aws-samples/sample-for-multi-modal-document-to-json-with-sagemaker-ai

This open-source project delivers a complete pipeline for converting multi-page documents (PDFs/images) into structured JSON using Vision LLMs on Amazon SageMaker. The solution leverages the SWIFT Framework to fine-tune models specifically for document understanding tasks.

34
/ 100
Emerging

This project helps businesses automate the extraction of specific data from multi-page documents like invoices or contracts. You can feed it PDFs or images, and it will output the key information you need in a structured JSON format, ready for your systems. It's designed for data analysts, operations managers, or IT professionals who deal with large volumes of varied documents.

No commits in the last 6 months.

Use this if you need to reliably convert diverse, multi-page documents into structured data for automated processing, especially if your documents have high variation.

Not ideal if you only need simple, generic text extraction or if your documents are already highly structured and machine-readable.

document-processing invoice-automation data-extraction business-operations information-management
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

Jupyter Notebook

License

MIT-0

Last pushed

Aug 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/aws-samples/sample-for-multi-modal-document-to-json-with-sagemaker-ai"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.