search

alejandro-ao / langchain-ask-pdf

An AI-app that allows you to upload a PDF and ask questions about it. It uses OpenAI's LLMs to generate a response.
584 stars 308 forks source link

Bug: PDF images vs text #5

Open axsddlr opened 1 year ago

axsddlr commented 1 year ago

ERROR

image

Reproduce

  1. upload PDF that is based on images i.e employee handbook, etc..
  2. error will show

Possible Solution

try/except if PDF cannot be read give user error message instead of traceback

DjangoMaker commented 1 year ago

Is there a solution to this error? Any PDF i upload I get this error.

axsddlr commented 1 year ago

Make sure pdf is native text. Not image text

On Mon, May 15, 2023 at 8:51 AM DjangoMaker @.***> wrote:

Is there a solution to this error? Any PDF i upload I get this error.

— Reply to this email directly, view it on GitHub https://github.com/alejandro-ao/langchain-ask-pdf/issues/5#issuecomment-1547802078, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAO5EMZ6VEQBN2KDLJ4NQQDXGIREFANCNFSM6AAAAAAX45GHUQ . You are receiving this because you authored the thread.Message ID: @.***>