joaomdmoura / crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
https://crewai.com
MIT License
16.95k stars 2.29k forks source link

PDF Tool and UTc-8 #825

Open 1d2g opened 1 week ago

1d2g commented 1 week ago

Trying to read a PDF and keep running into an "invalid continuation byte" from some searching it seems that this is due to the encoding of the PDF but I haven't found a viable way to get around this. Any help would be greatly appreciated. I'm new to Github so also please let me know if this is the improper way to go about asking this. Thanks!

kareemramd commented 1 week ago

In my case, if your Pdf only contain text and tables better convert it to markdown file, its more readable by LLM.

you can use Llamaparse, they gave a good job for me and give 1k free pages daily.