run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-07-18 07:44:41 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Issue Parsing Tables Across Multiple Pages in PDF Documents #569

New Issue
Open
opened 2026-02-16 00:18:17 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:18:17 -05:00
Owner
Copy Link
Copy Source

Originally created by @grouppalagi-hub on GitHub (Nov 11, 2025).

Hello,

I would appreciate your help in resolving an issue I’m facing.

Earlier, I successfully used your service for parsing PDF documents with the following basic settings, which provided stable results:

  • Parse mode: parse_page_with_llm
  • High-resolution OCR: enabled (high_res_ocr = true)
  • Adaptive long table processing: enabled (adaptive_long_table = true)
  • Outlined table extraction: enabled (outlined_table_extraction = true)
  • Output tables as HTML: enabled (output_tables_as_HTML = true)

However, since November, using these same settings has resulted in incorrect outputs.

I have also tried selecting specific models for parsing, but the accuracy has significantly decreased. The 'extract' with manual element selection tool does not provide satisfactory results either.

The main challenge arises when dealing with tables that span across multiple pages within a PDF document. While the tables themselves are structured, page breaks cause issues during recognition.

Could you please advise on what settings or tools would be best suited to accurately process PDFs containing such tables?

Thank you very much for your assistance and support!

For indication - https://cloud.llamaindex.ai/project/d1b3df3d-68b2-44d0-9cd9-27b3d3a0eb61

Originally created by @grouppalagi-hub on GitHub (Nov 11, 2025). Hello, I would appreciate your help in resolving an issue I’m facing. Earlier, I successfully used your service for parsing PDF documents with the following basic settings, which provided stable results: - **Parse mode:** `parse_page_with_llm` - **High-resolution OCR:** enabled (`high_res_ocr = true`) - **Adaptive long table processing:** enabled (`adaptive_long_table = true`) - **Outlined table extraction:** enabled (`outlined_table_extraction = true`) - **Output tables as HTML:** enabled (`output_tables_as_HTML = true`) However, since November, using these same settings has resulted in incorrect outputs. I have also tried selecting specific models for parsing, but the accuracy has significantly decreased. The 'extract' with manual element selection tool does not provide satisfactory results either. The main challenge arises when dealing with tables that span across multiple pages within a PDF document. While the tables themselves are structured, page breaks cause issues during recognition. Could you please advise on what settings or tools would be best suited to accurately process PDFs containing such tables? Thank you very much for your assistance and support! For indication - https://cloud.llamaindex.ai/project/d1b3df3d-68b2-44d0-9cd9-27b3d3a0eb61
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#569
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?