What's new#
Summarization now offers an optional full-page image mode that includes the entire page layout when generating summaries. Previously, summaries were always scoped to individual page fragments. Now you can choose between fragment-level or full-page summarization based on your document complexity.
Why it matters#
- Complex layouts (multi-column documents, forms) benefit from spatial context
- Fragment-only summaries can miss relationships between spatially separated content
- Hallucination reduction - some documents make more sense with full page context
- Flexibility - you control the summarization scope based on document type
Highlights#
- Toggle between fragment-scoped and full-page summarization
- Preserves spatial relationships in complex layouts
- Better handling of forms, insurance claims, technical diagrams
- Maintains existing fragment-level behavior as default (no breaking changes)
How to use#
Enable full-page summaries through the summarization configuration:
1doc_ai = DocumentAI()
2
3result = doc_ai.parse_and_wait(
4 file="complex_form.pdf",
5 summarization_config={
6 "include_full_page_image": True # New option
7 }
8)
9
10for page in result.pages:
11 for fragment in page.page_fragments:
12 summary = fragment.summary # Now includes full-page contextWhen to use full-page mode#
- Multi-column layouts where fragments span columns
- Forms where field relationships matter spatially
- Technical documents with diagrams and callouts
- Insurance claims with signature placement requirements
Status#
✅ Live now in the API. Default behavior unchanged (fragment-level summaries).
Try it with this colab notebook