Mayo Oshin

Hey there are several potential culprits behind this. I cover them [here](https://github.com/mayooear/gpt4-pdf-chatbot-langchain/discussions/6) in the discussions section. Here are potential causes of the error, I posted below. Try them out and...

> Hey there are several potential culprits behind this. I cover them [here](https://github.com/mayooear/gpt4-pdf-chatbot-langchain/discussions/6) in the discussions section. > > Here are potential causes of the error, I posted below. Try...

Hi, thanks for the feedback. Based on what you're saying the translation works well, but not for the page you want? What language is this? I will add this feature...

Generally openai's embeddings aren't great for multilingual. If you ask it to translate from English to Japanese how is the performance?

There is no concept of page because the chunks are currently split by character count. I will add a PR later to split the PDF docs by page number later.

It's working fine on my end. Can you send screenshot? What browser are you using

Is this resolved?

I will look to fix this in the next PR. Although it seems to be an issue once deployed?

Yes, good point. OCR, corrupted/non-viewable PDFs and scanned PDFs are very difficult to read, so that is another cause of errors.

Have you followed the steps in the `README`? Installing dependencies and running the ingest script.