WAARSCHUWING: Deze zijn ontwerp-Posts die 'onthuld'.
Het is waarschijnlijk veel van wat hieronder zal niet werken; IK genereren deze als how-to voor MIJ en dan doen alle stappen en krijg de sample app werken...Je bent stiekem en ze gezien! ze zullen waarschijnlijk klaar zijn medio december.
## Inleiding
Welkom in deel 6Deel 4), Windows client (Deel 5), inbeddingen en vectorzoeken (Deel 3), en GPU setup (Deel 2
Nu komt het spannende deel: het integreren van een lokale LLM om daadwerkelijk schrijven suggesties te genereren.
Dezelfde stem, hetzelfde pragmatisme, gewoon snellere vingers.
We zullen grote taalmodellen lokaal uitvoeren op uw A4000 GPU, het genereren van context-aware suggesties op basis van uw vorige blog berichten. |--------|-----------|-------------------| | Waarom lokale LLM? | ✅ Complete | ❌ Data sent to third party | | Voordat we naar binnen duiken, laten we begrijpen waarom we modellen lokaal draaien in plaats van OpenAI's API te gebruiken. | ✅ Free after setup | ❌ Per-token pricing | | Lokale vergelijking vs. API | ✅ <1 second | ⚠️ Network dependent | | Lokaal LLM API (OpenAI, enz.) | ✅ Full control | ❌ Limited | | Privacy | ✅ Any GGUF model | ❌ Provider's models only | | Kosten | ✅ Works offline | ❌ Requires internet | | Matigheid | ❌ Complex | ✅ Simple |
Aanpassen
Offline
graph TB
A[C# Application] --> B{Integration Method}
B --> C[LLamaSharp]
B --> D[ONNX Runtime]
B --> E[TorchSharp]
B --> F[HTTP API]
C --> G[llama.cpp bindings]
G --> H[GGUF Models]
D --> I[ONNX Models]
I --> J[Limited Model Support]
E --> K[PyTorch Models]
K --> L[Complex Setup]
F --> M[External Process]
M --> N[Ollama, LM Studio]
class C recommended
class G,H llamaSharp
classDef recommended stroke:#333,stroke-width:4px
classDef llamaSharp stroke:#333,stroke-width:2px
Instellen
Voor een schrijfassistent, privacy en kosten.
CUDA-versnelling ingebouwdActieve ontwikkeling en grote gemeenschap
graph LR
A[Original Model<br/>Llama 2 7B<br/>~28GB float32] --> B[Quantization]
B --> C[Q4_K_M<br/>~4.1GB<br/>4-bit]
B --> D[Q5_K_M<br/>~4.8GB<br/>5-bit]
B --> E[Q6_K<br/>~5.5GB<br/>6-bit]
B --> F[Q8_0<br/>~7.2GB<br/>8-bit]
C --> G[Fast, Lower Quality]
D --> H[Balanced]
E --> I[Higher Quality]
F --> J[Near Original]
class A original
class C,D quantized
class H recommended
classDef original stroke:#333,stroke-width:2px
classDef quantized stroke:#333,stroke-width:2px
classDef recommended stroke:#333,stroke-width:2px
Werkt met Llama, Mistral, Phi, Gemma, en nog veel meer:
Origineel model: 32-bits praalwagens (zeer groot, zeer nauwkeurig) |-------|---------------|------------|-----------|------------|------------|---------| | Q4: 4-bit gehele getallen (75% kleiner, minimaal kwaliteitsverlies) | 2.3GB | ~4GB | ✅ Easy | ✅ Easy | ✅ Easy | ⭐⭐⭐ Good | | Q5/Q6: Zoete plek voor de meeste gebruiks gevallen | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐ Good | | Q8: Bijna-originele kwaliteit, nog 4x kleiner | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐ Better | | Modelselectie door Hardware | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐ Better | | Maat (Q4_K_M) VRAM-gebruik Past 8GB? Past 12GB? Past 16GB? Kwaliteit | 4.7GB | ~7GB | ⚠️ Very Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐⭐ Best | | Phi-3 Mini (3.8B) | 7.4GB | ~10GB | ❌ No | ⚠️ Tight | ✅ Good | ⭐⭐⭐⭐ Better |
