← Back to all frameworks Azure ML & Cloud

Azure OpenAI Service

GPT-4 class models inside your Azure tenancy

What it is

OpenAI's models (GPT-4o, GPT-4 Turbo, embeddings, Whisper, DALL-E) hosted by Microsoft — your data stays in your region, with enterprise SLAs and content filters built in.

How Vaaani uses it

  • Private LLM deployment for regulated industries
  • Region-pinned GPT-4 for data sovereignty (EU, India, UAE)
  • Single-tenant rate limits — no surprise throttling
  • Direct integration with Azure AI Search for RAG

Why it makes the cut

When the customer's compliance team says 'no data may leave Azure,' Azure OpenAI is how Vaaani still gives them GPT-4 power.

Sample code

from openai import AzureOpenAI

client = AzureOpenAI(
    azure_endpoint="https://vaaani.openai.azure.com/",
    api_version="2024-10-01",
)
resp = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "hello"}])

Related in the Vaaani stack

Have a project that needs Azure?

30-min discovery call. You describe the busywork; I map it to an AI worker and a budget.