News for hackers. Stuff that matters.

Weves

Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @11:54AM (#46047794)
There are also many teams we work with that want to (1) retain model flexibility and (2) give everyone at the company the best model for the job. Every week? a model from a different provider comes out that is better at some tasks than anyone else. It's not great to be locked out from using that model since you're a "ChatGPT" company.
Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @11:49AM (#46047737)
Yea, the license is modeled after the Gitlab license. All of the core chat/RAG/agent logic is fully MIT, and >99% of deployments of Onyx are using the "community edition"!
Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @11:43AM (#46047648)
You don't need any subscription to run the code! By default, none of the enterprise code runs (and it can all be completely removed and the app will work as expected). Fully FOSS version here: https://github.com/onyx-dot-app/onyx-foss.
Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @11:27AM (#46047430)
Broadly, I think other open source solutions are lacking in (1) integration of external knowledge into the chat (2) simple UX (3) complex "agent" flows.

Both internal RAG and web search are hard to do well, and since we've started as an enterprise search project we've spent a lot of time making it good.

Most (all?) of these projects have UXs that are quite complicated (e.g. exposing front-and-center every model param like Top P without any explanation, no clear distinction between admin/regular user features, etc.). For broader deployments this can overwhelm people who are new to AI tools.

Finally trying to do anything beyond a simple back and forth with a single tool calls isn't great with a lot of these projects. So something like "find me all the open source chat options, understand their strengths/weaknesses, and compile that into a spreadsheet" will work well with Onyx, but not so well with other options (again partially due to our enterprise search roots).

Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @11:08AM (#46047165)
Agree that's a lot of other projects out there, but why do you say the Vercel option is more advanced/mature?

The common trend we've seen is that most of these other projects are okay for a true "just send messages to an AI and get responses" use case, but for most things beyond that they fall short / there a lot of paper cuts.

For an individual, this might show up when they try more complex tasks that require multiple tool calls in sequence or when they have a research task to accomplish. For an org, this might show up when trying to manage access to assistants / tools / connected sources.

Our goal is to make sure Onyx is the most advanced and mature option out there. I think we've accomplished that, so if there's anything missing I'd love to hear about it.

Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @11:02AM (#46047111)
Some of the key differences:

1/ large connector suite + good RAG. Answers at scale is hard, and from our enterprise search roots, we've spent a lot of time with it. It's something that many teams expect from their chat UI.

2/ deep research + open-source code interpreter.

3/ simpler UX. LibreChat has a lot of customizability exposed front and center to the user, which is great for the power user but can be overwhelming for someone new to using AI systems.

Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @10:50AM (#46046960)
Thanks! Open source is awesome :)
Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @10:46AM (#46046903)
RAG + connectors is a huge reason why people deploy Onyx (enterprise search roots means we do a pretty good job there).

Also, open-source works really here, since connectors are a long-tail game. We've tried to make it easy to add connectors (a single python interface), and as a result over half of our connectors are contributed by the community. We expect that percentage to grow over time. This means that compared to something like Agentspace, we'll very likely be connected to all of the key tools at your company (and if we aren't, you can easily add an integration).

Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @10:42AM (#46046850)
Haha, yea we've seen that exact story many times! Dissatisfied with Copilot and building a (not great) internal solution that is missing polish + most of the "advanced" feature set.
Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @10:39AM (#46046814)
Really appreciate the feedback (and glad to hear the core concept resonated with you).

The admin side of the house has been missing a bit of love, and we have a large overhaul coming soon that I'm hoping addresses some (most?) of your concerns. For now, if you'd like to view documents that have been processed, you can check out the `Explorer` panel on the left.

In general, I'd love to hear more about what gives it that "unbaked" feel for you if you're up for a quick chat.

Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @10:27AM (#46046675)
"Chat UI" can "feel" a bit thin from an eng/product when you initially think about, and that's something we've had to grapple with over time. As we've dug deeper, my worry about that has gone down over time.

For most people, the chat is the entrypoint to LLMs, and people are growing to expect more and more. So now it might be basic chat, web search, internal RAG, deep research, etc. Very soon, it will be more complex flows kicked off via this interface (e.g. cleaning up a Linear project). The same "chat UI" that is used for basic chat must (imo) support these flows to stay competitive.

On the engineering side, things like Deep Research are quite complex/open-ended, and there can be huge differences in quality between implementations (e.g. ChatGPTs vs Claude). Code interpreter as well (to do it securely) is quite a tricky task.

Re:Launch HN: Onyx (YC W24) – The open-source chat UI on Tuesday November 25, 2025 @10:11AM (#46046454)
Yes, it absolutely does! The chat UX, add-ons (deep research, code interpreter, RAG, etc.), and SSO are MIT licensed. Most deployments of Onyx are using the pure FOSS version of Onyx. Many individuals / teams have done extensive white labeling (something that OpenWebUI doesn't allow).

We have https://github.com/onyx-dot-app/onyx-foss, for a fully MIT licensed version of the repo if you want to be safe about the license/feel freedom to modify every file.

Launch HN: Onyx (YC W24) – The open-source chat UI

Hey HN, Chris and Yuhong here from Onyx (https://github.com/onyx-dot-app/onyx). We’re building an open-source chat that works with any LLM (proprietary + open weight) and gives these LLMs the tools they need to be useful (RAG, web search, MCP, deep research, memory, etc.).Demo: https://youtu.be/2g4BxTZ9ztgTwo years ago, Yuhong and I had the same recurring problem. We were on growing teams and...

