search

NVIDIA / ChatRTX

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM
Other
2.75k stars 339 forks source link

PDF Error? #67

Open electro-logic opened 5 months ago

electro-logic commented 5 months ago

Hello,

I'm trying ChatRTX, but I got this message many times in the console log:

[06/04/2024-20:10:42] /Kids or /Limits found in PageLabels. Please share this PDF with pypdf: https://github.com/py-pdf/pypdf/pull/1519

Is PDF support complete? I don't know which files should I share with pypdf.

anujj commented 5 months ago

Thanks for reporting it.

I have a few queries:

  1. Is it impacting the functionality?
  2. Are there many PDF files in the directory? Is it possible to narrow down which file this message is coming from? I want to reproduce the issue on my system and need the specific PDF file to do so."
electro-logic commented 5 months ago

Hello,

  1. The processing is taking forever with low CPU/GPU utilisation so seems that this error is slowing down the app.
  2. Yes there are many files, is there a way to print which file is generating the warning?
alanshlam commented 3 months ago

I find that if I split the pdf file into smaller pdf files. The error messages do not show up. Any solution without splitting the pdf file?