SDK Integration

Integrate a Classification model using the Mindee SDKs.

Use the SDKs to send documents to a Classification model and process the results.

This section helps you choose the right starting point and move through the full integration flow.

Choose your path

Start with the page that matches your next step:

• Classification Quick Start ⇒ install a client library, send a file, and get your first result.
• Classification Result ⇒ access the predicted class and optional chained extraction result.
• Classification Model Overview ⇒ understand how Classification models assign a class to a document.

Typical SDK workflow

1

Create Your Model

Create your Classification Model on the Mindee platform.

Upload some samples to the Live Test to validate the model.

2

Install and authenticate

Install the client library for your language.

Prepare your API key and initialize the client.

3

Send a document

Set the Classification model's ID and send a file or URL for processing.

Start with polling unless you already use webhooks.

4

Process the classification result

Read the predicted class from the response.

Use the returned document type to route the document in your workflow.

Before you start

Have these ready:

• your API key
• your Classification Model's unique ID
• a sample document for testing
• a language choice for the SDK

What is specific to Classification models

Classification responses describe the class predicted for the whole document.

The classifier looks at all pages in the file before assigning a document type.

Document types are returned exactly as configured on the platform.

If extraction chaining is enabled, the classification result can also include an extraction response.

Shared SDK building blocks

Integration builds on the same client library concepts used across all model types.

• Client Libraries / SDKs
• Client Configuration
• Send a File or URL
• Response Processing
• Webhook Results
• Error Handling