Azure OpenAI (Beta)

Installation

npm install @raindrop-ai/azure-openai openai

pnpm add @raindrop-ai/azure-openai openai

pip install raindrop-azure-openai openai

Quick Start

import { createRaindropAzureOpenAI } from "@raindrop-ai/azure-openai";
import { AzureOpenAI } from "openai";

const raindrop = createRaindropAzureOpenAI({
  writeKey: "your-write-key",
  userId: "user-123",
});

const client = new AzureOpenAI({
  endpoint: "https://your-resource.openai.azure.com",
  apiKey: "...",
  apiVersion: "2024-10-21",
});

const wrapped = raindrop.wrap(client);

const response = await wrapped.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "What is the capital of France?" }],
});

console.log(response.choices[0].message.content);
await raindrop.shutdown();

from raindrop_azure_openai import RaindropAzureOpenAI
from openai import AzureOpenAI

raindrop = RaindropAzureOpenAI(
    api_key="rk_...",
    user_id="user-123",
)

client = AzureOpenAI(
    azure_endpoint="https://your-resource.openai.azure.com",
    api_key="...",
    api_version="2024-10-21",
)
wrapped = raindrop.wrap(client)

response = wrapped.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)

print(response.choices[0].message.content)
raindrop.shutdown()

What Gets Traced

Chat completions — input messages (user text only), output text, model, token usage (prompt/completion)
Finish reason — azure_openai.finish_reason (stop, length, content_filter, tool_calls)
Extended tokens — ai.usage.cached_tokens (prompt cache hits) and ai.usage.thoughts_tokens (reasoning tokens for o1/o3 models)
Errors — captured with error status, re-thrown to caller

Configuration

const raindrop = createRaindropAzureOpenAI({
  writeKey: "your-write-key",       // Optional: your Raindrop write key (omit to disable telemetry)
  endpoint: "...",          // Optional: custom Raindrop API endpoint
  userId: "user-123",      // Optional: associate events with a user
  convoId: "convo-456",    // Optional: conversation/thread ID
  projectId: "support-prod", // Optional: route events to a specific project (slug)
  debug: false,             // Optional: enable verbose logging
});

from raindrop_azure_openai import RaindropAzureOpenAI

raindrop = RaindropAzureOpenAI(
    api_key="rk_...",                   # Optional: your Raindrop API key (omit to disable telemetry)
    user_id="user-123",                 # Optional: associate events with a user
    convo_id="convo-456",               # Optional: conversation/thread ID
    project_id="support-prod",          # Optional: route events to a specific project (slug)
    tracing_enabled=True,               # Optional: enable OTEL-based tracing
    bypass_otel_for_tools=True,         # Optional: bypass OTEL for tool calls
    debug=False,                        # Optional: enable verbose logging
)

Projects

Route events to a specific project by passing its slug as projectId (project_id in Python):

const raindrop = createRaindropAzureOpenAI({
  writeKey: "your-write-key",
  projectId: "support-prod",
});

raindrop = RaindropAzureOpenAI(
    api_key="rk_...",
    project_id="support-prod",
)

This sets the X-Raindrop-Project-Id header on every event. Omit it (or pass "default") to use your org’s default Production project, which is the existing behavior. Single-project orgs need nothing new.

Multiple projects in one process

Available in raindrop-ai>=0.0.56. When one service wraps several Azure OpenAI clients that should report to different projects, create one RaindropAzureOpenAI wrapper per project. Each wrapper owns its own raindrop.Raindrop client, so the two route independently — there is no shared module-level state:

from raindrop_azure_openai import RaindropAzureOpenAI

# One long-lived wrapper per project, created at startup and reused.
rd_support = RaindropAzureOpenAI(api_key="rk_...", project_id="support-prod")
rd_billing = RaindropAzureOpenAI(api_key="rk_...", project_id="billing-prod")

support_client = rd_support.wrap(support_client)   # -> support-prod
billing_client = rd_billing.wrap(billing_client)   # -> billing-prod

rd_support.flush()
rd_billing.flush()

Each wrapper owns its configuration and delivery pipeline, so clients handled by different wrappers route independently. To share a single client across wrappers (or with the module-level API), construct a raindrop.Raindrop yourself and pass it via client=:

from raindrop import Raindrop

client = Raindrop(api_key="rk_...", project_id="support-prod")
raindrop = RaindropAzureOpenAI(client=client)

Flushing and Shutdown

await raindrop.flush();     // flush pending data
await raindrop.shutdown();  // flush + release resources

raindrop.flush()     # flush pending data
raindrop.shutdown()  # flush + release resources

User Identification

raindrop.users.identify({ userId: "user-123", traits: { plan: "pro", name: "Alice" } });

raindrop.identify("user-123", traits={"plan": "pro", "name": "Alice"})

Tracking Signals

raindrop.signals.track({
  eventId: "evt-abc",
  name: "thumbs_up",
  type: "feedback",
  sentiment: "POSITIVE",
  comment: "Great response!",
});

raindrop.track_signal(
    event_id="evt-abc",
    name="thumbs_up",
    signal_type="feedback",
    sentiment="POSITIVE",
    comment="Great response!",
)

Factory Function (Backwards-Compatible)

Python

from raindrop_azure_openai import create_raindrop_azure_openai

raindrop = create_raindrop_azure_openai(api_key="rk_...", user_id="user-123")
# Returns a RaindropAzureOpenAI instance

Already using the Vercel AI SDK with Azure? The Vercel AI SDK integration automatically traces Azure OpenAI calls when you use the AI SDK’s Azure provider. This integration is for users calling the Azure OpenAI SDK directly.

​Installation

​Quick Start

​What Gets Traced

​Configuration

​Projects

​Multiple projects in one process

​Flushing and Shutdown

​User Identification

​Tracking Signals

​Factory Function (Backwards-Compatible)

Installation

Quick Start

What Gets Traced

Configuration

Projects

Multiple projects in one process

Flushing and Shutdown

User Identification

Tracking Signals

Factory Function (Backwards-Compatible)