September 10, 2025

Summaries now include optional full-page image context

Optionally reference the full-page during figure and table summarization to preserve spatial context in complex layouts.

Key Highlights

Full-page image context for better spatial relationship understanding
Reduces hallucinations in multi-column and form-based documents
Optional setting - maintains existing fragment-level behavior as default

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:

1[.code-block-title]Code[.code-block-title]doc_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 context

When 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

Get server-less runtime for agents and data ingestion

Data ingestion like never before.

TRY TENSORLAKE

REQUEST A DEMO

TRUSTED BY PRO DEVS GLOBALLY

Tensorlake is the Agentic Compute Runtime the durable serverless platform that runs Agents at scale.

"At SIXT, we're building AI-powered experiences for millions of customers while managing the complexity of enterprise-scale data. TensorLake gives us the foundation we need—reliable document ingestion that runs securely in our VPC to power our generative AI initiatives."

Boyan Dimitrov

CTO, Sixt

“Tensorlake enabled us to avoid building and operating an in-house OCR pipeline by providing a robust, scalable OCR and document ingestion layer with excellent accuracy and feature coverage. Ongoing improvements to the platform, combined with strong technical support, make it a dependable foundation for our scientific document workflows.”

Yaroslav Sklabinskyi

CEO, Reliant AI

"For BindHQ customers, the integration with Tensorlake represents a shift from manual data handling to intelligent automation, helping insurance businesses operate with greater precision, and responsiveness across a variety of transactions"

Cristian Joe

CEO @ BindHQ

“Tensorlake let us ship faster and stay reliable from day one. Complex stateful AI workloads that used to require serious infra engineering are now just long-running functions. As we scale, that means we can stay lean—building product, not managing infrastructure.”

Arpan Bhattacharya

Founder & CEO @ The Intelligent Search Company