Llama 2 7B
Llama 3 8B: of probeer13B modellenAlleen CPU: Elk model werkt, net veel langzamer (begin met Phi-3 Mini voor snelheid)
Uitstekende kwaliteit voor technisch schrijven
"mistral 7b gguf"**We gebruiken quantized GGUF versies.**GGUF-modellen vinden
# Install huggingface-cli
pip install huggingface-hub
# Download Mistral 7B Q5_K_M (recommended)
huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.2-GGUF \
mistral-7b-instruct-v0.2.Q5_K_M.gguf \
--local-dir C:\models\mistral-7b \
--local-dir-use-symlinks False
Directe links
mistral-7b-instruct-v0.2.Q5_K_M.ggufLlama-2-7B-Chat-GGUFC:\models\mistral-7b\cd Mostlylucid.BlogLLM.Core
dotnet add package LLamaSharp # Latest version
dotnet add package LLamaSharp.Backend.Cuda12 # Latest, matching CUDA version
Zoeken
[LLamaSharp](https://github.com/SciSharp/LLamaSharp)(~4,8 GB)LLamaSharp.Backend.Cuda12 - Klik op downloadenOpslaan naarPakket NuGet installeren
using LLama;
using LLama.Common;
// Check if CUDA is available
bool cudaAvailable = NativeLibraryConfig.Instance.CudaEnabled;
Console.WriteLine($"CUDA Available: {cudaAvailable}");
Waarom twee pakjes?false- Kernbibliotheek
LLamaSharp.Backend.Cuda1212 binaries voor GPU acceleratieusing LLama;
using LLama.Common;
namespace Mostlylucid.BlogLLM.Core.Services
{
public class ModelParameters
{
public string ModelPath { get; set; } = string.Empty;
public int ContextSize { get; set; } = 4096; // Context window
public int GpuLayerCount { get; set; } = 35; // Layers on GPU (35 = all for 7B)
public int Seed { get; set; } = 1337; // For reproducibility
public float Temperature { get; set; } = 0.7f; // Creativity (0.0 = deterministic, 1.0 = creative)
public float TopP { get; set; } = 0.9f; // Nucleus sampling
public int MaxTokens { get; set; } = 500; // Max generation length
}
}
, controleer::
**CUDA 12.x geïnstalleerd (deel 2)**pakket geïnstalleerd
ModelparametersUitleg van parameters
Groter = meer context maar langzamer en meer VRAMGpuLayerCount
Lagere waarden = minder VRAM maar langzamer gebruikenTemperatuur
using LLama;
using LLama.Common;
using Microsoft.Extensions.Logging;
namespace Mostlylucid.BlogLLM.Core.Services
{
public interface ILlmService
{
Task<string> GenerateAsync(string prompt, CancellationToken cancellationToken = default);
Task<string> GenerateWithContextAsync(string prompt, List<string> contextChunks, CancellationToken cancellationToken = default);
}
public class LlmService : ILlmService, IDisposable
{
private readonly LLamaWeights _model;
private readonly LLamaContext _context;
private readonly ILogger<LlmService> _logger;
private readonly ModelParameters _parameters;
public LlmService(ModelParameters parameters, ILogger<LlmService> logger)
{
_parameters = parameters;
_logger = logger;
_logger.LogInformation("Loading model from {ModelPath}", parameters.ModelPath);
// Configure model parameters
var modelParams = new ModelParams(parameters.ModelPath)
{
ContextSize = (uint)parameters.ContextSize,
GpuLayerCount = parameters.GpuLayerCount,
Seed = (uint)parameters.Seed,
UseMemoryLock = true, // Keep model in RAM
UseMemorymap = true // Memory-map the model file
};
// Load model
_model = LLamaWeights.LoadFromFile(modelParams);
