image-based PDFs #261

Closed
opened 2026-02-15 16:29:18 -05:00 by yindo · 2 comments
Owner

Originally created by @20246688 on GitHub (Apr 14, 2025).

Does Ollama-Python support recognizing text from image-based PDFs, like scanned documents? If so, is there an example of how to do that?

Originally created by @20246688 on GitHub (Apr 14, 2025). Does Ollama-Python support recognizing text from image-based PDFs, like scanned documents? If so, is there an example of how to do that?
yindo closed this issue 2026-02-15 16:29:18 -05:00
Author
Owner

@karanravindra commented on GitHub (Apr 14, 2025):

You turn the pdf into an image

to be honest, not sure what the best package is to do so but if you don't have many pdfs, there are many online tools to do the conversions

@karanravindra commented on GitHub (Apr 14, 2025): You turn the pdf into an image to be honest, not sure what the best package is to do so but if you don't have many pdfs, there are many online tools to do the conversions
Author
Owner

@20246688 commented on GitHub (Apr 14, 2025):

您将 PDF 转换为图像

老实说,不确定最好的软件包是什么,但如果您没有很多 PDF,则有许多在线工具可以进行转换

thanks

@20246688 commented on GitHub (Apr 14, 2025): > 您将 PDF 转换为图像 > > 老实说,不确定最好的软件包是什么,但如果您没有很多 PDF,则有许多在线工具可以进行转换 thanks
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: ollama/ollama-python#261