Trace PydanticAI agents

LangSmith can capture traces generated by PydanticAI using its built-in OpenTelemetry instrumentation. This guide shows you how to automatically capture traces from your PydanticAI agents and send them to LangSmith for monitoring and analysis.

In an agent-based workspace, create an agent once before sending traces. Use agent addressing to select its identifier and environment. If an integration requires project_name, use the selected environment’s tracer_session_name as a compatibility value.

Installation

Install the required packages:

pip install langsmith pydantic-ai opentelemetry-exporter-otlp

uv add langsmith pydantic-ai opentelemetry-exporter-otlp

Requires LangSmith Python SDK version langsmith>=0.4.26 for optimal OpenTelemetry support.

Setup

1. Configure environment variables

Set your API keys, agent identifier, and environment:

export LANGSMITH_API_KEY=<your_langsmith_api_key>
export LANGSMITH_AGENT_ID="<your-agent-id>"
export LANGSMITH_AGENT_ENVIRONMENT="local"
export OPENAI_API_KEY=<your_openai_api_key>

2. Configure OpenTelemetry integration

In your PydanticAI agent, configure the LangSmith OpenTelemetry integration:

from langsmith.integrations.otel import configure
from pydantic_ai import Agent

# Configure LangSmith tracing
configure()

# Instrument all PydanticAI agents
Agent.instrument_all()

You do not need to set any OpenTelemetry environment variables or configure exporters manually—configure() handles everything automatically.

3. Create and run your PydanticAI agent

Once configured, your PydanticAI agents will automatically send traces to LangSmith:

from langsmith.integrations.otel import configure
from pydantic_ai import Agent

# Configure LangSmith tracing
configure()

# Instrument all PydanticAI agents
Agent.instrument_all()

# Create and run an agent
agent = Agent('openai:gpt-6-luna')
result = agent.run_sync('What is the capital of France?')
print(result.output)
#> Paris

Advanced usage

Custom metadata and tags

You can add custom metadata to your traces using OpenTelemetry span attributes:

from opentelemetry import trace
from pydantic_ai import Agent
from langsmith.integrations.otel import configure

configure()
Agent.instrument_all()

tracer = trace.get_tracer(__name__)

agent = Agent('openai:gpt-6-luna')

with tracer.start_as_current_span("pydantic_ai_workflow") as span:
    span.set_attribute("langsmith.metadata.user_id", "user_123")
    span.set_attribute("langsmith.metadata.workflow_type", "question_answering")
    span.set_attribute("langsmith.span.tags", "pydantic-ai,production")

    result = agent.run_sync('Explain quantum computing in simple terms')
    print(result.output)

Connect these docs to your agent of choice via MCP for real-time answers.

Edit this page on GitHub or file an issue.

Tracing setup

Configuration & troubleshooting

Installation

Setup

1. Configure environment variables

2. Configure OpenTelemetry integration

3. Create and run your PydanticAI agent

Advanced usage

Custom metadata and tags

​Installation

​Setup

​1. Configure environment variables

​2. Configure OpenTelemetry integration

​3. Create and run your PydanticAI agent

​Advanced usage

​Custom metadata and tags

Installation

Setup

1. Configure environment variables

2. Configure OpenTelemetry integration

3. Create and run your PydanticAI agent

Advanced usage

Custom metadata and tags