Sending a Simple Query to DeepSeek Using C#

Sending a Simple Query to DeepSeek

Welcome to the first lesson of our course on creating a personal tutor with DeepSeek! DeepSeek is an advanced AI platform that offers state-of-the-art language models capable of understanding and generating human-like text. Its unique features include high accuracy in language comprehension, the ability to generate contextually relevant responses, and a robust API that supports seamless integration into various applications. These capabilities make DeepSeek an excellent choice for building AI tutors, as it can provide personalized and insightful interactions with users. In this lesson, we will explore the basics of interacting with DeepSeek's AI models using C# . Our goal is to send a simple query to DeepSeek's language model and receive a response. This foundational step will set the stage for more complex interactions in future lessons. By understanding how to communicate with DeepSeek, you'll be equipped to harness its full potential in creating a personal tutor that can adapt to individual learning needs.

Setting Up Your Environment

Before we can send a query to DeepSeek, we need to set up our development environment for C# . This involves installing the necessary tools and libraries. For this course, you will need the System.Net.Http and System.Text.Json libraries, which are included in .NET Core and later versions. These libraries allow us to send HTTP requests and handle JSON data when interacting with DeepSeek's API. If you are using an older version of .NET, make sure your project targets at least .NET Core 3.1 or later to have access to these libraries. Once your environment is ready, you can proceed to write and run your C# code to interact with DeepSeek.

Setting the DeepSeek API Key as an Environment Variable

Join the 1M+ learners on CodeSignal

Be a part of our community of 1M+ users who develop and demonstrate their skills on CodeSignal

Shell

export OPENAI_API_KEY=your_deepseek_api_key_here
export OPENAI_BASE_URL=https://api.deepseek.com

Visual Basic

set OPENAI_API_KEY=your_deepseek_api_key_here
set OPENAI_BASE_URL=https://api.deepseek.com

PowerShell

$env:OPENAI_API_KEY="your_deepseek_api_key_here"
$env:OPENAI_BASE_URL="https://api.deepseek.com"

string apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
string baseUrl = Environment.GetEnvironmentVariable("OPENAI_BASE_URL");

using System.Net.Http;
using System.Net.Http.Headers;

// Retrieve API key and base URL from environment variables
var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
var baseUri = Environment.GetEnvironmentVariable("OPENAI_BASE_URL");

// Ensure there's no trailing slash, then append the chat-completions path:
var endpoint = baseUri.TrimEnd('/') + "/v1/chat/completions";

using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);

using System.Net.Http;
using System.Net.Http.Headers;

// Retrieve API key and base URL from environment variables
var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
var baseUri = Environment.GetEnvironmentVariable("OPENAI_BASE_URL");

// Ensure there's no trailing slash, then append the chat-completions path:
var endpoint = baseUri.TrimEnd('/') + "/v1/chat/completions";

using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);

using System.Text;
using System.Threading.Tasks;

// Define a simple user message as a prompt
string prompt = "Can you tell me an engineering joke?";

// Build the JSON payload
var jsonPayload = $@"
{{
    ""model"": ""deepseek-ai/DeepSeek-V3"",
    ""messages"": [
        {{ ""role"": ""user"", ""content"": ""{prompt.Replace("\"", "\\\"")}"" }}
    ]
}}";

using var content = new StringContent(jsonPayload, Encoding.UTF8, "application/json");
var response = await client.PostAsync(endpoint, content);
var body = await response.Content.ReadAsStringAsync();

using System.Text;
using System.Threading.Tasks;

// Define a simple user message as a prompt
string prompt = "Can you tell me an engineering joke?";

// Build the JSON payload
var jsonPayload = $@"
{{
    ""model"": ""deepseek-ai/DeepSeek-V3"",
    ""messages"": [
        {{ ""role"": ""user"", ""content"": ""{prompt.Replace("\"", "\\\"")}"" }}
    ]
}}";

using var content = new StringContent(jsonPayload, Encoding.UTF8, "application/json");
var response = await client.PostAsync(endpoint, content);
var body = await response.Content.ReadAsStringAsync();

using System.Text.Json;

// If the call failed, print the raw error and exit
if (!response.IsSuccessStatusCode)
{
    Console.WriteLine($"Error ({response.StatusCode}): {body}");
    return;
}

// Extract the AI's reply from the API response
using var doc = JsonDocument.Parse(body);
var reply = doc.RootElement
               .GetProperty("choices")[0]
               .GetProperty("message")
               .GetProperty("content")
               .GetString();

