[GH-ISSUE #592] [FEAT]: Chunking of PDFs #344

Open
opened 2026-02-22 18:19:03 -05:00 by yindo · 4 comments
Owner

Originally created by @sumitsodhi88 on GitHub (Jan 13, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/592

What would you like to see?

The PDF when uploaded has some issue:

  1. chunks are more compared to txt - probably due to the formatting of the pdf file - the /n are more an lines are not continuous making the file large and making more cunks.
  2. the superscripts/ headers and footers of pdfs in the pdfs are also included causing lot of confusion to the llm - if I ask like "tell me about section 2" -I know a lot of cleaning has to be done before uploading a file - but I can't expect all managers to do that who will only finally complain that the LLM is not good.
    Screenshot 2024-01-14 100113
Originally created by @sumitsodhi88 on GitHub (Jan 13, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/592 ### What would you like to see? The PDF when uploaded has some issue: 1. chunks are more compared to txt - probably due to the formatting of the pdf file - the /n are more an lines are not continuous making the file large and making more cunks. 2. the superscripts/ headers and footers of pdfs in the pdfs are also included causing lot of confusion to the llm - if I ask like "tell me about section 2" -I know a lot of cleaning has to be done before uploading a file - but I can't expect all managers to do that who will only finally complain that the LLM is not good. ![Screenshot 2024-01-14 100113](https://github.com/Mintplex-Labs/anything-llm/assets/149290101/9c45903c-931a-47a4-9182-b42d09d089e6)
yindo added the enhancementfeature request labels 2026-02-22 18:19:03 -05:00
Author
Owner

@sumitsodhi88 commented on GitHub (Jan 17, 2024):

it seems properly fomatted Word files are working fine.

/n in the PDFs affects the context not being able to be identified it seems.

@sumitsodhi88 commented on GitHub (Jan 17, 2024): it seems properly fomatted Word files are working fine. /n in the PDFs affects the context not being able to be identified it seems.
Author
Owner

@Employee9833 commented on GitHub (Feb 1, 2024):

Hi, I also have the same issue with pdf not parsing them correctly.

@Employee9833 commented on GitHub (Feb 1, 2024): Hi, I also have the same issue with pdf not parsing them correctly.
Author
Owner

@jainpradeep commented on GitHub (May 30, 2024):

Did anyone solve this issue?

@jainpradeep commented on GitHub (May 30, 2024): Did anyone solve this issue?
Author
Owner

@station384 commented on GitHub (Oct 29, 2025):

I have been working around this by first converting the PDF to text/markdown which seems to help.

@station384 commented on GitHub (Oct 29, 2025): I have been working around this by first converting the PDF to text/markdown which seems to help.
yindo changed title from [FEAT]: Chunking of PDFs to [GH-ISSUE #592] [FEAT]: Chunking of PDFs 2026-06-05 14:34:49 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#344