Chapter 150 · LLM Analytics Setup
Subchapter 150.18
references/langgraph.mdMarkdown7 KBView on GitHub
Required
Setting up analytics starts with installing the PostHog SDK for your language. LLM analytics works best with our Python and Node SDKs.
PostHog AI
pip install posthognpm install @posthog/ai posthog-node2
Required
Install LangGraph and LangChain. PostHog instruments your LLM calls through LangChain-compatible callback handlers that LangGraph supports.
PostHog AI
pip install langgraph langchain-openainpm install @langchain/langgraph @langchain/openai @langchain/core3
Required
Initialize PostHog with your project token and host from your project settings (opens in a new tab), then create a LangChain CallbackHandler.
PostHog AI
from posthog.ai.langchain import CallbackHandler
from posthog import Posthog
posthog = Posthog(
"<ph_project_token>",
host="https://us.i.posthog.com"
)
callback_handler = CallbackHandler(
client=posthog,
distinct_id="user_123", # optional
trace_id="trace_456", # optional
properties={"conversation_id"
import { PostHog } from 'posthog-node';
import { LangChainCallbackHandler } from '@posthog/ai';
const phClient = new PostHog(
'<ph_project_token>',
{ host: 'https://us.i.posthog.com' }
);
const callbackHandler = new LangChainCallbackHandler({
client: phClient,
How this works
LangGraph is built on LangChain, so it supports LangChain-compatible callback handlers. PostHog’s CallbackHandler captures $ai_generation events and trace hierarchy automatically without proxying your calls.
4
Required
Pass the callback_handler in the config when invoking your LangGraph graph. PostHog automatically captures generation events for each LLM call.
PostHog AI
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI
from langchain_core.tools import tool
@tool
def get_weather(city: str) -> str:
"""Get the weather for a given city."""
return f"It's always sunny in {city}!"
model = ChatOpenAI(api_key="your_openai_api_key")
agent = create_react_agent(model, tools=[get_weather])
result = agent.invoke(
{"messages": [{"role": "user", "content": "What's the weather in Paris?"}]},
config={"callbacks": [callback_handler]}
)
print(result["messages"][-1].content)import { createReactAgent } from '@langchain/langgraph/prebuilt';
import { ChatOpenAI } from '@langchain/openai';
import { tool } from '@langchain/core/tools';
import { z } from 'zod';
const getWeather = tool(
(input
PostHog automatically captures $ai_generation events and creates a trace hierarchy based on how LangGraph components are nested. You can expect captured 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) |
| […] (opens in a new tab) | See full list (opens in a new tab) of properties |
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.


5
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 (opens in a new tab) | Learn the basics of how LLM calls become events in PostHog. |
| Generations (opens in a new tab) | Read about the $ai_generation event and its properties. |
| Traces (opens in a new tab) | Explore the trace hierarchy and how to use it to debug LLM calls. |
| Spans (opens in a new tab) | Review spans and their role in representing individual operations. |
| Anaylze LLM performance (opens in a new tab) | Learn how to create dashboards to analyze LLM performance. |
Ask a question
HelpfulCould be better