AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

omnibus-instrument-llm-analytics

Add PostHog LLM analytics to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. Also handles initial PostHog SDK setup if not yet installed.

Original source
posthog
License
MIT
Pinned revision
cac7c80a9e5b73484d18eda1bffb47297c938e0c

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

Ask your assistant

Use Agentic Memory skills to read posthog--omnibus-instrument-llm-analytics at revision cac7c80a9e5b73484d18eda1bffb47297c938e0c, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 38

references/pydantic-ai.md

Pydantic AI LLM analytics installation - Docs

  1. 1

    Install the PostHog SDK

    Required

    Setting up analytics starts with installing the PostHog SDK. The Pydantic AI integration uses PostHog's OpenAI wrapper.

    pip install posthog
    
  2. 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. 3

    Initialize PostHog and Pydantic AI

    Required

    Initialize PostHog with your project token and host from your project settings, 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. 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:

    | Property | Description | | --- | --- | | $ai_model | The specific model, like gpt-5-mini or claude-4-sonnet | | $ai_latency | The latency of the LLM call in seconds | | $ai_time_to_first_token | Time to first token in seconds (streaming only) | | $ai_tools | Tools and functions available to the LLM | | $ai_input | List of messages sent to the LLM | | $ai_input_tokens | The number of tokens in the input (often found in response.usage) | | $ai_output_choices | List of response choices from the LLM | | $ai_output_tokens | The number of tokens in the output (often found in response.usage) | | $ai_total_cost_usd | The total cost in USD (input + output) | | [...] | See full list of properties |

  5. 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.

    LLM generations in PostHogLLM generations in PostHog

    Check for LLM events in PostHog

  6. 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.

    | Resource | Description | | --- | --- | | Basics | Learn the basics of how LLM calls become events in PostHog. | | Generations | Read about the $ai_generation event and its properties. | | Traces | Explore the trace hierarchy and how to use it to debug LLM calls. | | Spans | Review spans and their role in representing individual operations. | | Anaylze LLM performance | Learn how to create dashboards to analyze LLM performance. |

Community questions

Ask a question

Was this page useful?

HelpfulCould be better