azure-doc-ocr
by li-hongmin
DevOps & CloudBrief
Extract text and structured data from documents using Azure Document Intelligence (formerly Form Recognizer).
Description
What This Skill Does
Extracts text and structured data from documents using Azure Document Intelligence REST API v4.0. Supports PDFs, images, scanned documents, handwritten text, CJK languages, tables, forms, invoices, receipts, ID documents, and tax forms via prebuilt models.
Prebuilt models for invoices, receipts, IDs, and tax forms return structured fields directly without needing custom model training.
When to Use It
- Extract line items and totals from invoice PDFs
- Batch OCR a folder of scanned contracts
- Parse ID documents or passports for identity fields
- Pull table data from structured reports into markdown
- Recognize handwritten notes in mixed-language documents
Example Workflow
User asks: extract structured data from invoice.pdf
- 1
Set AZURE_DOC_INTEL_ENDPOINT and AZURE_DOC_INTEL_KEY environment variables
- 2
Run ocr_extract.py with --model prebuilt-invoice and --format json
- 3
API submits document to Azure Document Intelligence REST endpoint
- 4
Poll for analysis result and receive structured JSON response
- 5
Write output to invoice_data.json
JSON file containing vendor info, line items, totals, and dates extracted from the invoice
Requirements
- AZURE_DOC_INTEL_ENDPOINT environment variable
- AZURE_DOC_INTEL_KEY environment variable
- Azure account with Document Intelligence resource
Installation
clawhub install li-hongmin/azure-doc-ocrRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.