Find answers from the community

Updated 4 months ago

Hi! I'm using LlamaParse through Python

At a glance

The community member is using the LlamaParse Python library to process a 9-page PDF, but the code debugger is only returning 1 document instead of 9. Another community member suggests that 1 document object corresponds to 1 PDF file. The community member then mentions that they have to split the text by "\n—-\n", but one of their PDF files with 209 pages is not being split correctly, resulting in 212 pages. The other community members are unsure about this issue.

ppikachu8887867

Hi! I'm using LlamaParse through Python library. I've sent a pdf with 9 pages. I can see in LlamaCloud that it indeed processed 9 pages.

But in my code debugger, I can see that it returns only 1 document, not 9. Where is the rest of the pages?

Attachments

3 comments

LLogan M

1 document object == 1 pdf here

ppikachu8887867

@Logan M Okay, turned out I have to split the text by “\n—-\n”, but one of my pdf files is not being split correctly. It has 209 pages, but splitting by \n—-\n gives me 212 pages. Is that a known issue?

LLogan M

Hmm, weird. Not sure actually 😅

Add a reply