experiment a bit and didn't expect the repo to explode, so feel free to critique the UI code I hacked together over a few evenings.

The ultimate goal:

A corporation-free LLM usage (local graph database integration sounds good).

A corporation-free web search (this is a massive challenge — even SearXNG relies on Google/Bing under the hood)

So, if you feel the same join the project, and lets build something great!

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

#33

Post by HashedViking » Mon, Mar 17, 2025, 9:08 AM UTC

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…

Summarization quality depends on the question, of course mathematical or programming requests will benefit from reasoning models, but for some casual researches consisting of a few web-pages summarization is done ok even by mistral:7b, but as for the Detailed Report it would be better done by a reasoning model.

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

#34

Post by HashedViking » Mon, Mar 17, 2025, 9:12 AM UTC

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.

Good take on that. I still think a q8 32B model with a 200k context would fit into the 48Gb VRAM of one of those modded RTX 4090.

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

#35

Post by learningcircuit » Sun, Mar 23, 2025, 3:25 PM UTC

I wanted to share some updates on Local Deep Research since posting here 12 days ago. Thanks to everyone who gave feedback and suggestions - the project has improved significantly with your input.

Recent improvements:

- Better inline citation: Sources from PubMed, arXiv, Wikipedia, etc. are now properly cited directly in the text

- Improved report structure: Reports now have better organization with logical sections and clearer source attribution

- Added support for multiple research domains: Works well across scientific, historical, economic, and technical topics

- Enhanced search iterations: Now performs multiple rounds of research with follow-up questions for deeper analysis - More flexible LLM integration: Works with pretty much any model (local via Ollama or cloud-based)

- Expanded search engine options: Easy to add new sources for specialized research

For those who mentioned concerns about report quality and organization - we've made significant improvements in this area. The citation tracking now provides much better provenance information throughout the research pipeline.

I'd also like to thank HashedViking who joined as a contributor and has been improving the UI/UX side of things. We're committed to keeping this as a truly local, privacy-focused tool that doesn't rely on expensive APIs.

For anyone interested in contributing, we're looking for help with: 1. Further improving report organization 2. More local search engines and sources 3. Documentation and examples 4. UI/UX enhancements 5. Testing with different models and research domains

The project is at: https://github.com/LearningCircuit/local-deep-research/

What features would be most useful to you in a research tool like this? We're particularly interested in ideas for better knowledge organization and making the research outputs more valuable.