references/azure-openai.md
Azure OpenAI LLM analytics installation - Docs
-
1
Install the SDKs
Required
Setting up analytics starts with installing the PostHog and OpenAI SDKs.
PostHog AI
Python
pip install posthog openaiNode
npm install @posthog/ai posthog-node openai -
2
Initialize PostHog and Azure OpenAI client
Required
We call Azure OpenAI through PostHog's AzureOpenAI wrapper to capture all the details of the call. Initialize PostHog with your PostHog project token and host from your project settings, then pass the PostHog client along with your Azure OpenAI config (the API key, API version, and endpoint) to our AzureOpenAI wrapper.
PostHog AI
Python
from posthog.ai.openai import AzureOpenAI from posthog import Posthog posthog = Posthog( "<ph_project_token>", host="https://us.i.posthog.com" ) client = AzureOpenAI( api_key="<azure_openai_api_key>", api_version="2024-10-21", azure_endpoint="https://<your-resource>.openai.azure.com", posthog_client=posthog )Node
import { AzureOpenAI } from '@posthog/ai' import { PostHog } from 'posthog-node' const phClient = new PostHog( '<ph_project_token>', { host: 'https://us.i.posthog.com' } ); const client = new AzureOpenAI({ apiKey: '<azure_openai_api_key>', apiVersion: '2024-10-21', endpoint: 'https://<your-resource>.openai.azure.com', posthog: phClient, }); // ... your code here ... // IMPORTANT: Shutdown the client when you're done to ensure all events are sent phClient.shutdown()Note: This also works with the
AsyncAzureOpenAIclient.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 for more details.
-
3
Call Azure OpenAI
Required
Now, when you call Azure OpenAI, PostHog automatically captures an
$ai_generationevent. You can also capture or modify additional properties with the distinct ID, trace ID, properties, groups, and privacy mode parameters.PostHog AI
Python
response = client.chat.completions.create( model="<your-deployment-name>", 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.choices[0].message.content)Node
const completion = await client.chat.completions.create({ model: "<your-deployment-name>", messages: [{ role: "user", content: "Tell me a fun fact about hedgehogs" }], posthogDistinctId: "user_123", // optional posthogTraceId: "trace_123", // optional posthogProperties: { conversation_id: "abc123", paid: true }, // optional posthogGroups: { company: "company_id_in_your_db" }, // optional posthogPrivacyMode: false // optional }); console.log(completion.choices[0].message.content)Notes:
- 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.
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 |
- This works with responses where
-
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
-
4
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