smolagents AI Observability installation

Let AI instrument your LLM calls for you

Skip the manual setup — run this in your project and the wizard installs the SDK and wires up AI Observability for you.

Learn more
PostHog Wizard hedgehog

Contents

  1. Install dependencies

    Required
    Full working examples

    See the complete Python example on GitHub. If you use the PostHog SDK wrapper instead of OpenTelemetry, see the Python wrapper example.

    Install the OpenTelemetry SDK, the OpenAI instrumentation, and smolagents.

    pip install smolagents openai opentelemetry-sdk "posthog[otel]" opentelemetry-instrumentation-openai-v2

  2. Set up OpenTelemetry tracing

    Required

    Configure OpenTelemetry to auto-instrument OpenAI SDK calls and export traces to PostHog. PostHog converts gen_ai.* spans into $ai_generation events automatically.

    from opentelemetry import trace
    from opentelemetry.sdk.trace import TracerProvider
    from opentelemetry.sdk.resources import Resource, SERVICE_NAME
    from posthog.ai.otel import PostHogSpanProcessor
    from opentelemetry.instrumentation.openai_v2 import OpenAIInstrumentor
    

    resource = Resource(attributes={
        SERVICE_NAME: "my-app",
        "posthog.distinct_id": "user_123", # optional: identifies the user in PostHog
        "foo": "bar", # custom properties are passed through
    })
    

    provider = TracerProvider(resource=resource)
    provider.add_span_processor(
        PostHogSpanProcessor(
            api_key="<ph_project_token>",
            host="https://us.i.posthog.com",
        )
    )
    trace.set_tracer_provider(provider)
    

    OpenAIInstrumentor().instrument()

  3. Run your agent

    Required

    Use smolagents as normal. PostHog automatically captures an $ai_generation event for each LLM call made through the OpenAI SDK that smolagents uses internally.

    import os
    from smolagents import CodeAgent, LiteLLMModel
    

    model = LiteLLMModel(model_id="gpt-4o-mini", api_key=os.environ["OPENAI_API_KEY"])
    agent = CodeAgent(tools=[], model=model)
    

    result = agent.run("Tell me a fun fact about hedgehogs")
    print(result)

    Note: If you want to capture LLM events anonymously, omit the posthog.distinct_id resource attribute. See our docs on anonymous vs identified events to learn more.

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

    PropertyDescription
    $ai_modelThe specific model, like gpt-5-mini or claude-4-sonnet
    $ai_latencyThe latency of the LLM call in seconds
    $ai_time_to_first_tokenTime to first token in seconds (streaming only)
    $ai_toolsTools and functions available to the LLM
    $ai_inputList of messages sent to the LLM
    $ai_input_tokensThe number of tokens in the input (often found in response.usage)
    $ai_output_choicesList of response choices from the LLM
    $ai_output_tokensThe number of tokens in the output (often found in response.usage)
    $ai_total_cost_usdThe total cost in USD (input + output)
    [...]See full list of properties

  4. Group traces into sessions

    Optional

    PostHog groups traces into a session when they share an $ai_session_id. Set it if your product has multi-turn conversations, so the Sessions tab can reconstruct them. Workloads that finish in a single trace, like batch jobs or one-shot generation, do not need it.

    The instrumentation creates the LLM span for you, so there is no call to pass the session ID to. Add a span processor that sets the $ai_session_id attribute as each span starts. PostHog forwards span attributes it does not recognize onto the event, so the value arrives as the $ai_session_id property.

    Python
    import contextvars
    from collections.abc import Iterator
    from contextlib import contextmanager
    from typing import Optional
    

    from opentelemetry.context import Context
    from opentelemetry.sdk.trace import Span, SpanProcessor
    

    session_id_var: contextvars.ContextVar[Optional[str]] = contextvars.ContextVar(
        "ai_session_id", default=None
    )
    

    

    class SessionIdSpanProcessor(SpanProcessor):
        def on_start(self, span: Span, parent_context: Optional[Context] = None) -> None:
            session_id = session_id_var.get()
            if session_id is not None:
                span.set_attribute("$ai_session_id", session_id)
    

    

    @contextmanager
    def ai_session(session_id: str) -> Iterator[None]:
        token = session_id_var.set(session_id)
        try:
            yield
        finally:
            session_id_var.reset(token)
    

    

    # Register it on the same provider as PostHogSpanProcessor
    provider.add_span_processor(SessionIdSpanProcessor())
    

    # Resetting on exit keeps the ID off the next request that reuses this thread
    with ai_session("conversation-abc"):
        reply = handle_turn(user_message)

    If a process only ever handles one session, set $ai_session_id as a resource attribute next to service.name instead. Resource attributes apply to every span the process emits, so that only works when the process and the session are the same thing.

  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 AI Observability, you should see rows of data appear in the Traces and Generations tabs.


    LLM generations in PostHog
    Check for LLM events in PostHog

  6. Next steps

    Recommended

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

    ResourceDescription
    BasicsLearn the basics of how LLM calls become events in PostHog.
    GenerationsRead about the $ai_generation event and its properties.
    TracesExplore the trace hierarchy and how to use it to debug LLM calls.
    SpansReview spans and their role in representing individual operations.
    Anaylze LLM performanceLearn how to create dashboards to analyze LLM performance.

Still have questions?

Was this page useful?