OpenAI LLM analytics installation

Setting up analytics starts with installing the PostHog SDK for your language. LLM analytics works best with our Python and Node SDKs.

pip install posthog

Install the OpenAI SDK:

pip install openai

In the spot where you initialize the OpenAI SDK, import PostHog and our OpenAI wrapper, initialize PostHog with your project API key and host from your project settings, and pass it to our OpenAI wrapper.

from posthog.ai.openai import OpenAI
from posthog import Posthog

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

client = OpenAI(
    api_key="your_openai_api_key",
    posthog_client=posthog # This is an optional parameter. If it is not provided, a default client will be used.
)

Note: This also works with the AsyncOpenAI client.

Now, when you use the OpenAI SDK, it automatically captures many properties into PostHog including $ai_input, $ai_input_tokens, $ai_cache_read_input_tokens, $ai_latency, $ai_model, $ai_model_parameters, $ai_reasoning_tokens, $ai_tools, $ai_output_choices, and $ai_output_tokens.

You can also capture or modify additional properties with the distinct ID, trace ID, properties, groups, and privacy mode parameters.

response = client.responses.create(
    model="gpt-4o-mini",
    input=[
        {"role": "user", "content": "Tell me a fun fact about hedgehogs"}
    ],
    posthog_distinct_id="user_123", # optional
    posthog_trace_id="trace_123", # optional
    posthog_properties={"conversation_id": "abc123", "paid": True}, # optional
    posthog_groups={"company": "company_id_in_your_db"},  # optional 
    posthog_privacy_mode=False # optional
)

print(response.choices[0].message.content)

Notes:

• We also support the old chat.completions API.
• This works with responses where stream=True.
• If you want to capture LLM events anonymously, don't pass a distinct ID to the request. See our docs on anonymous vs identified events to learn more.

Before proceeding, 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.

PostHog can also capture embedding generations as $ai_embedding events. Just make sure to use the same posthog.ai.openai client to do so:

response = client.embeddings.create(
    input="The quick brown fox",
    model="text-embedding-3-small",
    posthog_distinct_id="user_123", # optional
    posthog_trace_id="trace_123",   # optional
    posthog_properties={"key": "value"} # optional
    posthog_groups={"company": "company_id_in_your_db"}  # optional 
    posthog_privacy_mode=False # optional
)