Eduard Ruzga

Well reason I asked for this is that I did fail to make it work in some simple case. Like here create vanilla typescript project on codesandbox and added just...

Was actually looking for something to do language identification client side, bit sad this does work even though it seems it could.

Wanted to test it quickly by loading from CDN trough unpkg https://www.unpkg.com/browse/[email protected]/ So I could add script tag to a html page like this: `` That results in an error:...

Ouh its my bad, it seems to work. I was using TensorFlow JS universal sentence encoder https://github.com/tensorflow/tfjs-models/blob/master/universal-sentence-encoder/README.md And for whatever reasons in some cases it returns [number[]] instead of number[]...

@MentalGear sorry missed your question, I since then switched to using other things My code was kinda like this https://jsfiddle.net/wonderwhy_er/k4bwLf2e/31/ But it does not work in jsfiddle and I do...

Because it will timeout anyways due to how clients work There are also blocking never returning calls Synchronous was first implementation I moved away from As for the problem you...

Yeah, that limit is there as this would already eat 25% of chat context. If page is larger you are risking not being able to do anything useful with it....

@romnovi yeah I am thinking to add options to ask for only parts of the page. So you can get text only, or markdown style and other reduced forms.

Is it 90k characters? I would usually recommend to split files to small ones. I try not to go over 300 lines per file. That helps LLMs to read only...

We just released a version that allows to read any size in chunks and change defaults of how much is read by default