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

# Python quick start

> Install lighton-sdk and get your first grounded answer.

[`lighton-sdk`](https://github.com/lightonai/lighton-python-sdk) wraps the LightOn API: typed models, pagination handled for you, and rate-limit pacing built in. It's the code shown in the **Python SDK** tab of every tutorial snippet.

<Tip>
  Requires Python 3.11 or later.
</Tip>

## Install

```bash theme={null}
uv add lighton-sdk
```

Set your API key in the environment. `LightOn()` reads it from there, so it never appears in your code:

```bash theme={null}
export LIGHTON_API_KEY="..."
```

## Your first result

```python theme={null}
from lighton import LightOn, Workspace

with LightOn() as client:  # reads LIGHTON_API_KEY from the environment
    workspace = Workspace(name="Docs").create(client)
    workspace.ingest_many(["docs/**/*.pdf"], wait=True)

    answer = client.ask("What were Q4 revenues?", workspaces=[workspace])
    print(answer.answer)
```

## Where to go next

<Columns cols={2}>
  <Card title="API reference" icon="code" href="/sdks/python/reference">
    Every public class, method, and type, generated from the installed SDK.
  </Card>

  <Card title="Tutorials" icon="graduation-cap" href="/tutorials/index">
    Task-by-task walkthroughs, each with a **Python SDK** tab.
  </Card>
</Columns>

For `parse`, `extract`, async jobs, and agent-framework integrations (LangChain, LangGraph, LlamaIndex, OpenAI Agents, CrewAI), see the [SDK README](https://github.com/lightonai/lighton-python-sdk#readme).