본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

azure-doc-ocr

li-hongmin 제작

DevOps & Cloud
349clawskills.sh가 보고한 다운로드 수
1조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

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

설명

이 스킬이 하는 일

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.

사용 시점

  • 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

예시 워크플로

입력

User asks: extract structured data from invoice.pdf

에이전트
  1. 1

    Set AZURE_DOC_INTEL_ENDPOINT and AZURE_DOC_INTEL_KEY environment variables

  2. 2

    Run ocr_extract.py with --model prebuilt-invoice and --format json

  3. 3

    API submits document to Azure Document Intelligence REST endpoint

  4. 4

    Poll for analysis result and receive structured JSON response

  5. 5

    Write output to invoice_data.json

출력

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

요구 사항

  • AZURE_DOC_INTEL_ENDPOINT environment variable
  • AZURE_DOC_INTEL_KEY environment variable
  • Azure account with Document Intelligence resource

설치

clawhub install li-hongmin/azure-doc-ocr

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크