LlamaIndex LLM analytics installation

  1. Install the PostHog SDK

    Required

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

    pip install posthog

  2. Install LlamaIndex

    Required

    Install LlamaIndex with the OpenAI integration. PostHog instruments your LLM calls by wrapping the OpenAI client that LlamaIndex uses.

    pip install llama-index llama-index-llms-openai

  3. Initialize PostHog and LlamaIndex

    Required

    Initialize PostHog with your project API key and host from your project settings, then create a PostHog OpenAI wrapper and pass it to LlamaIndex's OpenAI LLM class.

    from llama_index.llms.openai import OpenAI as LlamaOpenAI
    from posthog.ai.openai import OpenAI
    from posthog import Posthog
    

    posthog = Posthog(
        "<ph_project_api_key>",
        host="https://us.i.posthog.com"
    )
    

    openai_client = OpenAI(
        api_key="your_openai_api_key",
        posthog_client=posthog
    )
    

    llm = LlamaOpenAI(
        model="gpt-4o-mini",
        api_key="your_openai_api_key",
    )
    llm._client = openai_client
    How this works

    PostHog's OpenAI wrapper is a proper subclass of openai.OpenAI, so it can replace the internal client used by LlamaIndex's OpenAI LLM. PostHog captures $ai_generation events automatically without proxying your calls. Note: This approach accesses an internal attribute (_client) which may change in future LlamaIndex versions. Check for updates if you encounter issues after upgrading LlamaIndex.

  4. Query with LlamaIndex

    Required

    Use LlamaIndex as normal. PostHog automatically captures an $ai_generation event for each LLM call made through the wrapped client.

    from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
    

    # Load your documents
    documents = SimpleDirectoryReader("data").load_data()
    

    # Create an index
    index = VectorStoreIndex.from_documents(documents, llm=llm)
    

    # Query the index
    query_engine = index.as_query_engine(llm=llm)
    response = query_engine.query("What is this document about?")
    

    print(response)

    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

  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 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 LLM Analytics 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.

Community questions

Was this page useful?

Questions about this page? or post a community question.