LangChain

2

Install LangChain and OpenAI SDKs

Required

Install LangChain. The PostHog SDK instruments your LLM calls by wrapping LangChain. The PostHog SDK does not proxy your calls.

PostHog AI

Python

pip install langchain openai langchain-openai

Node

npm install langchain @langchain/core @langchain/openai @posthog/ai

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 LangChain

Required

Initialize PostHog with your project token and host from your project settings (opens in a new tab), then pass it to the LangChain CallbackHandler wrapper. Optionally, you can provide a user distinct ID, trace ID, PostHog properties, groups (opens in a new tab), and privacy mode.

PostHog AI

Python

from posthog.ai.langchain import CallbackHandler
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from posthog import Posthog
posthog = Posthog(
    "<ph_project_token>",
    host="https://us.i.posthog.com"
)
callback_handler =

Node

import { PostHog } from 'posthog-node';
import { LangChainCallbackHandler } from '@posthog/ai';
import { ChatOpenAI } from '@langchain/openai';
import { ChatPromptTemplate } from '@langchain/core/prompts';
const phClient = new PostHog(
  '<ph_project_token>',

Note: If you want to capture LLM events anonymously, don’t pass a distinct ID to the CallbackHandler. See our docs on anonymous vs identified events (opens in a new tab) to learn more.

4

Call LangChain

Required

When you invoke your chain, pass the callback_handler in the config as part of your callbacks:

PostHog AI

Python

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant."),
    ("user", "{input}")
])
model = ChatOpenAI(openai_api_key="your_openai_api_key")
chain = prompt | model
# Execute the chain with the callback handler
response = chain.invoke(
    {"input": "Tell me a joke about programming"},
    config={"callbacks": [callback_handler]}
)
print(response.content)

Node

const prompt = ChatPromptTemplate.fromMessages([
  ["system", "You are a helpful assistant."],
  ["user", "{input}"]
]);
const model = new ChatOpenAI({
  apiKey: "your_openai_api_key"
});
const chain = prompt.pipe

PostHog automatically captures an $ai_generation event along with these properties:

It also automatically creates a trace hierarchy based on how LangChain components are nested.

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.