How's it different from something like reka.js or builder.io?

To my understanding, Reka is more of a core no-code builder library while we're an implementation of it. Now I'm considering if we should use Reka to build out the rest of the editor.

With Builder.io, you have to set up a component to inject their UI into your app. It's more difficult to set up and maintain the components. We're opting to give full control of the code. You can develop with Onlook locally without internet for example.

Is there a valtown for Python?

Why do you want it to generate web pages from images? I'm having trouble understanding the workflow here. You see a component you like on another website and want to obtain the code from it? Or if you have a design already, why not just use a Figma to Code tool?

It's not that uncommon to have a workflow where the webpage design gets built and negotiated with stakeholders/customers as a series of photoshop images, and when they're approved, it's forwarded to developers to make a pixel-perfect implementation of that design in HTML/CSS.

say you draw up your rough vision of things that you drew up paper, a very simple mock-up. That could be a nice use case.

If you want to see how something like this might work, I made a fun project where I added a single board computer (SBC) into a keyboard. When you press the 'AI' button, the SBC would send inputs to the LLM on the SBC and output keystrokes to the PC. Demo below if you're curious.

https://youtu.be/BbMSWZKrrcI?si=T_3XIWEtrS8lvxP3

Do you have any good resources for what you mentioned?

Have good critical thinking skills and you’re pretty much there.

Nobody considers them beneath them, you just found a straw man and keep doubling down on it.

In emergency medicine we refer to this as closed loop communication.

It might be helpful to include this in the README.

We have updated the license for Apache-2.0 in the github repository. Please feel free to check it out.

To be more specified, our codes follows the license of Apache 2.0 and the model weights follows the license of Llama 1 since our model is initialized from Llama1

Why do you want to use Next.js if you already have a FastAPI backend?

One of the goals of making an API is to be able to implement multiple frontends on top of it.

In Next.JS server side, whether you query a database or a remote API with `fetch`, there are not much differences. And you'd still want Server Side Rendering to avoid having slow "first display" time.

Looks like it uses pylance for vector database.

We use PyLance for performing searches in databases which do not have a vector-comparison engine. However we use the primary database as the store of vectors and model outputs.

You should check out https://makedraft.com.

It's like v0 but for HTML and TailwindCSS +/- vanilla JavaScript.

Cool! That's more my speed, I'll give it a look... thanks.

Just generates total gibberish for me.

What were you trying to get it to do? It was working alright for me but I was mostly doing quick HTML/CSS templating. I just paste in boilerplates and get it to make tailwind styles changes