> For the complete documentation index, see [llms.txt](https://docs.mindee.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mindee.com/extraction-models/sdk-integration.md).

# SDK Integration

Use the SDKs to send documents to an Extraction model and process dynamic 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:

* [Extraction Quick Start](/extraction-models/sdk-integration/quick-start.md) ⇒ install a client library, send a file, and get your first result.
* [Extraction Configuration](/extraction-models/sdk-integration/extraction-configuration.md) ⇒ set model-specific parameters and optional features.
* [Extraction Result Fields](/extraction-models/sdk-integration/extraction-result.md) ⇒ access dynamic fields and metadata in the SDK response.

### Typical SDK workflow

{% stepper %}
{% step %}

#### Create Your Model

[Create your Extraction Model](/extraction-models/extraction-models-overview.md#creating-from-scratch) on the Mindee platform.

Upload some samples to the [Live Test](/models/live-test.md) to validate the model.
{% endstep %}

{% step %}

#### Install and authenticate

Install the client library for your language.

Prepare your API key and initialize the client.
{% endstep %}

{% step %}

#### Send a document

Choose your model ID and send a file or URL for processing.

Start with polling unless you already use webhooks.
{% endstep %}

{% step %}

#### Process the results

Read extracted values from the response fields.

Handle field types based on your Data Schema.
{% endstep %}
{% endstepper %}

### Before you start

Have these ready:

* an API key
* your Extraction Model's unique ID
* a sample document for testing
* a language choice for the SDK

### What is specific to Extraction models

Extraction responses are dynamic.

Field names come from your model's Data Schema. Field types can be simple values, objects, or lists.

Optional metadata such as confidence scores and locations depends on which features are enabled for the request.

For better results, make sure your schema design is solid before tuning request-time options.

### Shared SDK building blocks

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

* [Client Libraries / SDKs](/integrations/client-libraries-sdk.md)
* [Client Configuration](/integrations/client-libraries-sdk/configure-the-client.md)
* [Send a File or URL](/integrations/client-libraries-sdk/send-a-file-or-url.md)
* [Response Processing](/integrations/client-libraries-sdk/process-the-response.md)
* [Webhook Results](/integrations/webhooks.md)
* [Error Handling](/integrations/problem-database.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.mindee.com/extraction-models/sdk-integration.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.