Pydantic AI¶

Pydantic AI is a Python agent framework designed to build production-grade applications with Generative AI. It leverages Pydantic for data validation and type safety, ensuring structured and reliable interactions with LLMs.

Installation¶

First, install the pydantic-ai package.

pip install pydantic-ai

uv add pydantic-ai

You can then set the OVHCLOUD_API_KEY environment variable with our AI Endpoints API key.

Usage¶

Create a new file such as main.py and paste this code. You are ready in less than 5 lines of code!

from pydantic_ai import Agent

agent = Agent('ovhcloud:gpt-oss-120b')
result = agent.run_sync('What is the capital of France?')
print(result.output)

You get the following output: The capital of France is Paris..

If you need to configure the provider, you can use the OVHcloudProvider class:

from pydantic_ai import Agent
from pydantic_ai.models.openai import OpenAIChatModel
from pydantic_ai.providers.ovhcloud import OVHcloudProvider

model = OpenAIChatModel(
    'gpt-oss-120b',
    provider=OVHcloudProvider(api_key='your-api-key'),
)
agent = Agent(model)
result = agent.run_sync('What is the capital of France?')
print(result.output)

Going further¶

You can explore the Pydantic AI documentation to dive deeper into advanced features.

• Check out our Getting Started guide to learn more about OVHcloud AI Endpoints capabilities.
• Need support or want to chat? Join our community on Discord.
• Found a mistake or want to improve this guide? Feel free to open a Pull Request or Issue on GitHub.