run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-26 16:56:36 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Document Size Limitation Error - Need Higher Page Limit for parse_page_with_agent Mode #527

New Issue
Open
opened 2026-02-16 00:18:09 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:18:09 -05:00
Owner
Copy Link
Copy Source

Originally created by @Dhanush-klm on GitHub (Sep 1, 2025).

Error Details

  • Error Code: DOCUMENT_TOO_LARGE
  • Error Message: "Job would parse 999 out of 999 pages in document, max pages allowed for parse mode parse_page_with_agent is 700"
  • Job ID:`c7f0ca53-eaee-4e6c-a1ea-8991f0443c74
  • Parse Mode:parse_page_with_agent
  • Current Limit: 700 pages
  • Required Limit: At least 999+ pages

Problem Description
Our application is encountering a critical limitation when processing large documents through LlamaCloud's parse_page_with_agent mode. We have a document with 999 pages that needs to be processed, but the current page limit of 700 pages is preventing us from completing the job.

Impact:

  • Cannot process documents larger than 700 pages
  • Business-critical documents are being rejected
  • Need to either split documents (which may affect parsing quality) or find alternative solutions

Technical Context
We're using the LlamaParseReader with the following configuration:

parse_mode: "parse_page_with_agent"

This mode is essential for our use case as we need:

  • Intelligent document parsing with agent-based understanding
  • Proper table extraction and conversion
  • Structured content processing
  • High-quality text extraction

Requested Solution
We need one of the following options:

  1. Increase Page Limit:Extend the parse_page_with_agent mode limit from 700 to at least 1000+ pages
  2. Alternative Mode:Provide a high-capacity parsing mode that maintains similar quality
  3. Tiered Limits: Implement different page limits based on subscription tiers
  4. Document Chunking: Provide guidance on how to properly split large documents while maintaining parsing quality

Business Justification

  • Processing large documents (800-1000+ pages) is a core requirement
  • Current limitation is blocking production workflows
  • Alternative parsing modes may not provide the same quality for complex documents
  • Need for consistent parsing quality across document sizes

Additional Information

  • Platform: DataLoom (LlamaCloud integration)
  • Use Case: Document processing and content extraction
  • Document Types: PDFs, Word documents, and other formats
  • Processing Requirements: High-quality text extraction with table conversion

Contact Information

  • Name: Dhanush Ramasamy
  • Platform: DataLoom
  • Job Record ID: c7f0ca53-eaee-4e6c-a1ea-8991f0443c74
Originally created by @Dhanush-klm on GitHub (Sep 1, 2025). Error Details - Error Code: `DOCUMENT_TOO_LARGE` - Error Message: "Job would parse 999 out of 999 pages in document, max pages allowed for parse mode parse_page_with_agent is 700" - Job ID:`c7f0ca53-eaee-4e6c-a1ea-8991f0443c74 - Parse Mode:`parse_page_with_agent` - Current Limit: 700 pages - Required Limit: At least 999+ pages --- Problem Description Our application is encountering a critical limitation when processing large documents through LlamaCloud's `parse_page_with_agent` mode. We have a document with 999 pages that needs to be processed, but the current page limit of 700 pages is preventing us from completing the job. Impact: - Cannot process documents larger than 700 pages - Business-critical documents are being rejected - Need to either split documents (which may affect parsing quality) or find alternative solutions --- Technical Context We're using the LlamaParseReader with the following configuration: ```typescript parse_mode: "parse_page_with_agent" ``` This mode is essential for our use case as we need: - Intelligent document parsing with agent-based understanding - Proper table extraction and conversion - Structured content processing - High-quality text extraction --- Requested Solution We need one of the following options: 1. Increase Page Limit:Extend the `parse_page_with_agent` mode limit from 700 to at least 1000+ pages 2. Alternative Mode:Provide a high-capacity parsing mode that maintains similar quality 3. Tiered Limits: Implement different page limits based on subscription tiers 4. Document Chunking: Provide guidance on how to properly split large documents while maintaining parsing quality --- Business Justification - Processing large documents (800-1000+ pages) is a core requirement - Current limitation is blocking production workflows - Alternative parsing modes may not provide the same quality for complex documents - Need for consistent parsing quality across document sizes --- Additional Information - Platform: DataLoom (LlamaCloud integration) - Use Case: Document processing and content extraction - Document Types: PDFs, Word documents, and other formats - Processing Requirements: High-quality text extraction with table conversion --- Contact Information - Name: Dhanush Ramasamy - Platform: DataLoom - Job Record ID: c7f0ca53-eaee-4e6c-a1ea-8991f0443c74 ---
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#527
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?