# Pydantic AI | Sentry for Python

##### Beta

The support for **Pydantic AI** is in beta. Please test locally before using in production.

This integration connects Sentry with the [Pydantic AI](https://ai.pydantic.dev/) library. The integration has been confirmed to work with Pydantic AI version 1.0.0+.

Once you've installed this integration, you can use [Sentry AI Agents Insights](https://sentry.io/orgredirect/organizations/:orgslug/insights/ai/agents/), a Sentry dashboard that helps you understand what's going on with your AI agents.

Sentry AI Agents monitoring will automatically collect information about agents, tools, prompts, tokens, and models.

## [Install](https://docs.sentry.io/platforms/python/integrations/pydantic-ai.md#install)

Install `sentry-sdk` from PyPI:

```bash
pip install "sentry-sdk"
```

## [Configure](https://docs.sentry.io/platforms/python/integrations/pydantic-ai.md#configure)

Add `PydanticAIIntegration()` to your `integrations` list:

```python
import sentry_sdk
from sentry_sdk.integrations.pydantic_ai import PydanticAIIntegration
from sentry_sdk.integrations.openai import OpenAIIntegration

sentry_sdk.init(
    dsn="https://examplePublicKey@o0.ingest.sentry.io/0",
    traces_sample_rate=1.0,
    # Add data like LLM and tool inputs/outputs;
    # see https://docs.sentry.io/platforms/python/data-management/data-collected/ for more info
    send_default_pii=True,
    integrations=[
        PydanticAIIntegration(),
    ],
    # Disable the OpenAI integration to avoid double reporting of chat spans
    disabled_integrations=[OpenAIIntegration()],
)
```

When using Pydantic AI with OpenAI models, you must disable the OpenAI integration to avoid double reporting of chat spans. Add `disabled_integrations=[OpenAIIntegration()]` to your `sentry_sdk.init()` call as shown in the OpenAI tab above.

## [Verify](https://docs.sentry.io/platforms/python/integrations/pydantic-ai.md#verify)

Verify that the integration works by running an AI agent. The resulting data should show up in your AI Agents Insights dashboard. In this example, we're creating a customer support agent that analyzes customer inquiries and can optionally look up order information using a tool.

```python
import asyncio

import sentry_sdk
from sentry_sdk.integrations.pydantic_ai import PydanticAIIntegration
from sentry_sdk.integrations.openai import OpenAIIntegration
from pydantic_ai import Agent, RunContext
from pydantic import BaseModel

class SupportResponse(BaseModel):
    message: str
    sentiment: str
    requires_escalation: bool

support_agent = Agent(
    'openai:gpt-4o-mini',
    name="Customer Support Agent",
    system_prompt=(
        "You are a helpful customer support agent. Analyze customer inquiries, "
        "provide helpful responses, and determine if escalation is needed. "
        "If the customer mentions an order number, use the lookup tool to get details."
    ),
    result_type=SupportResponse,
)

@support_agent.tool
async def lookup_order(ctx: RunContext[None], order_id: str) -> dict:
    """Look up order details by order ID.
    
    Args:
        ctx: The context object.
        order_id: The order identifier.
    
    Returns:
        Order details including status and tracking.
    """
    # In a real application, this would query a database
    return {
        "order_id": order_id,
        "status": "shipped",
        "tracking_number": "1Z999AA10123456784",
        "estimated_delivery": "2024-03-15"
    }

async def main() -> None:
    sentry_sdk.init(
        dsn="https://examplePublicKey@o0.ingest.sentry.io/0",
        traces_sample_rate=1.0,
        # Add data like LLM and tool inputs/outputs;
        # see https://docs.sentry.io/platforms/python/data-management/data-collected/ for more info
        send_default_pii=True,
        integrations=[
            PydanticAIIntegration(),
        ],
        # Disable the OpenAI integration to avoid double reporting of chat spans
        disabled_integrations=[OpenAIIntegration()],
    )

    result = await support_agent.run(
        "Hi, I'm wondering about my order #ORD-12345. When will it arrive?"
    )
    print(result.data)

if __name__ == "__main__":
    asyncio.run(main())
```

It may take a couple of moments for the data to appear in [sentry.io](https://sentry.io).

## [Behavior](https://docs.sentry.io/platforms/python/integrations/pydantic-ai.md#behavior)

Data on the following will be collected:

* AI agents invocations
* execution of tools
* number of input and output tokens used
* LLM models usage
* model settings (temperature, max\_tokens, etc.)

Sentry considers LLM and tool inputs/outputs as PII and doesn't include PII data by default. If you want to include the data, set `send_default_pii=True` in the `sentry_sdk.init()` call. To explicitly exclude prompts and outputs despite `send_default_pii=True`, configure the integration with `include_prompts=False` as shown in the Options section below.

## [Options](https://docs.sentry.io/platforms/python/integrations/pydantic-ai.md#options)

By adding `PydanticAIIntegration` to your `sentry_sdk.init()` call explicitly, you can set options for `PydanticAIIntegration` to change its behavior:

```python
import sentry_sdk
from sentry_sdk.integrations.pydantic_ai import PydanticAIIntegration

sentry_sdk.init(
    # ...
    # Add data like inputs and responses;
    # see https://docs.sentry.io/platforms/python/data-management/data-collected/ for more info
    send_default_pii=True,
    integrations=[
        PydanticAIIntegration(
            include_prompts=False,  # LLM and tool inputs/outputs will be not sent to Sentry, despite send_default_pii=True
        ),
    ],
)
```

You can pass the following keyword arguments to `PydanticAIIntegration()`:

* `include_prompts`:

  Whether LLM and tool inputs and outputs should be sent to Sentry. Sentry considers this data personal identifiable data (PII) by default. If you want to include the data, set `send_default_pii=True` in the `sentry_sdk.init()` call. To explicitly exclude prompts and outputs despite `send_default_pii=True`, configure the integration with `include_prompts=False`.

  The default is `True`.

## [Supported Versions](https://docs.sentry.io/platforms/python/integrations/pydantic-ai.md#supported-versions)

* Pydantic AI: 1.0.0+
* Python: 3.9+