Azure OpenAI Provider

The Azure OpenAI provider integrates Reveal SDK AI with Azure's OpenAI Service, allowing you to use OpenAI models deployed in your own Azure subscription with enterprise-grade security and compliance.

Installation

ASP.NET

Install the Azure OpenAI provider NuGet package:

dotnet add package Reveal.Sdk.AI.AzureOpenAI

Node.js

The Azure OpenAI provider is bundled with reveal-sdk-node-ai — no extra package is required:

npm

npm install reveal-sdk-node-ai

Yarn

yarn add reveal-sdk-node-ai

pnpm

pnpm add reveal-sdk-node-ai

Bun

bun add reveal-sdk-node-ai

Java

The Azure OpenAI provider is bundled with reveal-sdk-ai — no extra dependency is required beyond the base AI artifact:

pom.xml

<dependency>
  <groupId>io.revealbi</groupId>
  <artifactId>reveal-sdk-ai</artifactId>
  <version>1.0.6-SNAPSHOT</version>
</dependency>

Configuration

Basic Setup

ASP.NET

Add the Azure OpenAI provider in your Program.cs:

Program.cs

using Reveal.Sdk;
using Reveal.Sdk.AI;

var builder = WebApplication.CreateBuilder(args);

builder.Services.AddControllers().AddReveal();

builder.Services.AddRevealAI()
    .AddAzureOpenAI(options =>
    {
        options.ApiKey = builder.Configuration["RevealAI:AzureOpenAI:ApiKey"];
        options.Endpoint = "https://your-resource-name.openai.azure.com/";
        options.DeploymentName = "gpt-4o";
    });

var app = builder.Build();
app.MapControllers();
app.Run();

Node.js

Pass Azure OpenAI settings under the azure-openai key in the settings object:

server.js

const reveal = require('reveal-sdk-node');
const revealAI = require('reveal-sdk-node-ai');
const express = require('express');

const aiSettings = {
    'azure-openai': {
        ApiKey: process.env.AZURE_OPENAI_API_KEY,
        Endpoint: 'https://your-resource-name.openai.azure.com/',
        DeploymentName: 'gpt-4o'
    }
};

const revealOptions = {
    plugins: [
        revealAI.withOptions({
            defaultProvider: 'azure-openai',
            settings: aiSettings
        })
    ]
};

const app = express();
app.use('/', reveal(revealOptions));
app.listen(5111);

Java

Pass Azure OpenAI settings under the azure-openai key in the settings map and register the plugin:

Application.java

import io.revealbi.ai.RevealAIPlugin;
import io.revealbi.ai.RevealAIPluginOptions;
import io.revealbi.core.IRevealServer;
import io.revealbi.core.RevealServerBuilder;

import java.util.Map;

Map<String, Object> aiSettings = Map.of(
        "azure-openai", Map.of(
                "ApiKey", System.getenv("AZURE_OPENAI_API_KEY"),
                "Endpoint", "https://your-resource-name.openai.azure.com/",
                "DeploymentName", "gpt-4o"));

RevealAIPluginOptions aiPluginOptions = new RevealAIPluginOptions(
        "azure-openai",
        "config/catalog.json",
        null,
        null,
        Map.of("settings", aiSettings));

IRevealServer revealServer = new RevealServerBuilder()
        .addPlugin(RevealAIPlugin.withOptions(aiPluginOptions))
        .build();

Using a Configuration File

ASP.NET

The provider automatically binds to the RevealAI:AzureOpenAI configuration section:

appsettings.json

{
  "RevealAI": {
    "AzureOpenAI": {
      "ApiKey": "your-azure-api-key",
      "Endpoint": "https://your-resource-name.openai.azure.com/",
      "DeploymentName": "gpt-4o",
      "Temperature": 0.0,
      "MaxTokens": 4096
    }
  }
}

With configuration binding, no code options are needed:

builder.Services.AddRevealAI()
    .AddAzureOpenAI();

Node.js

Node.js does not bind to appsettings.json. Load your settings from environment variables, a secrets manager, or a local config file and pass them inline:

server.js

const aiSettings = {
    'azure-openai': {
        ApiKey: process.env.AZURE_OPENAI_API_KEY,
        Endpoint: 'https://your-resource-name.openai.azure.com/',
        DeploymentName: 'gpt-4o',
        Temperature: 0.0,
        MaxTokens: 4096
    }
};

Java

Java does not bind to appsettings.json. Load your settings from environment variables, a secrets manager, or a local config file and pass them inline:

Application.java

Map<String, Object> aiSettings = Map.of(
        "azure-openai", Map.of(
                "ApiKey", System.getenv("AZURE_OPENAI_API_KEY"),
                "Endpoint", "https://your-resource-name.openai.azure.com/",
                "DeploymentName", "gpt-4o",
                "Temperature", 0.0,
                "MaxTokens", 4096));

Options

The same option names are used across all server platforms — ASP.NET sets them on the strongly-typed options object, Node.js and Java set them as keys in the azure-openai settings map.

Property	Type	Default	Description
ApiKey	string	""	Required. Your Azure OpenAI API key.
Endpoint	string	""	Required. The Azure OpenAI endpoint URL (e.g., https://your-resource-name.openai.azure.com/).
DeploymentName	string	""	Required. The name of your model deployment in Azure.
Temperature	float?	0.0	Controls randomness (0.0 to 2.0). Lower values are more deterministic.
MaxTokens	int?	4096	Maximum number of tokens to generate in the response.
TopP	float?	1.0	Nucleus sampling parameter.
ReasoningEffort	string?	null	Reasoning effort level for reasoning models (e.g., o3, o4).

Azure Setup Prerequisites

Before using the Azure OpenAI provider, you need:

1. An Azure subscription with access to Azure OpenAI Service
2. An Azure OpenAI resource created in the Azure portal
3. A model deployment (e.g., GPT-4o, GPT-4.1) within that resource
4. The API key and endpoint from the Azure portal

You can find your API key and endpoint in the Azure portal under your Azure OpenAI resource's Keys and Endpoint section.

Reasoning Models

Like the OpenAI provider, the Azure OpenAI provider automatically detects reasoning model deployments (o1, o3, o4, gpt-5) and adjusts behavior accordingly:

• Temperature is disabled for reasoning models
• Reasoning effort can be configured

ASP.NET

builder.Services.AddRevealAI()
    .AddAzureOpenAI(options =>
    {
        options.ApiKey = builder.Configuration["RevealAI:AzureOpenAI:ApiKey"];
        options.Endpoint = "https://your-resource.openai.azure.com/";
        options.DeploymentName = "o3";
        options.ReasoningEffort = "Medium";
    });

Node.js

const aiSettings = {
    'azure-openai': {
        ApiKey: process.env.AZURE_OPENAI_API_KEY,
        Endpoint: 'https://your-resource.openai.azure.com/',
        DeploymentName: 'o3',
        ReasoningEffort: 'Medium'
    }
};

Java

Map<String, Object> aiSettings = Map.of(
        "azure-openai", Map.of(
                "ApiKey", System.getenv("AZURE_OPENAI_API_KEY"),
                "Endpoint", "https://your-resource.openai.azure.com/",
                "DeploymentName", "o3",
                "ReasoningEffort", "Medium"));

Never Commit API Keys

Never commit API keys to source control. Always use environment variables, User Secrets, or a secure key management service.