@raindrop-ai/azure-openai

Raindrop integration for Azure OpenAI. Automatically captures chat.completions.create() calls by wrapping the AzureOpenAI client.

Installation

npm install @raindrop-ai/azure-openai openai

Usage

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: "Hello!" }],
});

await raindrop.shutdown();

What gets captured

• Chat completions: input messages, output text, model, token usage (prompt/completion)
• Errors: captured with error status on spans, re-thrown to caller

Options

| Option | Type | Default | Description | |--------|------|---------|-------------| | writeKey | string | - | Raindrop API write key (omit to disable telemetry) | | endpoint | string | https://api.raindrop.ai/v1/ | Raindrop API endpoint | | userId | string | - | Associate all events with a user | | convoId | string | - | Group events into a conversation | | projectId | string | - | Route events to a specific project (slug); omit for the default Production project | | debug | boolean | false | Enable verbose logging | | maxTextFieldChars | number | 1000000 | Per-field character cap for captured input/output text |

Projects

If your org has multiple projects, route events to a specific one by passing its slug as projectId:

const raindrop = createRaindropAzureOpenAI({
  writeKey: "your-write-key",
  projectId: "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 — the existing behavior. Single-project orgs need nothing new.

Payload size limits

Captured input/output text is capped at 1,000,000 characters per field by default and truncated with a ...[truncated by raindrop] marker (the result, marker included, never exceeds the limit). Multi-part message content (e.g. base64 image blocks) is serialized under the same budget, so multi-MB payloads cost the cap — not the payload — on your calling thread, and oversized events land truncated instead of being dropped at the ingest size limit. Tune it via maxTextFieldChars.

Testing

pnpm test