Missing Data When Parsing in Auto Mode #453

Open
opened 2026-02-16 00:17:53 -05:00 by yindo · 0 comments
Owner

Originally created by @vicacid on GitHub (Mar 17, 2025).

Describe the bug
I have a PDF document containing text data (text, tables, etc.). At the top of the document, there is a logo on one side and text with the company name and address on the other. The text is not an image – it is selectable. However, when I upload the document in auto mode, this text is missing.

Job ID
14ec6c1a-b92e-4281-87be-64c36daad8d2

Client:
Please remove untested options:

  • API
  • Frontend (cloud.llamaindex.ai)

Additional context
The same behavior occurs in both the FE and API. The auto_mode_trigger_on_table_in_page and auto_mode_trigger_on_image_in_page flags are enabled.

Originally created by @vicacid on GitHub (Mar 17, 2025). **Describe the bug** I have a PDF document containing text data (text, tables, etc.). At the top of the document, there is a logo on one side and text with the company name and address on the other. The text is not an image – it is selectable. However, when I upload the document in auto mode, this text is missing. **Job ID** ```14ec6c1a-b92e-4281-87be-64c36daad8d2``` **Client:** Please remove untested options: - API - Frontend (cloud.llamaindex.ai) **Additional context** The same behavior occurs in both the FE and API. The ```auto_mode_trigger_on_table_in_page``` and ```auto_mode_trigger_on_image_in_page``` flags are enabled.
yindo added the bug label 2026-02-16 00:17:53 -05:00
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#453