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

# 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

<CodeGroup>
  ```shell Shell theme={null}
  pip install pydantic-ai -q
  ```
</CodeGroup>

Set your Neosantara AI API key:

<CodeGroup>
  ```shell Shell theme={null}
  export NAI_API_KEY=***
  ```
</CodeGroup>

## Example

<CodeGroup>
  ```python Python theme={null}
  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)
  ```
</CodeGroup>

### Output

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