( Read More... | 158 comments | 73 points | on HN )
Re:Launch HN: Airweave (YC X25) – Let agents search any app on Tuesday September 30, 2025 @07:00PM (#45432315)
Don't mean to hijack (one of the Onyx founders here), but the example you described should be doable with Drive service accounts. Admittedly, our permissioning system is only implemented for a handful of connectors like Drive.

Congratulations on the launch Rauf & Lennert! Always great to have more innovation in the open source AI space :D. It looks like Airweave works well with Cursor, something we don't have nailed down yet!

We do have support for IdPs like Azure AD + role based access control (these aren't in the MIT version of Danswer though :sweat:).

If you're interested in learning more, would love to chat through the details on Slack / Discord.

The name was intended to be (1) Danswer -> Deep (learning) Answer and (2) Danswer -> Dancer (thus the logo). Although we've heard quite a ton of different interpretations (the "dude named Dan" is quite popular, as is "Danswer -> The Answer".

The granularity is currently hard-coded (e.g. 512 tokens default chunk size, augmented with passes of 128 tokens). I have not heard of the idea of Frames, but it's interesting. Thanks for sharing - I'll probably do a deep dive sometime this weekend.

"We were building something similar in house, but then we found Danswer". That's something we keep hearing all the time :D

(1) We handle chunking, embedding, building the keyword search index, etc. all on our end! We use Vespa as both our Vector DB / Search Engine (it allows a custom hybrid search, which we've found to perform really well). So no, you would not need to bring your own Vector DB - everything needed to run the system is managed dockerized and managed by Docker compose / kubernetes (whichever you choose).

(2) It would be straightforward! We both offer an API to ingest documents into the system as well as a pretty simple connector interface that you can implement to add your own custom connector (https://github.com/danswer-ai/danswer/blob/main/backend/dans...)

Yep, this is exactly correct! For our SaaS version, we do have an agreement which allows us to look at data if needed to debug issues and/or improve search performance.

For self-hosted deployments, usually a select few admins who have setup the plumbing on AWS do have access (but as nl has mentioned, these people usually have access to superuser access on the tools we connect to anyways so this is a noop).

OpenAI's models may fit that description as well under the hood. Specifically, for `prefix-aware`, this is useful when you have short passages (e.g. Slack messages) that you are trying to match against short queries (e.g. user questions). Without being prefix-aware, the model can get confused, think both are queries, and cause any short passages to match very strongly with short queries.

For learning from feedback for sure! No exact benchmarks, but we've heard from quite a few users about how useful this is to push high quality docs up and reduce the prevalence of poor docs. This is all very hard to evaluate since there aren't readily available, real-world "corporate tool / knowledge base" datasets out there. We're actually building our own in house right now, so we should have more concrete numbers around these things soon.

For the backend, we do a lot of stuff with local embedding models / cross encoders / tokenization / stemming / stop word removal etc. Python has the most mature ecosystem for this kinda stuff (and the retrieval pipeline is the core of our product), so we don't regret it at all!

Thank you for the kind words!

Yea, the name has many meanings. It's a fun little puzzle to find them all :)

Yes absolutely! We actually have a doc specifically for Ollama: https://docs.danswer.dev/gen_ai_configs/ollama
Well the most standard approach is to use cross-encoders (e.g. something like Cohere Rerank) to give similarity scores between the query and the chunk, and then use these scores to update the ranking.

Our approach is to use an LLM (gpt-3.5-turbo for example), and to ask it explicitly "Is this chunk <CHUNK> useful for answering this query <QUERY>". We've found, while certainly a bit more expensive, the larger model size and greater understanding of the world allows this approach to yield significantly better results that the SOTA cross-encoders. It also allows us to ask the model to explain why it's useful, which can be really helpful for the user when determining if they should look deeper into a document (as opposed to the standard keyword-based highlighting which often isn't very useful when determining if a document actually has useful information for your query).

So we're leaning on access control to do this! Right now we support manually configured group-based access at the connector level (e.g. Users X, Y, and Z make up the `Engineering` group and that group should have access to Folders A, B, C in Google Drive + Github).

We're also in the process of adding the ability to sync permissions from sources. For example, with this in place you would only be able to chat with / search over documents in Google Drive that you have access to. Since everything is RAG based rather than any fine-tuning, this will guarantee that someone asking "how much do my colleagues make?" will not get an answer UNLESS they already have access to the document that has this info (in which case, it shouldn't be a problem :D)

Chris here (the other founder) - yes you can! We have an `VALID_EMAIL_DOMAINS ` env variable which controls this.

For example, for us we have `VALID_EMAIL_DOMAINS=danswer.ai`.

Totally understand that :)

With that said, we feel this is a completely different way of interacting with the system and therefore warranted a new post. Rather than just search, you can now converse with your docs while retaining all the same benefits (like being able to browse through the results, go in detail on specific docs, etc.).

Show HN: DanswerChat – open-source GPTs with access to all your org's knowledge [video]

https://www.youtube.com/watch?v=6cDiv-TShh4

Danswer is an MIT licensed project that can connect to a wide range of SaaS tools and provide a search/chat (RAG) functionality to help your team discover information and to turn that information into deeper understanding and actionable insights.Code here: https://github.com/danswer-ai/danswer Setup docs: https://docs.danswer.dev/quickstartDanswer is self-hostable and comes ready to use out of...

( Read More... | 4 comments | 7 points | on HN )

Older »