intelligent-document-processing

AI-enabled Intelligent Document Processing for Python: 12+ LLM backends, Pydantic schemas, self-hosted OCR (Nanonets-OCR2-3B), auto-schema discovery, HITL review, prod FastAPI server. AGPL-3.0 + commercial.

Open-source document management platform leveraging AWS managed services. RESTful API for document storage, processing, full-text search, and metadata management. Multi-tenant serverless architecture with auto-scaling... deployed entirely in your AWS account.

Open-source toolkit to extract structured knowledge graphs from documents and tables — power analytics, digital twins, and AI-driven assistants.

A Python framework for multi-modal document understanding with Amazon Bedrock

End-to-end Intelligent Document Processing (IDP) pipeline using Amazon Bedrock, LanceDB, Lambda, Strands Agents, and Step Functions. Supports multimodal document analysis for PDFs, images, videos, and audio.

This repository contains examples for customers to get started using Amazon Bedrock Data Automation. The samples focus mainly on document processing use cases

GDocz by Gramosoft is an open-source Intelligent Document Processing platform that turns raw PDFs and images into clean, structured JSON — powered by multi-engine OCR and AI-driven schema extraction.

Open-source invoice-to-pay agent for AP automation: OCR/VLM extraction, 3-way matching, approvals, fraud checks, ERP mock posting, evals, and audit logs.

NeuroDoc is a powerful AI-based offline document summarization tool that leverages OCR and NLP to intelligently analyze PDFs and generate structured summaries. Built using Flask, this tool is designed to run completely offline and supports both text-based and scanned/image-based documents.

This open-source project provides a serverless solution for automated identity document processing (IDP) using Amazon Bedrock's Claude-3 model. The solution creates an end-to-end pipeline that processes identity documents, particularly optimized for birth certificates, by automatically extracting relevant information.

AI-powered Form Response Extractor for paper forms, scanned documents, PDFs, and images. Convert handwritten and printed forms into structured JSON using OpenAI, Anthropic, Ollama, and SurveyJS Form Library. Open-source alternative to enterprise IDP tools like Rossum or FlexiCapture.

An end-to-end serverless pipeline for Intelligent Document Processing (IDP) using Amazon Bedrock and Anthropic Claude 3 Sonnet. This project extracts structured data from scanned documents (e.g., PDFs, forms, invoices) using GenAI models, and stores results in a scalable cloud-native architecture.

AI-powered Gov. ID classifier using OCR, BERT, ResNet, and LayoutLMv3 for Aadhar, PAN, Passport, and other scanned IDs.

Boilerplate CSS that can be used with any Grooper DataModel

AI-powered Intelligent Document Processing (IDP) system with RAG, anomaly detection, and natural language insights. Local, zero-cost alternative to AWS Textract + Bedrock.

Single-file Python library for scanned-document extraction: measured page quality drives adaptive preprocessing, pluggable OCR/VLM backends, schema-driven extraction with bbox provenance, calibrated confidence, and an eval harness. Zero required dependencies.

Leveraging the Robocorp integration to analyse customer feedback

Open-source Intelligent Document Processing (IDP) for accounting paperwork - Tesseract OCR, confidence scoring, page-quality checks, automatic document assembly and filing, with human-in-the-loop review and SharePoint integration.

Affinda — independent third-party profile of a public API surface, by API Evangelist. Affinda is an Intelligent Document Processing (IDP) platform that uses AI to extract structured data from documents — resumes, invoices, receipts, contracts, passports, IDs, and custom document types.

this repo contains repo for AWS BedRock DataAutomation.