Not able to retrieve full extract of the parsed pdf #225

Closed
opened 2026-02-16 00:17:11 -05:00 by yindo · 2 comments
Owner

Originally created by @cardit1 on GitHub (Aug 5, 2024).

Originally assigned to: @BinaryBrain on GitHub.

I have parsed multiple pdfs in different ways - web ui, post api, and python simplDir.. package.

  1. But when retrieving there is no particular method to retrieve old jobs in python package.
  2. Different amounts of data are being retrieved in different methods ex - in api we are getting some 5000 words where as in python package only 2100 words are being retrieved, i have checked for any limitations variables in python but there are none

Could any one please help me in this or if this looks like a bug please fix it

Originally created by @cardit1 on GitHub (Aug 5, 2024). Originally assigned to: @BinaryBrain on GitHub. I have parsed multiple pdfs in different ways - web ui, post api, and python simplDir.. package. 1. But when retrieving there is no particular method to retrieve old jobs in python package. 2. Different amounts of data are being retrieved in different methods ex - in api we are getting some 5000 words where as in python package only 2100 words are being retrieved, i have checked for any limitations variables in python but there are none Could any one please help me in this or if this looks like a bug please fix it
yindo added the help wanted label 2026-02-16 00:17:11 -05:00
yindo closed this issue 2026-02-16 00:17:11 -05:00
Author
Owner

@BinaryBrain commented on GitHub (Aug 8, 2024):

Hi @cardit1,
This discrepancy between the API and the python package shouldn't occur. Can you please provide your code and package version so that's we can debug it together?

@BinaryBrain commented on GitHub (Aug 8, 2024): Hi @cardit1, This discrepancy between the API and the python package shouldn't occur. Can you please provide your code and package version so that's we can debug it together?
Author
Owner

@BinaryBrain commented on GitHub (Aug 21, 2024):

Please reopen if you have more info.

@BinaryBrain commented on GitHub (Aug 21, 2024): Please reopen if you have more info.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#225