The repository contains samples and Community Samples that demonstrate how to analyze, classify and search documents using Google Cloud Document AI.

• Apps Script & Google Drive Integration: Code in Google Apps Script for integration with Document AI.
• Document AI Warehouse Processing (Python): This project demonstrates how to perform common actions on Document AI Warehouse through API.
• Document AI Warehouse Batch Ingestion via script: This project is a helper utility to do batch ingestion of the documents into the Document AI Warehouse.
• BQ Connector: This project uses the Document AI API to process a document, format the result and save it into a BigQuery table.
• Content Moderation with Dialogflow CX: This project uses the Content Moderation processor with Dialogflow CX for toxicity routing during a conversation.
• Filter HITL Language: This project uses the languages detected by Document AI (post-HITL) to sort the Document.json files into separate Cloud Storage buckets.
• Fraud Detection: This project uses the Document AI Invoice Parser with EKG and Google Maps to store document Entities in BigQuery.
• JSON Explorer: A React Tool to explore the Document JSON Response.
• Language Extraction: This project uses the Document AI API to detect the languages in a multi-page document.
• Paper Summarization: This project uses the Document AI API to summarize scientific articles.
• PDF Embedded Text: Demonstrates how to use the Native PDF parsing feature for the OCR Processor (v1beta3)
• SQL over Docs: This project shows how to run a BigQuery SQL and extract information from documents.
• Tax Processing Pipeline: This project uses the Document AI API to classify, parse, and calculate a tax form using multiple document types.
• Web App Demo: This project is a full-stack application that uses Document AI to process different types of documents. This application currently supports Form, Invoice and OCR processors.

• Document AI Sheets Plugin
• Document AI Intake Accelerator

Replaced by Document AI Toolbox

• PDF Splitter: This project uses the Document AI API to split PDF documents.
• Tabular Data Extraction: This project uses the Document AI API to extract tabular data from a document.

If you need Document Files to run the samples, you can access them from this publicly-accessible Google Cloud Storage Bucket.

gs://cloud-samples-data/documentai/

You can also view sample input/output files by processor on the Sample Output page of the documentation.

• Optical Character Recognition (OCR) with Document AI (Python)
• Form Parsing with Document AI (Python)
• Specialized Processors with Document AI (Python)
• Managing Document AI processors (Python)

Disclaimer: Community samples are not officially maintained by Google.

• PDF Annotator Sample: This project uses the Document AI API to annotate PDF documents.

Contributions welcome! See the Contributing Guide.

Please use the issues page to provide feedback or submit a bug report.

This is not an officially supported Google product. The code in this repository is for demonstrative purposes only.