Observability for Pydantic AI with Opik

Pydantic AI is a Python agent framework designed to build production grade applications with Generative AI.

Pydantic AI’s primary advantage is its integration of Pydantic’s type-safe data validation, ensuring structured and reliable responses in AI applications.

Account Setup

Comet provides a hosted version of the Opik platform, simply create an account and grab your API Key.

You can also run the Opik platform locally, see the installation guide for more information.

Getting Started

Installation

To use the Pydantic AI integration with Opik, you will need to have Pydantic AI and logfire installed:

$
pip install --upgrade pydantic-ai logfire 'logfire[httpx]'

Configuring Pydantic AI

In order to use Pydantic AI, you will need to configure your LLM provider API keys. For this example, we’ll use OpenAI. You can find or create your API keys in these pages:

You can set them as environment variables:

$
export OPENAI_API_KEY="YOUR_API_KEY"

Or set them programmatically:

1
import os
2
import getpass
3
4
if "OPENAI_API_KEY" not in os.environ:
5
    os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter your OpenAI API key: ")

Configuring OpenTelemetry

You will need to set the following environment variables to make sure the data is logged to Opik:

$
export OTEL_EXPORTER_OTLP_ENDPOINT=https://www.comet.com/opik/api/v1/private/otel
$
export OTEL_EXPORTER_OTLP_HEADERS='Authorization=<your-api-key>,Comet-Workspace=default'
$
export OTEL_METRICS_EXPORTER=none

$
export OTEL_EXPORTER_OTLP_HEADERS='Authorization=<your-api-key>,Comet-Workspace=default,projectName=<your-project-name>'

Using Opik with Pydantic AI

To track your Pydantic AI agents, you will need to configure logfire as this is the framework used by Pydantic AI to enable tracing.

1
import logfire
2
3
logfire.configure(
4
    send_to_logfire=False,
5
)
6
logfire.instrument_pydantic_ai()

Practical Example

Now that everything is configured, you can create and run Pydantic AI agents:

1
import nest_asyncio
2
from pydantic_ai import Agent
3
4
# Enable async support in Jupyter notebooks
5
nest_asyncio.apply()
6
7
# Create a simple agent
8
agent = Agent(
9
    "openai:gpt-4o",
10
    system_prompt="Be concise, reply with one sentence.",
11
)
12
13
# Run the agent
14
result = agent.run_sync('Where does "hello world" come from?')
15
print(result.data)

Logging threads

You can group multiple agent calls into a conversation thread by setting thread_id as a span attribute on the root Logfire span. Opik’s OTEL ingestion recognizes this attribute and maps it directly to the trace’s thread_id field:

1
# Logfire wraps OTEL - thread_id becomes a span attribute automatically
2
with logfire.span("chat_turn", thread_id=thread_id):
3
    result = agent.run_sync("What is machine learning?")

Further improvements

If you would like to see us improve this integration, simply open a new feature request on Github.