Pydantic AI

2

Install Pydantic AI

Required

Install Pydantic AI with OpenAI support. PostHog instruments your LLM calls by wrapping the OpenAI client that Pydantic AI uses.

pip install 'pydantic-ai[openai]'

3

Initialize PostHog and Pydantic AI

Required

Initialize PostHog with your project token and host from your project settings (opens in a new tab), then create a PostHog AsyncOpenAI wrapper, pass it to an OpenAIProvider, and use that with Pydantic AI’s OpenAIChatModel.

from pydantic_ai import Agent
from pydantic_ai.models.openai import OpenAIChatModel
from pydantic_ai.providers.openai import OpenAIProvider
from posthog.ai.openai import AsyncOpenAI
from posthog import Posthog
posthog = Posthog(
    "<ph_project_token>",
    host="https://us.i.posthog.com"
)
openai_client = AsyncOpenAI(
    api_key="your_openai_api_key",
    posthog_client=posthog
)
provider = OpenAIProvider(openai_client=openai_client)
model = OpenAIChatModel(
    "gpt-5-mini",
    provider=provider
)

How this works

PostHog’s AsyncOpenAI wrapper is a proper subclass of openai.AsyncOpenAI, so it works directly as the client for Pydantic AI’s OpenAIProvider. PostHog captures $ai_generation events automatically without proxying your calls.

4

Run your agent

Required

Create a Pydantic AI agent with the model and run it. PostHog automatically captures an $ai_generation event for each LLM call.

agent = Agent(
    model,
    system_prompt="You are a helpful assistant.",
)
result = agent.run_sync(
    "Tell me a fun fact about hedgehogs.",
    # Pass PostHog metadata via the OpenAI client's extra params
)
print(result.output)

You can expect captured $ai_generation events to have the following properties:

Verify traces and generations

Recommended

Confirm LLM events are being sent to PostHog

Let’s make sure LLM events are being captured and sent to PostHog. Under LLM analytics, you should see rows of data appear in the Traces and Generations tabs.

Check for LLM events in PostHog (opens in a new tab)

5

Next steps

Recommended

Now that you’re capturing AI conversations, continue with the resources below to learn what else LLM Analytics enables within the PostHog platform.