Unique table parsing Issue #495

Open
opened 2026-02-16 00:18:01 -05:00 by yindo · 0 comments
Owner

Originally created by @sree-teja on GitHub (Jul 1, 2025).

Hi team,

I'm using LlamaCloud to parse a PDF document that contains tables with subheadings (e.g., "Adrenal Gland: Pheochromocytoma"). However, in the output JSON, these subheadings are NOT included in the table node.

Image

In the document, these subheadings appear within or directly above the table structure, serving as logical groupings for the data rows that follow. They are visually distinct (e.g., bold text spanning across columns), but do not appear to be recognized or associated with the table in the parsed output.

Is there a way to include these subheadings in the structured output, or tag them so that they can be associated with the relevant table rows?

Thanks!

Originally created by @sree-teja on GitHub (Jul 1, 2025). Hi team, I'm using LlamaCloud to parse a PDF document that contains tables with subheadings (e.g., "Adrenal Gland: Pheochromocytoma"). However, in the output JSON, these subheadings are NOT included in the **table node**. <img width="704" alt="Image" src="https://github.com/user-attachments/assets/929cca72-fb2e-4eae-b616-2df7d87b281e" /> In the document, these subheadings appear within or directly above the table structure, serving as logical groupings for the data rows that follow. They are visually distinct (e.g., bold text spanning across columns), but do not appear to be recognized or associated with the table in the parsed output. Is there a way to include these subheadings in the structured output, or tag them so that they can be associated with the relevant table rows? Thanks!
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#495