141–150 of 163 posts
Just curious. Especially with both OpenAI and Anthropic really also outpacing startups in release cadence unlike previous cycles.
Guessing your selling point is any model no locking (Assuming we are happy with the privacy SOC 2 etc guarantees on enterprise contracts here)
Earlier quoted context omitted.
Yes, but imagine a chat app that's designed for accountants, that has widgets for accounting, and it's set up for accounting workflows. That's _HUGE_ but not something that a "one chat to rule them all" is going to just go and do. You could use that same example for lab technicians and any other role.
Same "verticalization" argument people made for search in the early 2000s. There's a lot more use cases for tech than just vertical SaaS apps.
One thing I really care about is extensibility. Every now and then one of the big consumer apps adds a feature I really like and the self-hosted solution should have some way to integrate that. The main thing I really care about is voice mode, as that's my far preferred way of interacting with LLMs for longer backs and forths (most apps I've seen disable a lot of other functionality during it, which I hate, btw). Two…
> One thing I really care about is extensibility Totally makes sense! We've defined simple `Connector`, `Tool` and (soon) `Agent` interfaces to make it easy to plug in your own implementations/apps. If you wanted, you could just use Langchain under our Agent class to build arbitrary flows. Additionally, the main chat is created from a series of `Renderer` components, and it should be easy to build your own. Do you th…
It definitely sounds good. Of course it's hard to anticipate what interfaces new features will require, it probably won't always be possible to integrate new features with a generic plugin (voice mode is most likely such a feature), but if the code is well architected, this should be okay.
> Interesting. Why do you think that is?
Writing has a lot of friction to me. It's much more comfortable for me to provide context through verbal rambling, which LLMs are great at processing. I like to research stuff and throw around ideas while pacing, doing chores or just lying with my eyes closed.
Unfortunately I just discovered that I won't be able to run Onyx on my low powered home server anyway (https://docs.onyx.app/deployment/getting_started/resourcing#...). I understand that a Vector database requires significant resources to run, but I wish there was a version without it.
This is great, the value is there. I work for a F100 company that is trying (and failing) to build this in house because every product manager fundamentally misunderstands that users just want a chat window for AI, not to make their own complicated agents. Your biggest competition in the enterprise space, Copilot, has terrible UI and we only put up with it because it has access to email, SharePoint and Teams.
I would actually argue chat windows are terrible ui/ux for most cases and users. It does the opposite of `don't make me think`. Too much potential for user error.
Not saying there shouldn't be any LLM integration/features, just that it should be in the form of a button press or something (familiar ux), not the same chatgpt interface that all the early apps are trying to mimic for no good reason.
My main concern is how well do all the extra features work compared to the native versions? Like web search, RAG on a document, or deep research, adding images, voice chats - my understanding is the models providers don't provide any API's for any of this stuff, so you have your own implementations of all the extra stuff right? Usually I find the open source versions of all these features aren't up to par with the corporate versions and they lag behind in development.
I was pretty excited for Onyx as a way to stand up a useful open source RAG + LLM at small scale but as of two weeks ago it was clearly full of features ticked off a list that nobody has actually tried to use. For example, you can scrape sites and upload docs but you can’t really keep track of what’s been processed within the UI or map back to the documents cleanly. It’s nice to see an attempt at an end to end stack…
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 th…
I'm sure you guys are thinking about this, but please just go through the steps of setting up via docker, uploading say a grad student's worth of papers and docs, scrape a small topic off wikipedia, try and use it for three days and take a look at the ergonomics. It's not easy to regroup sets of documents, get results that link to the document to view post indexing for RAG etc. etc. etc.
In general there are a lot of low hanging RAG optimizations that you could do to make this usable for people who don't want to write their own bits of code to make it usable. I ended up fiddling a bit more with anythingllm which, while having fewer features, understands the workflows a bit more.
This was funded by YC? Why? It's more of a developer project/tool. It will become useless really quickly.
"The reason is because VC needs to show that their flagship investments have "traction" so they manufacture ecosystem interest by funding and encouraging ecosystem product usage. It's a small price to pay. If someone builds a wrapper that gets 100 business users then token use on the foundation layer gets that passed down. Big scheme."