_context = _model.CreateContext(modelParams);
_logger.LogInformation("Model loaded successfully. VRAM used: ~{VRAM}GB",
EstimateVRAMUsage(parameters.GpuLayerCount));
}
public async Task<string> GenerateAsync(string prompt, CancellationToken cancellationToken = default)
{
var executor = new InteractiveExecutor(_context);
var inferenceParams = new InferenceParams
{
Temperature = _parameters.Temperature,
TopP = _parameters.TopP,
MaxTokens = _parameters.MaxTokens,
AntiPrompts = new[] { "\n\nUser:", "###" } // Stop generation at these
};
var result = new StringBuilder();
_logger.LogInformation("Generating response for prompt: {Prompt}", TruncateForLog(prompt));
await foreach (var token in executor.InferAsync(prompt, inferenceParams, cancellationToken))
{
result.Append(token);
}
var response = result.ToString().Trim();
_logger.LogInformation("Generated {Tokens} tokens", CountTokens(response));
return response;
}
public async Task<string> GenerateWithContextAsync(
string prompt,
List<string> contextChunks,
CancellationToken cancellationToken = default)
{
// Build prompt with retrieved context
var fullPrompt = BuildContextualPrompt(prompt, contextChunks);
_logger.LogInformation("Context chunks: {Count}, Total prompt tokens: ~{Tokens}",
contextChunks.Count, CountTokens(fullPrompt));
return await GenerateAsync(fullPrompt, cancellationToken);
}
private string BuildContextualPrompt(string userPrompt, List<string> contextChunks)
{
var sb = new StringBuilder();
sb.AppendLine("You are a helpful writing assistant for a technical blog.");
sb.AppendLine("Use the following excerpts from past blog posts as context:");
sb.AppendLine();
for (int i = 0; i < contextChunks.Count; i++)
{
sb.AppendLine($"--- Context {i + 1} ---");
sb.AppendLine(contextChunks[i]);
sb.AppendLine();
}
sb.AppendLine("---");
sb.AppendLine();
sb.AppendLine("Based on the context above, help with the following:");
sb.AppendLine(userPrompt);
sb.AppendLine();
sb.AppendLine("Response:");
return sb.ToString();
}
private int CountTokens(string text)
{
// Rough estimate: 1 token ≈ 4 characters
return text.Length / 4;
}
private string TruncateForLog(string text, int maxLength = 100)
{
if (text.Length <= maxLength) return text;
return text.Substring(0, maxLength) + "...";
}
private double EstimateVRAMUsage(int gpuLayers)
{
// Rough estimate for 7B model
return (gpuLayers / 35.0) * 6.0; // ~6GB for full 7B model
}
public void Dispose()
{
_context?.Dispose();
_model?.Dispose();
}
}
}
1.0+ = zeer creatief (kan nonsensisch zijn):
using Microsoft.Extensions.Logging;
class Program
{
static async Task Main(string[] args)
{
// Setup logging
var loggerFactory = LoggerFactory.Create(builder => builder.AddConsole());
var logger = loggerFactory.CreateLogger<LlmService>();
// Configure model
var parameters = new ModelParameters
{
ModelPath = @"C:\models\mistral-7b\mistral-7b-instruct-v0.2.Q5_K_M.gguf",
ContextSize = 4096,
GpuLayerCount = 35,
Temperature = 0.7f,
MaxTokens = 200
};
// Create service
using var llmService = new LlmService(parameters, logger);
// Test simple generation
Console.WriteLine("=== Test 1: Simple Generation ===\n");
var response1 = await llmService.GenerateAsync(
"Explain what Docker Compose is in 2-3 sentences."