// Show both the user's prompt and the AI's reply
Console.WriteLine("Prompt: " + prompt);
Console.WriteLine("Response: " + reply?.Trim());

using System.Text.Json;

// If the call failed, print the raw error and exit
if (!response.IsSuccessStatusCode)
{
    Console.WriteLine($"Error ({response.StatusCode}): {body}");
    return;
}

// Extract the AI's reply from the API response
using var doc = JsonDocument.Parse(body);
var reply = doc.RootElement
               .GetProperty("choices")[0]
               .GetProperty("message")
               .GetProperty("content")
               .GetString();

// Show both the user's prompt and the AI's reply
Console.WriteLine("Prompt: " + prompt);
Console.WriteLine("Response: " + reply?.Trim());

using System;
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text;
using System.Text.Json;
using System.Threading.Tasks;

namespace App
{
    public class Program
    {
        public static async Task Main(string[] args)
        {
            // Initialize API key and base URL from environment variables
            var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
            var baseUri = Environment.GetEnvironmentVariable("OPENAI_BASE_URL");
            if (string.IsNullOrEmpty(apiKey))
            {
                Console.WriteLine("Set your OPENAI_API_KEY.");
                return;
            }
            if (string.IsNullOrEmpty(baseUri))
            {
                Console.WriteLine("Set your OPENAI_BASE_URL (e.g. https://api.openai.com).");
                return;
            }

            // Ensure there's no trailing slash, then append the chat-completions path:
            var endpoint = baseUri.TrimEnd('/') + "/v1/chat/completions";

            using var client = new HttpClient();
            client.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);

            // Define a simple user message as a prompt
            string prompt = "Can you tell me an engineering joke?";

            // Build the JSON payload
            var jsonPayload = $@"
            {{
                ""model"": ""deepseek-ai/DeepSeek-V3"",
                ""messages"": [
                    {{ ""role"": ""user"", ""content"": ""{prompt.Replace("\"", "\\\"")}"" }}
                ]
            }}";

            using var content = new StringContent(jsonPayload, Encoding.UTF8, "application/json");
            var response = await client.PostAsync(endpoint, content);
            var body = await response.Content.ReadAsStringAsync();

            // If the call failed, print the raw error and exit
            if (!response.IsSuccessStatusCode)
            {
                Console.WriteLine($"Error ({response.StatusCode}): {body}");
                return;
            }

            // Extract the AI's reply from the API response
            using var doc = JsonDocument.Parse(body);
            var reply = doc.RootElement
                           .GetProperty("choices")[0]
                           .GetProperty("message")
                           .GetProperty("content")
                           .GetString();

            // Show both the user's prompt and the AI's reply
            Console.WriteLine("Prompt: " + prompt);
            Console.WriteLine("Response: " + reply?.Trim());
        }
    }
}

using System;
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text;
using System.Text.Json;
using System.Threading.Tasks;

namespace App
{
    public class Program
    {
        public static async Task Main(string[] args)
        {
            // Initialize API key and base URL from environment variables
            var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
            var baseUri = Environment.GetEnvironmentVariable("OPENAI_BASE_URL");
            if (string.IsNullOrEmpty(apiKey))
            {
                Console.WriteLine("Set your OPENAI_API_KEY.");
                return;
            }
            if (string.IsNullOrEmpty(baseUri))
            {
                Console.WriteLine("Set your OPENAI_BASE_URL (e.g. https://api.openai.com).");
                return;
            }

            // Ensure there's no trailing slash, then append the chat-completions path:
            var endpoint = baseUri.TrimEnd('/') + "/v1/chat/completions";

            using var client = new HttpClient();
            client.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);

            // Define a simple user message as a prompt
            string prompt = "Can you tell me an engineering joke?";

            // Build the JSON payload
            var jsonPayload = $@"
            {{
                ""model"": ""deepseek-ai/DeepSeek-V3"",
                ""messages"": [
                    {{ ""role"": ""user"", ""content"": ""{prompt.Replace("\"", "\\\"")}"" }}
                ]
            }}";

            using var content = new StringContent(jsonPayload, Encoding.UTF8, "application/json");
            var response = await client.PostAsync(endpoint, content);
            var body = await response.Content.ReadAsStringAsync();

            // If the call failed, print the raw error and exit
            if (!response.IsSuccessStatusCode)
            {
                Console.WriteLine($"Error ({response.StatusCode}): {body}");
                return;
            }

