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

Show HN: Open-source Deep Research across workplace applications

github.com

Post reply on HN
Print view View original

21–30 of 32 posts

Re: Show HN: Open-source Deep Research across workplace applications

#21

Post by yuhongsun »

monkeydust wrote: post #6

I have recently found myself drawing parallels between deep research and knowledge working org structures. For example,board exec asks senior exec a question about a particular product. The senior exec then has to fire off emails to say 5 managers, who might go down their tree to ICs, all the info is gathered and synthesised into a response. Normally this response takes into account some angle the senior exec might h…

Yup, hopefully with Onyx, the folks who have these questions can just fire off a query with agent mode turned on and the LLM will research the relevant tree of knowledge and come back with an answer in the fraction of the time it would take for people to do it with all of the handoffs in between.

Re: Show HN: Open-source Deep Research across workplace applications

#22

Post by yuhongsun »

lxe wrote: post #10

What's the difference between deep research and RAG?

RAG is a tool for the deep research agent to use in finding all of the context it needs. Deep research can call the search many times and reflect on the results of the previous searches and then search for other things as needed. Deep research flows can also generate chain-of-thought type outputs that is not for searching or for directly answering the user.

Re: Show HN: Open-source Deep Research across workplace applications

#23

Post by timhigins »

yuhongsun wrote: post #15
laborcontract wrote: post #3

Cool product. Few Qs: - What would you say is the agentic approach's special sauce over a typical RAG pipeline, ie query->multi-query generation->HyDE->vector search->bm25 search->RRF->rerank->evaluate->(retry|refuse|respond) that differentiates the approach? - If a user has 20 services connected, how does the agent know how to call/search/traverse the information in the right order? - Do you have any internal evals…

Quite a lot to cover here! So in addition to the typical RAG pipeline, we have many other signals like learning from user feedback, time based weighting, metadata handling, weighting between title/content, and different custom deep learning models that run at inference and indexing time all to help the retrieval. But this is all part of the RAG component. The agent part is the loop of running the LLM over RAG system…

Do you think this indexing architecture would bring benefits to general web research? If implemented like: planner, searches, index webpages in chunks, search in index, response

Would you ever extend your app to search the web or specialized databases for law, finance, science etc?

Re: Show HN: Open-source Deep Research across workplace applications

#26

Post by murshudoff »

From the demo it looks great. And the UX is pretty sick! Can it be used via API in the self-hosted version? If yes, what are the limitations over UI? In my use-case I would like to use it as a RAG infra and together with tool calling and generative UI in the client code (already implemented) it would complete the picture.

Re: Show HN: Open-source Deep Research across workplace applications

#27

Post by monkeydust »

yuhongsun wrote: post #21
monkeydust wrote: post #6

I have recently found myself drawing parallels between deep research and knowledge working org structures. For example,board exec asks senior exec a question about a particular product. The senior exec then has to fire off emails to say 5 managers, who might go down their tree to ICs, all the info is gathered and synthesised into a response. Normally this response takes into account some angle the senior exec might h…

Yup, hopefully with Onyx, the folks who have these questions can just fire off a query with agent mode turned on and the LLM will research the relevant tree of knowledge and come back with an answer in the fraction of the time it would take for people to do it with all of the handoffs in between.

Yes. I suspect it won't, right now, be as good a response but where time or cost matters an 80% effective response in 10% of the time it would have taken or say 5% of cost (if you were to 'dollarize' worker effort) would present useful options to those asking.

Re: Show HN: Open-source Deep Research across workplace applications

#29

Post by mentalgear »

Thank you for open-sourcing this - very impressive and great UI ! This also marks the need for comprehensive benchmarks for the "large knowledge search, retrieval and analysis" category for users to effectively compare solutions and vendors to objectively compete on.

Re: Show HN: Open-source Deep Research across workplace applications

#30

Post by ai4fun2004 »

yuhongsun wrote: post #2

Before sharing how it works, I want to highlight some of the challenges of a system like this. Unlike deep research over the internet, LLMs aren’t able to easily leverage the built in searches of these SaaS applications. They each have different ways of searching for things, many do not have strong search capabilities, or they rely on their internal query language. There are also a ton of other signals that web searc…

Great work!

When you talked about "document index is a hybrid index of keyword frequencies and vectors", I am a bit curious of how to get them. In pre-processing, do you have to use LLM / models go through documents to get keywords? What about vectors? Are you using embed model to generate them? Does that imply preprocess has to be done whenever there is new doc or any modification in existing doc? Would that be costly in time? Any spicy cook to make the preprocessing more efficient?

Post reply on HN