LaunchKit · 2026
Back to Skills

azure-doc-ocr

Extract text and structured data from documents using Azure Document Intelligence (formerly Form Recognizer).

0
349 downloads
by @li-hongmin

Setup & Installation

openclaw skills install @li-hongmin/azure-doc-ocr

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install azure-doc-ocr

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

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: extract structured data from invoice.pdf

AGENT
  1. 1Set AZURE_DOC_INTEL_ENDPOINT and AZURE_DOC_INTEL_KEY environment variables
  2. 2Run ocr_extract.py with --model prebuilt-invoice and --format json
  3. 3API submits document to Azure Document Intelligence REST endpoint
  4. 4Poll for analysis result and receive structured JSON response
  5. 5Write output to invoice_data.json
OUTPUT

JSON file containing vendor info, line items, totals, and dates extracted from the invoice

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

AZURE_DOC_INTEL_ENDPOINT environment variableAZURE_DOC_INTEL_KEY environment variableAzure account with Document Intelligence resource