google-document-ai-ocr

Extract text and structured entities from PDFs and scanned documents via OCR.

Updated Feb 24, 2026
One-click install
npx skills add https://github.com/AgentPMT/agent-skills --skill google-document-ai-ocr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google-document-ai-ocr
Source: https://github.com/AgentPMT/agent-skills/tree/main/skills/google-document-ai-ocr
Command: npx skills add https://github.com/AgentPMT/agent-skills --skill google-document-ai-ocr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the extraction of text and structured data from various document formats, eliminating the need for manual data entry and processing.

Core Features & Use Cases

  • OCR and Document Intelligence: Extracts text, structured entities (dates, amounts, names, addresses, line items), and per-page metadata from PDFs, images, and scanned documents.
  • Flexible Input: Accepts documents via base64 encoding, public URLs, or file storage IDs.
  • Use Case: Automatically process a batch of scanned invoices to extract key financial details and populate a database.

Quick Start

Use the google-document-ai-ocr skill to process the document located at the provided URL.

Frequently Asked Questions about google-document-ai-ocr

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

FAQPage Schema
How do I extract text and structured data from scanned invoices?

To extract text and structured data from scanned invoices, you can use an OCR Skill that processes base64 encoded files, public URLs, or file storage IDs to retrieve dates, amounts, names, addresses, and line items automatically.

What document formats are supported for OCR text extraction?

OCR text extraction supports PDFs, images, and scanned documents. You can provide these files for processing via base64 encoding, public URLs, or file storage IDs to retrieve both raw text and per-page metadata.

Can I automate invoice processing to extract financial details into a database?

Yes, you can automate invoice processing to extract key financial details and populate a database. The Skill performs Optical Character Recognition to pull structured entities like amounts and line items directly from your scanned documents.

How does document intelligence work for extracting entities like dates and addresses?

Document intelligence works for extracting entities by applying Optical Character Recognition to analyze documents and identify structured data such as dates, amounts, names, addresses, and line items alongside general text retrieval.

Does the OCR API require wallet signatures and credit management?

Yes, the OCR API requires wallet signatures and credit management for execution. You must manage these prerequisites to successfully run the external API for document processing and data extraction.

What is the best way to process a batch of PDFs for data extraction?

The best way to process a batch of PDFs for data extraction is to submit them via public URLs or file storage IDs to an automated OCR service, which outputs structured entities and per-page metadata without manual data entry.