Anthropic

2

Install the Anthropic SDK

Required

Install the Anthropic SDK. The PostHog SDK instruments your LLM calls by wrapping the Anthropic client. The PostHog SDK does not proxy your calls.

PostHog AI

Python

pip install anthropic

Node

npm install @anthropic-ai/sdk

Proxy note

These SDKs do not proxy your calls. They only fire off an async call to PostHog in the background to send the data. You can also use LLM analytics with other SDKs or our API, but you will need to capture the data in the right format. See the schema in the manual capture section (opens in a new tab) for more details.

3

Initialize PostHog and the Anthropic wrapper

Required

Initialize PostHog with your project token and host from your project settings (opens in a new tab), then pass it to our Anthropic wrapper.

PostHog AI

Python

from posthog.ai.anthropic import Anthropic
from posthog import Posthog
posthog = Posthog(
    "<ph_project_token>",
    host="https://us.i.posthog.com"
)
client = Anthropic(
    api_key="sk-ant-api...", # Replace with your Anthropic API key
    posthog_client=posthog # This is an optional parameter. If it is not provided, a default client will be used.
)

Node

import { Anthropic } from '@posthog/ai'
import { PostHog } from 'posthog-node'
const phClient = new PostHog(
  '<ph_project_token>',
  { host: 'https://us.i.posthog.com' }
)
const client = new Anthropic({
  apiKey: 'sk-ant-api...', // Replace with your Anthropic API key
  posthog: phClient

Note: This also works with the AsyncAnthropic client as well as AnthropicBedrock, AnthropicVertex, and the async versions of those.

4

Call Anthropic LLMs

Required

Now, when you use the Anthropic SDK to call LLMs, PostHog automatically captures an $ai_generation event. You can enrich the event with additional data such as the trace ID, distinct ID, custom properties, groups, and privacy mode options.

PostHog AI

Python

response = client.messages.create(
    model="claude-3-opus-20240229",
    messages=[
        {
            "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.content[0].text)

Node

const response = await client.messages.create({
  model: "claude-3-5-sonnet-latest",
  messages: [
    {
      role: "user",
      content: "Tell me a fun fact about hedgehogs"
    }
  ],
  posthogDistinctId: "user_123", // optional
  posthogTraceId: "trace_123", // optional
  posthogProperties: { conversationId: 

Notes:

• This also works when message streams are used (e.g. stream=True or client.messages.stream(...)).
• 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 (opens in a new tab) to learn more.

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.