Adam Laker Illoul

Results 9 comments of Adam Laker Illoul

Wondering whether we should split this out into - univariate_linear_regression.py => numerical method - multivariate_linear_regression.py => gradient descent approach and deprecate the linear_regression.py file we have. That way individuals can...

@mishushakov tested for the openai section, doesn't crash the server anymore :D ![Screenshot 2024-05-02 at 11 18 39](https://github.com/mishushakov/llm-scraper/assets/85499621/dded95b7-df21-4a0e-8536-23f1e506ee8e) I haven't tested the Llama one, but I think it should work...

@mishushakov Been trying to test using [this model](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF) as my model, but my machine cannot handle it. What model are you using?

Tested this with TinyLlama and no crashes :D ![Screenshot 2024-05-03 at 13 37 33](https://github.com/mishushakov/llm-scraper/assets/85499621/b7879105-91e1-48e8-9c8d-5a13ca131bd5) that being said, there weren't any crashes without the try/catch block for the local model, because...

While I have you @mishushakov , maybe you have more experience, with these models, I seem to get this error when trying to scrape data from a fairly large website....

We can try and use the Accessibility feature on playwright https://playwright.dev/docs/accessibility-testing This would extract all the text. Could be a good start to reduce the HTML size. @mishushakov

> seems like they transpile that code that is supposed to be evaluated in the browser Yeah, which is a bit strange right? Surely a TS dev would know to...

I've been able to get around the issue by running ``` page.addScriptTag({url: 'http://X.com/Y', type: 'module'}) ... page.addScriptTag({content: 'import {Z} from http://X.com/Y', type: 'module'}) ``` to enable me to use `Z`...