The Python AI SDK

Zero-configuration functions that work consistently across providers with first-class streaming, tool-calling, and structured output support.

Welcome to the Python AI SDK

A pure Python re-implementation of Vercel’s popular AI SDK for TypeScript. Get started with AI in minutes, not hours.

Quick Start

Get up and running in under 5 minutes with our quick start guide.

Why the Python AI 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 Pydantic types throughout - you know exactly what you’re getting
• Strict structured-output generation and streaming via Pydantic models
• Provider-agnostic embeddings with built-in batching & retry logic
• Tiny dependency footprint - no bloated external frameworks

Quick Examples

Text Generation

from ai_sdk import generate_text, openai

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

Streaming

import asyncio
from ai_sdk import stream_text, openai

async def main():
    model = openai("gpt-4.1-mini")
    stream_res = stream_text(model=model, prompt="Write a story")

    async for chunk in stream_res.text_stream:
        print(chunk, end="", flush=True)

asyncio.run(main())

Structured Output

from ai_sdk import generate_object, openai
from pydantic import BaseModel

class Person(BaseModel):
    name: str
    age: int

model = openai("gpt-4.1-mini")
res = generate_object(
    model=model,
    schema=Person,
    prompt="Create a person named Alice, age 30"
)
print(res.object)  # Person(name='Alice', age=30)

Core Functions

Text Generation

Generate text synchronously with generate_text or stream in real-time with stream_text.

Object Generation

Parse model output directly into your own Pydantic models with automatic validation.

Embeddings

Create vector embeddings with embed and embed_many, plus semantic similarity with cosine_similarity.

Tools

Turn any Python function into an LLM-callable tool with a single decorator.

Supported Providers

OpenAI

GPT models, embeddings, and function calling with full streaming support.

Anthropic

Claude models with OpenAI-compatible API interface.

Installation

Install via UV (Python package manager):

uv add ai-sdk-python

Or with pip:

pip install ai-sdk-python

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

Key Benefits

1. Zero Configuration

No complex setup - just import and use:

from ai_sdk import generate_text, openai
res = generate_text(model=openai("gpt-4.1-mini"), prompt="Hello!")

2. Provider Agnostic

Swap providers without changing code:

# Works with any provider
model = openai("gpt-4.1-mini")  # or anthropic("claude-3-haiku-20240307")
res = generate_text(model=model, prompt="Hello!")

3. Strong Typing

Full Pydantic integration for type safety:

from pydantic import BaseModel
from ai_sdk import generate_object

class User(BaseModel):
    name: str
    age: int

res = generate_object(model=model, schema=User, prompt="Create a user")
user = res.object  # Fully typed User instance

4. Built-in Streaming

Real-time text generation:

async for chunk in stream_text(model=model, prompt="Tell a story").text_stream:
    print(chunk, end="", flush=True)

5. Automatic Tool Calling

Define tools once, use everywhere:

add = tool(name="add", description="Add numbers",
           parameters={...}, execute=lambda x, y: x + y)

res = generate_text(model=model, prompt="What's 2+2?", tools=[add])

Documentation Sections

Getting Started

Introduction

Learn about the SDK’s philosophy and core concepts.

Concepts

Understand the fundamental concepts and patterns.

Examples & Guides

Basic Text

Simple text generation examples.

Streaming

Real-time streaming examples.

Structured Output

Working with Pydantic models.

Tool Agent

Building agents with tool calling.

Embeddings Search

Semantic search with embeddings.

Reference

Text Generation

generate_text and stream_text functions.

Object Generation

generate_object and stream_object functions.

Embeddings

embed, embed_many, and cosine_similarity functions.

Tools

tool function for LLM-callable functions.

Providers

Supported AI providers and their features.

Types

Type definitions and schemas.

Community & Support

GitHub

View source code, report issues, and contribute.

PyPI

Install the package from PyPI.

Support

Get help with implementation questions.

---

The Python AI SDK is designed to be simple yet powerful. Start with the basics and gradually explore advanced features like tool calling and structured output.