# Document AI integrations: processors and documents

> Create a processor and create a schema in Document AI. Connect Document AI to the rest of your documents and e-signature stack with Tray.ai.

**Canonical page:** https://tray.ai/connectors/document-ai-integrations/
**Categories:** Documents and e-signature
**Connects through:** HTTP Connector

## Overview

Document AI is a Google Cloud service that reads scanned and digital documents and pulls out text, tables and fields using trained or custom processors. Tray.ai connects to Document AI through the HTTP Connector, so your workflows can call the Document AI API alongside the rest of your stack.

## Use cases

### Processors

Read, create, update, and delete processors in Document AI from any Tray.ai workflow. The Document AI API covers calls such as list processors and create a processor.

- List processors
- Create a processor
- Get a processor

### Documents

Manage documents in Document AI from any Tray.ai workflow. The Document AI API covers calls such as process a document and batch process documents.

- Process a document
- Batch process documents

### Processor versions

Read and manage processor versions in Document AI from any Tray.ai workflow. The Document AI API covers calls such as list processor versions and train a processor version.

- List processor versions
- Train a processor version
- Deploy a processor version

### Schemas

Read, create, update, and delete schemas in Document AI from any Tray.ai workflow. The Document AI API covers calls such as list schemas and create a schema.

- List schemas
- Create a schema
- Update a schema

### Operations

Read and delete operations in Document AI from any Tray.ai workflow. The Document AI API covers calls such as list operations and get an operation.

- List operations
- Get an operation
- Cancel an operation

## Challenges Tray.ai solves

### Keeping Document AI credentials out of logs

A raw API call usually means pasting a key or token into the request, where it ends up in step inputs, logs, and screenshots.

**How Tray.ai helps:** Store Document AI credentials once as a Tray.ai authentication and reference them from the HTTP Connector. Tray.ai masks authentication values in logs, so the secret never shows up in a step's input or output.

### Going from the Document AI API docs to a working call

Translating an example request from API docs into a workflow step means copying the method, URL, headers, and body by hand.

**How Tray.ai helps:** Paste a cURL example from the Document AI API docs into the HTTP Connector and Tray.ai fills in the method, URL, headers, and body for you.

### Handling files and non-JSON responses

Not every API answers in JSON. Some return XML, files, or binary data, or expect a multipart upload.

**How Tray.ai helps:** The HTTP Connector parses JSON and XML responses, returns files you can pass to the next step, and sends multipart form data for uploads.

## Frequently asked questions

### Does Tray.ai connect to Document AI?

Yes. Tray.ai connects to Document AI through the HTTP Connector, which calls the Document AI API directly. Any call the Document AI API documents can run as a step in a Tray.ai workflow.

### How does Tray.ai authenticate with Document AI?

The Document AI API uses OAuth 2.0. You save it once as a Tray.ai authentication, and the HTTP Connector adds it to every request.

### Can I get a dedicated Document AI connector?

Document AI runs through the HTTP Connector rather than a dedicated connector. If your team wants one, the Tray.ai connector SDK can build a dedicated Document AI connector from the Document AI API.

## Learn more

- Intelligent Integration: https://tray.ai/platform/intelligent-ipaas/
- Merlin Agent Builder: https://tray.ai/platform/merlin-agent-builder/
- Agent Gateway for MCP: https://tray.ai/platform/agent-gateway/
- Book a demo: https://tray.ai/contact/