azure-ai-formrecognizer-java

Extract text, tables, and key-value pairs from documents using Java.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/davidrrowley/CortexYouV3 --skill azure-ai-formrecognizer-java-davidrrowley
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: azure-ai-formrecognizer-java
Source: https://github.com/davidrrowley/CortexYouV3/tree/main/.agents/skills/azure-ai-formrecognizer-java
Command: npx skills add https://github.com/davidrrowley/CortexYouV3 --skill azure-ai-formrecognizer-java-davidrrowley

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates manual data extraction from documents by providing Java patterns and guidance to extract text, tables, key/value pairs, and classification labels from PDFs, images, receipts, invoices, and ID documents so developers can automate document ingestion and downstream workflows.

Core Features & Use Cases

  • Prebuilt model usage: Use prebuilt models for layout, receipts, invoices, business cards and ID documents to quickly extract common fields.
  • Custom model training and composition: Build, compose, and manage custom document models for specialized invoice or form layouts and classify mixed document sets.
  • Programmatic analysis: Patterns for synchronous polling, URL and binary analysis, table parsing, and field confidence checks integrated into Java applications.
  • Production considerations: Guidance for authentication with API key or managed identities, model lifecycle operations, and basic HTTP error handling and retries.

Quick Start

Analyze an invoice URL with the Java Azure Document Intelligence SDK to extract merchant, date, line items, and totals into structured fields.

Frequently Asked Questions about azure-ai-formrecognizer-java

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text and tables from a PDF invoice in Java?

You can extract structured text and tables from PDFs in Java using Azure Document Intelligence prebuilt models for invoices to parse line items and totals. Apply synchronous polling to analyze document URLs or binary data directly within your application.

Can I train custom document models for specialized forms using Java?

Yes, you can train custom document models in Java to classify mixed document sets and extract fields from specialized invoice layouts. The SDK supports model composition, lifecycle administration, and custom classification for varied form structures.

Does Azure Document Intelligence work with Java for receipt and ID document extraction?

Azure Document Intelligence works with Java to extract structured data from receipts and ID documents using prebuilt models. These models parse common fields from images and PDFs without requiring custom model training, simplifying ingestion workflows.

How do I authenticate a Java application with Azure Document Intelligence?

Authenticate a Java application with Azure Document Intelligence using an API key or managed identities. Configure client builders with Azure credentials to securely access prebuilt and custom models for document analysis and field extraction.

What are the limitations of synchronous polling for document analysis in Java?

Synchronous polling for document analysis in Java blocks execution until the operation completes, potentially impacting throughput for large document batches. Implement basic HTTP error handling and retries to manage network timeouts and processing delays safely.

When do I need custom models versus prebuilt models for document extraction in Java?

Use prebuilt models in Java for standard invoices and IDs to quickly extract common fields. Train custom models when processing specialized invoice layouts or classifying mixed document collections with unique, non-standard form structures.