Azure OpenAI Chat Completion in C# — Azure.AI.OpenAI SDK vs REST API (.NET 8)

A .NET 8 console application that demonstrates two ways to call an Azure OpenAI chat completion endpoint from C#: via the Azure.AI.OpenAI NuGet package and via a raw HTTP REST call. Both approaches use the same system prompt, which instructs the model to extract a product code and attributes from a natural-language query and return structured JSON.

Overview

The application runs two test queries against each connection method:

  1. A product-related query: "Can you help me to find the values of Sealing, Matched arrangement in 6205?"
  2. An unrelated query: "What is the capital of Sri Lanka?"

The system message instructs the model to extract product codes (e.g. 6205) and attributes from the user query and return:

{ "product": "<product_code>", "attributes": ["<attr1>", "<attr2>"] }

For queries unrelated to products, the model returns a polite refusal.

Connection Methods

PackageDemo — Azure.AI.OpenAI SDK

Uses AzureOpenAIClient and GetChatClient to send a ChatCompletionOptions request with Temperature = 0.7f and MaxOutputTokenCount = 100.

RestDemo — Raw HTTP

Uses HttpClient to POST directly to the Azure OpenAI REST endpoint, with a Newtonsoft.Json-serialised request body, extracting the response text from choices[0].message.content.

Configuration

All connection settings are defined in Configuration.cs:

Setting Description
EndPoint Azure OpenAI resource URL
Key API key
Model Deployment name (gpt-4o-mini)
Version API version (2024-08-01-preview)
SystemMessage System prompt for product code extraction

Security note: Do not commit a real API key. Keep Key empty or a placeholder in source control, and supply the key at run time — for example from an environment variable, .NET user secrets, or Azure Key Vault — or use Microsoft Entra ID authentication instead of a key. If a real key has ever been committed, rotate it in the Azure portal.

Sample Data

Data/6205.json contains SKF bearing specifications for part number 6205. It is copied to the build output as sample reference data, but the current code does not read it or send it to the model — the model only extracts the product code and attributes from the question.

Requirements

  • .NET 8 SDK
  • An Azure OpenAI resource with a gpt-4o-mini deployment

NuGet Packages

Package Version
Azure.AI.OpenAI 2.1.0
Newtonsoft.Json 13.0.3

Build and Run

cd Simple_ChatCompletion
dotnet run

Example Output

Model responses can vary between runs and deployments; a typical run looks like this:

** Package Demo **
{"product": "6205", "attributes": ["Sealing", "Matched arrangement"]}
I am sorry, I cannot help with your request. Your question is not related to products.

** Rest Demo **
{"product": "6205", "attributes": ["Sealing", "Matched arrangement"]}
I am sorry, I cannot help with your request. Your question is not related to products.

Project Structure

Simple_ChatCompletion/
├── ConnectByPackage/
│   └── PackageDemo.cs       # SDK-based chat completion
├── ConnectByRest/
│   └── RestDemo.cs          # Raw HTTP REST chat completion
├── Data/
│   └── 6205.json            # SKF bearing 6205 specification data
├── Configuration.cs         # Endpoint, key, model, and system message constants
├── Program.cs               # Runs both demos with two test queries
├── Simple_ChatCompletion.csproj
└── Simple_ChatCompletion.sln

FAQ

Should I use the SDK or the REST API? The Azure.AI.OpenAI SDK gives typed requests and responses and handles authentication options for you. The raw REST call shows exactly what goes over the wire and works from any HTTP client; it is useful for debugging or when you cannot take an SDK dependency.

What is the Model setting? In Azure OpenAI, requests target a deployment name that you create in your resource. This demo expects a deployment named gpt-4o-mini.

Read all C# and .NET Code Examples guides online · Project overview · All developer projects