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

# Introduction

> The Python AI SDK is a pure Python re-implementation of Vercel's popular AI SDK for TypeScript.

## Why another SDK?

Python is the defacto language for AI. However, to actually get started with AI, you'll need to 1. use a bloated external framework and install a bunch of dependencies, or 2. use an incredibly confusing API client (to simply call an LLM, you need `client.chat.completions.create(**kwargs).result.choices[0].message.content`).

### Features

* Zero-configuration functions that work consistently across providers.
* First-class **streaming** & **tool-calling** support.
* <strong>Strong Pydantic types</strong> throughout - you know exactly what you're getting.
* <strong>Strict</strong> structured-output generation and streaming via Pydantic models.
* Provider-agnostic embeddings with built-in batching & retry logic.
* Tiny dependency footprint - no bloated external frameworks.

## Installation

```bash theme={null}
pip install ai-sdk-python
# or
uv add ai-sdk-python
```

That's it - no extra build steps or config files.

## Quick-start

Get started in just a few lines of code.

```python generate_text.py lines icon="python" theme={null}
from ai_sdk import openai, generate_text

res = generate_text(
  model=openai("gpt-4.1"),
  prompt="Tell me a haiku about Python",
)

print(res.text)
```

## What's next?

<CardGroup cols={2}>
  <Card title="Text generation" href="/ai-sdk/text-generation" icon="comment-dots">
    Generate or stream text with a single line of code.
  </Card>

  <Card title="Tool calling" href="/ai-sdk/tool-calling" icon="hammer">
    Build agentic flows with real Python functions.
  </Card>

  <Card title="Agent" href="/ai-sdk/agent" icon="robot">
    Create AI agents with persistent state and tool-calling capabilities.
  </Card>

  <Card title="Embeddings" href="/ai-sdk/embeddings" icon="vector-circle">
    Create vector embeddings and compute cosine similarity.
  </Card>

  <Card title="Structured output" href="/ai-sdk/object-generation" icon="boxes-packing">
    Return fully-validated Pydantic objects - no messy JSON parsing.
  </Card>
</CardGroup>