            // Extract the AI's reply from the API response
            using var doc = JsonDocument.Parse(body);
            var reply = doc.RootElement
                           .GetProperty("choices")[0]
                           .GetProperty("message")
                           .GetProperty("content")
                           .GetString();

            // Show both the user's prompt and the AI's reply
            Console.WriteLine("Prompt: " + prompt);
            Console.WriteLine("Response: " + reply?.Trim());
        }
    }
}

using System.Net.Http;
using System.Net.Http.Headers;

// Retrieve API key and base URL from environment variables
var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
var baseUri = Environment.GetEnvironmentVariable("OPENAI_BASE_URL");

// Ensure there's no trailing slash, then append the chat-completions path:
var endpoint = baseUri.TrimEnd('/') + "/v1/chat/completions";

using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);

using System.Text;
using System.Threading.Tasks;

// Define a simple user message as a prompt
string prompt = "Can you tell me an engineering joke?";

// Build the JSON payload
var jsonPayload = $@"
{{
    ""model"": ""deepseek-ai/DeepSeek-V3"",
    ""messages"": [
        {{ ""role"": ""user"", ""content"": ""{prompt.Replace("\"", "\\\"")}"" }}
    ]
}}";

using var content = new StringContent(jsonPayload, Encoding.UTF8, "application/json");
var response = await client.PostAsync(endpoint, content);
var body = await response.Content.ReadAsStringAsync();

using System.Text.Json;

// If the call failed, print the raw error and exit
if (!response.IsSuccessStatusCode)
{
    Console.WriteLine($"Error ({response.StatusCode}): {body}");
    return;
}

// Extract the AI's reply from the API response
using var doc = JsonDocument.Parse(body);
var reply = doc.RootElement
               .GetProperty("choices")[0]
               .GetProperty("message")
               .GetProperty("content")
               .GetString();

// Show both the user's prompt and the AI's reply
Console.WriteLine("Prompt: " + prompt);
Console.WriteLine("Response: " + reply?.Trim());

using System;
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text;
using System.Text.Json;
using System.Threading.Tasks;

namespace App
{
    public class Program
    {
        public static async Task Main(string[] args)
        {
            // Initialize API key and base URL from environment variables
            var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");
            var baseUri = Environment.GetEnvironmentVariable("OPENAI_BASE_URL");
            if (string.IsNullOrEmpty(apiKey))
            {
                Console.WriteLine("Set your OPENAI_API_KEY.");
                return;
            }
            if (string.IsNullOrEmpty(baseUri))
            {
                Console.WriteLine("Set your OPENAI_BASE_URL (e.g. https://api.openai.com).");
                return;
            }

            // Ensure there's no trailing slash, then append the chat-completions path:
            var endpoint = baseUri.TrimEnd('/') + "/v1/chat/completions";

            using var client = new HttpClient();
            client.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);

            // Define a simple user message as a prompt
            string prompt = "Can you tell me an engineering joke?";

            // Build the JSON payload
            var jsonPayload = $@"
            {{
                ""model"": ""deepseek-ai/DeepSeek-V3"",
                ""messages"": [
                    {{ ""role"": ""user"", ""content"": ""{prompt.Replace("\"", "\\\"")}"" }}
                ]
            }}";

            using var content = new StringContent(jsonPayload, Encoding.UTF8, "application/json");
            var response = await client.PostAsync(endpoint, content);
            var body = await response.Content.ReadAsStringAsync();

            // If the call failed, print the raw error and exit
            if (!response.IsSuccessStatusCode)
            {
                Console.WriteLine($"Error ({response.StatusCode}): {body}");
                return;
            }

            // Extract the AI's reply from the API response
            using var doc = JsonDocument.Parse(body);
            var reply = doc.RootElement
                           .GetProperty("choices")[0]
                           .GetProperty("message")
                           .GetProperty("content")
                           .GetString();

            // Show both the user's prompt and the AI's reply
            Console.WriteLine("Prompt: " + prompt);
            Console.WriteLine("Response: " + reply?.Trim());
        }
    }
}

Sending a Simple Query to DeepSeek

Setting Up Your Environment

Setting the DeepSeek API Key as an Environment Variable

Join the 1M+ learners on CodeSignal

Initializing the API Client for DeepSeek

Sending Your First Query to DeepSeek

Extracting and Displaying the AI's Reply

Example: Full Code Implementation

Summary and Next Steps