OpenInference PydanticAI
Python auto-instrumentation library for PydanticAI. These traces are fully OpenTelemetry compatible and can be sent to an OpenTelemetry collector for viewing, such as Arize Phoenix or Arize AX.
Installation
pip install openinference-instrumentation-pydantic-ai
Requires Pydantic AI 2.24.0 or newer.
Quickstart
This quickstart shows you how to instrument your PydanticAI agents.
Install required packages.
pip install "pydantic-ai>=2.24.0" arize-phoenix opentelemetry-sdk opentelemetry-exporter-otlp
Start Phoenix in the background as a collector. By default, it listens on http://localhost:6006. You can visit the app via a browser at the same address. (Phoenix does not send data over the internet. It only operates locally on your machine.)
phoenix serve
Here's a simple example that demonstrates how to use PydanticAI with OpenInference instrumentation:
import os
from pydantic import BaseModel
from pydantic_ai import Agent
from pydantic_ai.models.instrumented import InstrumentationSettings
from pydantic_ai.models.openai import OpenAIModel
from pydantic_ai.providers.openai import OpenAIProvider
from opentelemetry import trace
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.trace import TracerProvider
from openinference.instrumentation.pydantic_ai import OpenInferenceSpanProcessor
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
# Set your OpenAI API key
os.environ["OPENAI_API_KEY"] = "YOUR_OPENAI_API_KEY"
# Set up the tracer provider
tracer_provider = TracerProvider()
trace.set_tracer_provider(tracer_provider)
# Add the OpenInference span processor
endpoint = "http://127.0.0.1:6006/v1/traces"
exporter = OTLPSpanExporter(endpoint=endpoint)
tracer_provider.add_span_processor(OpenInferenceSpanProcessor())
tracer_provider.add_span_processor(SimpleSpanProcessor(exporter))
# Define your Pydantic model
class LocationModel(BaseModel):
city: str
country: str
instrumentation = InstrumentationSettings(version=2)
# Create and configure the agent
model = OpenAIModel("gpt-4", provider=OpenAIProvider())
agent = Agent(model, output_type=LocationModel, instrument=instrumentation)
# Run the agent
result = agent.run_sync("The windy city in the US of A.")
print(result)
This example:
- Sets up OpenTelemetry tracing with Phoenix
- Defines a simple Pydantic model for location data
- Creates a PydanticAI agent with instrumentation enabled
- Runs a query and gets structured output
The traces will be visible in the Phoenix UI at http://localhost:6006.
More Info
1 maintainer
Release files for openinference-instrumentation-pydantic-ai 0.1.27
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| openinference_instrumentation_pydantic_ai-0.1.27.tar.gz | 25.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| openinference_instrumentation_pydantic_ai-0.1.27-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 42.2 kB
Release files / openinference_instrumentation_pydantic_ai-0.1.27.tar.gz
| Download URL | openinference_instrumentation_pydantic_ai-0.1.27.tar.gz |
|---|---|
| Size | 25.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7f5eb6841e919c50ba46a61b689717ea9ed4b3ae4bac733609f4765cc3388538
|
|
BLAKE2b-256 checksum How to use checksums |
59889d3aff1643cdc20a3aa9ede1167cf00f6222c3af87cbdf2e5c9c7b01c038
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 10, 2026.
Transparency logRelease files / openinference_instrumentation_pydantic_ai-0.1.27-py3-none-any.whl
| Download URL | openinference_instrumentation_pydantic_ai-0.1.27-py3-none-any.whl |
|---|---|
| Size | 17.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
65737aeba739cc233d03456b85f4c1d1a48c2ce6c2269f3f535092df8e3c5c39
|
|
BLAKE2b-256 checksum How to use checksums |
e321716ff7f048e5db0d9119bc27ed172e68c481e2c4e3333771eed30bbf59a3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 10, 2026.
Transparency log
