Weves

Yep, we have our own implementations! We've spent a lot of time on them, and in our internal benchmarks they compare pretty favorable to the native versions.

RAG specifically is our speciality - we've done a ton of optimizations there (hybrid search, document age-based weighting, giving the LLM the ability to read more from interesting docs and less of irrelevant docs, etc.) and we outperform the implementation within ChatGPT quite substantially in internal blind testing.

Curious what you find if you compare them head to head though!

A few reasons:

1/ No model lock-in / ability to use the ideal model for each use case.

2/ More connectivity. A fuller connector library (contributed to by the open-source community). More built-in tools (similar to the ^).

3/ Customizability and flexibility. If you really need a feature, you can build it rather than waiting months (years?) for your request to go through.

4/ White-labeling. You can make it feel like a product built for/by your company rather than generic.

You could! We have a number of users who do something like that (e.g. Ramp's in-app chat bot is powered by Onyx)

Great suggestion! I haven't heard of it before, but I'll definitely add it to the list.

Would love to hear your feedback after you get a chance to try Onyx out.

Thanks! Especially these days, refinement is (by far) the hardest part :)

> 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 think that's in-line with what you're thinking of, or do you want to build outside of those confines?

> canvas mode and scheduled actions

Yes, writing and recurring are two big areas we want to tackle next year.

> The main thing I really care about is voice mode

Interesting. Why do you think that is?

We have! Likely not for a while, since we want to focus on the web app for a bit more. But long term that would be the plan.

Things like shortcuts to access the chat + ability to reach into the local file system are very compelling.

Yes indeed! Our belief is that tool design, compaction (e.g. tool result summarization), and reminders are the things that separate a product that works magically vs one that falls over on any slightly more complex task.

And this is all made all the more important when supporting the wide range of models, even "weaker" open-source models.

What format are the docs being uploaded as? By default, images uploaded into the chat would be directly passed through. PDFs would be parsed and fed to the LLM as text.

Writing is a really common use case, and something we'd like to explore more. Currently people often use Onyx for "write something combining X, Y, and Z documents", but I feel that's just scratching the surface.