Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Why doesn't it answer questions? #30

Open
Tony20221 opened this issue Feb 4, 2025 · 2 comments
Open

Why doesn't it answer questions? #30

Tony20221 opened this issue Feb 4, 2025 · 2 comments

Comments

@Tony20221
Copy link

I gave it an Amazon page which has 48 products. I told it to create a csv file from the products. It extracted 10 only. When I asked it why it extracted 10 only, it comes back with the same list without answering my question. I was using gpt-4o-mini. When I used gpt-3.5-turbo, I got 5 products only back.

Why doesn't answer my question? Why doesn't it extract all the products on the page? Is Amazon dynamically returning fewer products based on the type of visitor?

@itsOwen
Copy link
Owner

itsOwen commented Feb 5, 2025

Try these below:

Does the page already have 48 products loaded, or do you need to scroll down to load more?

If there are multiple pages, use the multiple-page extract feature.

Try prompting it like, "Can you extract all pages in CSV format, please?"

@Tony20221
Copy link
Author

Tony20221 commented Feb 5, 2025

https://www.amazon.com/s?k=chocolate&crid=2LE7GL6YR9LM8&sprefix=chocolate%2Caps%2C169

The first page has 48 products. I have tried different prompts. I never get 48 products.

I think what's happening is that I see 48 products when I use the browser manually. Amazon is returning a different page when the browser session in your app is used. I would like to see a way to save the response your browser got so I can compare.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants