Thanks for the reminder. Yes, we do have this on our queue, but it is still lower priority compared to other tasks we are working on.
Please understand we have a small team, and we rank tasks based on the potential number of users who would likely use these features, and this POST request block is too advanced for most of our users.
Thanks for the suggestion. There are 2 issues to consider:
I’ve discovered WebLLM recently and it’s impressive, running Llama-3.2-1B-Instruct-q4f16_1-MLC on a school chromebook with 8gb RAM with my custom HTML chat UI, here was my result:
Essentially, instead of running AIs on a backend or server, like with ChatGPT (which costs money), it runs it all on your device, or more accurately, inside your browser. The only downside is that some devices/browsers (like Safari) don’t support WebGPU, which I assume is an API that this library depends on. Another is that initializing these and/or talking to these could be slow or eat up your memory.
Maybe CreatiCode could add this? Here is the link to the NPM library: https://www.npmjs.com/package/@mlc-ai/web-llm
And the list of models is in the prebuiltAppConfig object of the module, so therefore accessed by logging webllm.prebuiltAppConfig to the console. I’ve only been able to get it to work in <script> tags with type=module , so if you guys don’t use ES6 modular code, this might not work. If you need help, ill give it.
This would be game changing, as we wouldn’t have to worry about chatting with it for too long and wasting credits or facing ratelimiting/ errors like “MAX LIMIT REACHED”, and it would all be done for free!
@info-creaticode said in POST request block:
So what would this block look like? What parameters should it take? Where would the results be stored?
it should allow to send more detailed HTTP requests (GET and POST) and allow all of the options and headers and whatnot.
https://forum.creaticode.com/topic/1255/feature-request-blocks-to-send-http-requests?_=1754798704902 was where i showed what the block could look like
So what would this block look like? What parameters should it take? Where would the results be stored?
@info-creaticode i made a suggestion for POST a while ago, it can be used for good purposes and is also found in other scratch mods as well. It can be used to interact with APIs easier and do things that GET currently cant
There is already a block for “fetch web page as markdown” in the cloud extension. Can you give some specific examples for how to use this new POST block?
Got it. We will implement a better way to ban this user.
@info-creaticode they made another using their real face again https://forum.creaticode.com/user/stupidjuniorcomedian
