references/instructor.md
Instructor LLM analytics installation - Docs
-
1
Install the PostHog SDK
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
Python
pip install posthogNode
npm install @posthog/ai posthog-node -
2
Install Instructor and OpenAI SDKs
Required
Install Instructor and the OpenAI SDK. PostHog instruments your LLM calls by wrapping the OpenAI client, which Instructor uses under the hood.
PostHog AI
Python
pip install instructor openaiNode
npm install @instructor-ai/instructor openai zod@3 -
3
Initialize PostHog and Instructor
Required
Initialize PostHog with your project token and host from your project settings, then create a PostHog OpenAI wrapper and pass it to Instructor.
PostHog AI
Python
import instructor from pydantic import BaseModel from posthog.ai.openai import OpenAI from posthog import Posthog posthog = Posthog( "<ph_project_token>", host="https://us.i.posthog.com" ) openai_client = OpenAI( api_key="your_openai_api_key", posthog_client=posthog ) client = instructor.from_openai(openai_client)Node
import Instructor from '@instructor-ai/instructor' import { OpenAI } from '@posthog/ai' import { PostHog } from 'posthog-node' import { z } from 'zod' const phClient = new PostHog( '<ph_project_token>', { host: 'https://us.i.posthog.com' } ); const openai = new OpenAI({ apiKey: 'your_openai_api_key', posthog: phClient, }); const client = Instructor({ client: openai, mode: 'TOOLS' })How this works
PostHog's
OpenAIwrapper is a proper subclass ofopenai.OpenAI, so it works directly withinstructor.from_openai(). PostHog captures$ai_generationevents automatically without proxying your calls. -
4
Use Instructor with structured outputs
Required
Now use Instructor to extract structured data from LLM responses. PostHog automatically captures an
$ai_generationevent for each call.PostHog AI
Python
class UserInfo(BaseModel): name: str age: int user = client.chat.completions.create( model="gpt-5-mini", response_model=UserInfo, messages=[ {"role": "user", "content": "John Doe is 30 years old."} ], posthog_distinct_id="user_123", posthog_trace_id="trace_123", posthog_properties={"conversation_id": "abc123"}, ) print(f"{user.name} is {user.age} years old")Node
const UserInfo = z.object({ name: z.string(), age: z.number(), }) const user = await client.chat.completions.create({ model: 'gpt-5-mini', response_model: { schema: UserInfo, name: 'UserInfo' }, messages: [ { role: 'user', content: 'John Doe is 30 years old.' } ], posthogDistinctId: 'user_123', posthogTraceId: 'trace_123', posthogProperties: { conversation_id: 'abc123' }, }) console.log(`${user.name} is ${user.age} years old`) phClient.shutdown()You can expect captured
$ai_generationevents 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) | | [...] | See full list of 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.
LLM generations in PostHogLLM generations in PostHog
-
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.
| Resource | Description | | --- | --- | | Basics | Learn the basics of how LLM calls become events in PostHog. | | Generations | Read about the $ai_generation event and its properties. | | Traces | Explore the trace hierarchy and how to use it to debug LLM calls. | | Spans | Review spans and their role in representing individual operations. | | Anaylze LLM performance | Learn how to create dashboards to analyze LLM performance. |
Community questions
Ask a question
Was this page useful?
HelpfulCould be better