PydanticAI

Using PydanticAI with Neosantara.

PydanticAI is an agent framework created by the Pydantic team to simplify building production-grade generative AI applications. It brings the ergonomic design philosophy of FastAPI to AI agent development, offering a familiar and type-safe approach to working with language models.

Installing Libraries

Shell

pip install pydantic-ai -q

Set your Neosantara AI API key:

Shell

export NAI_API_KEY=***

Example

Python

from pydantic_ai import Agent
from pydantic_ai.models.openai import OpenAIChatModel
from pydantic_ai.providers.openai import OpenAIProvider

## Connect PydanticAI to LLMs on Neosantara
model = OpenAIChatModel(
    'nusantara-base',
    provider=OpenAIProvider(
        base_url="https://api.neosantara.xyz/v1",
        api_key=os.environ.get("NAI_API_KEY"),
    ),
)

## Setup the agent
agent = Agent(
    model,
    system_prompt='Be concise, reply with one sentence.',
)

result = agent.run_sync('Where does "hello world" come from?')  
print(result.output)

Output

It originated with Brian Kernighan's examples for the B programming language, later popularized in "The C Programming Language" book.