> ## Documentation Index
> Fetch the complete documentation index at: https://docs.unstructured.io/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> ## Agent quick links and documentation index
> Fetch key links about the MCP server, SDK, and API at: https://docs.unstructured.io/agent-guide.md
> Then fetch the complete documentation index at: https://docs.unstructured.io/llms.txt
> Use these two files to discover all available pages before exploring further.

# SDK & API overview

> Unstructured offers an SDK and a REST API that enable you to programmatically automate Unstructured.

<Tip>
  Start calling the Unstructured API right now with the [quickstart](/api-reference/quickstart/overview)!
</Tip>

```mermaid theme={null}
%%{init: {"theme": "base", "themeVariables": { "background": "#26c6ff", "primaryColor": "#26c6ff", "lineColor": "#26c6ff" }}}%%
flowchart LR
    A["Unstructured Python SDK"] --> C["Unstructured API"]
    B["Unstructured REST API"] --> C
    C --> D["Unstructured services"]
    click A href "https://docs.unstructured.io/overview-python-sdk"
    click B href "https://docs.unstructured.io/overview-rest-api"
    click C href "https://docs.unstructured.io/api-reference/overview"
```

## Key takeaways

* The [Unstructured Python SDK](/overview-python-sdk) enables you to call the Unstructured API with Python.
* The [Unstructured REST API](/overview-rest-api) enables you to call the Unstructured API with a REST client, such as cURL or Postman.
* The [Unstructured API](/api-reference/overview) provides a set of programmatic operations that automate Unstructured.
* Unstructured services, such as those that power [Unstructured Transform](/transform/overview) and [Unstructured Pipelines](/pipelines/overview), do things such as:

  * Perform a full range of partitioning, enrichment, chunking, and embedding of your files and data, producing results that are AI-ready.
  * Batch-process files locally.
  * Batch-process files and data that are stored in remote storage locations, databases, and vector stores.
  * Retrieve batch-processed local file results locally.
  * Send batch-processed remote file or data results to remote storage locations, databases, and vector stores.
  * Use the latest and highest-performing models.

## Next steps

<CardGroup cols={2}>
  <Card title="Python SDK" icon="python" href="/overview-python-sdk">
    Get started with the Unstructured Python SDK.
  </Card>

  <Card title="REST API" icon="terminal" href="/overview-rest-api">
    Get started with the Unstructured REST API.
  </Card>

  <Card title="Samples and reference" icon="code" href="/api-reference/api">
    Get code samples for Python and cURL, along with the full API reference.
  </Card>
</CardGroup>