);
Console.WriteLine(response1);
Console.WriteLine("\n");
// Test with context
Console.WriteLine("=== Test 2: Generation with Context ===\n");
var context = new List<string>
{
"Docker Compose is a tool for defining and running multi-container Docker applications. With Compose, you use a YAML file to configure your application's services.",
"In development, Docker Compose makes it easy to spin up all dependencies (databases, caches, etc.) with one command: docker-compose up."
};
var response2 = await llmService.GenerateWithContextAsync(
"Write an introduction paragraph for a blog post about using Docker Compose for development dependencies.",
context
);
Console.WriteLine(response2);
}
}
: Streams tokens als ze worden gegenereerd (real-time output):
=== Test 1: Simple Generation ===
Docker Compose is a tool that allows you to define and run multi-container Docker applications using a simple YAML configuration file. It simplifies the process of managing multiple containers, networking, and volumes, making it ideal for development environments.
=== Test 2: Generation with Context ===
If you've ever found yourself juggling multiple terminal windows to start databases, caches, and other services for local development, Docker Compose is about to become your new best friend. This powerful tool lets you define your entire development environment in a single YAML file and spin everything up with one command. In this post, we'll explore how to leverage Docker Compose to manage all your development dependencies, making your local setup reproducible, shareable, and incredibly easy to manage.
Contextgebouw
Antiprompts
namespace Mostlylucid.BlogLLM.Client.Services
{
public class SuggestionService : ISuggestionService
{
private readonly BatchEmbeddingService _embeddingService;
private readonly QdrantVectorStore _vectorStore;
private readonly ILlmService _llmService; // NEW
public SuggestionService(
BatchEmbeddingService embeddingService,
QdrantVectorStore vectorStore,
ILlmService llmService) // NEW
{
_embeddingService = embeddingService;
_vectorStore = vectorStore;
_llmService = llmService;
}
public async Task<string> GenerateAiSuggestionAsync(
string currentText,
List<SimilarPost> context)
{
// Extract text from similar posts
var contextChunks = context
.Take(3) // Top 3 most similar
.Select(p => p.FullText)
.ToList();
// Determine what type of suggestion to generate
var prompt = DeterminePromptType(currentText);
// Generate suggestion
var suggestion = await _llmService.GenerateWithContextAsync(
prompt,
contextChunks
);
return suggestion;
}
private string DeterminePromptType(string currentText)
{
// Analyze what user is writing
var lines = currentText.Split('\n');
var lastLine = lines.LastOrDefault(l => !string.IsNullOrWhiteSpace(l)) ?? "";
// Is user starting a new section?
if (lastLine.StartsWith("## "))
{
return "Suggest 3-5 bullet points for what this section could cover.";
}
// Is user writing code?
if (lastLine.Contains("```"))
{
return "Suggest relevant code examples that might be useful here.";
}
// Is user writing an introduction?
if (currentText.Length < 500 && currentText.Contains("## Introduction"))
{
return "Suggest 2-3 sentences to continue this introduction based on similar posts.";
}
// Default: continue current thought
return "Suggest 1-2 sentences to continue the current paragraph in a natural way.";
}
}
}
public partial class SuggestionsViewModel : ViewModelBase
{
[RelayCommand]
private async Task RegenerateSuggestion()
{
IsGenerating = true;
AiSuggestion = "Generating...";
try
{
var currentText = GetCurrentEditorText(); // From messaging
var suggestion = await _suggestionService.GenerateAiSuggestionAsync(
currentText,
SimilarPosts.ToList()
);
AiSuggestion = suggestion;
}
catch (Exception ex)
{
AiSuggestion = $"Error: {ex.Message}";
}
finally
{
IsGenerating = false;
}
}
}
Het model werkt en genereert coherente, contextbewuste tekst.
public class LlmServiceFactory
{
private static LlmService? _instance;
private static readonly object _lock = new();
public static LlmService GetInstance(ModelParameters parameters, ILogger<LlmService> logger)
{
if (_instance == null)
{
lock (_lock)
{
if (_instance == null)
{
_instance = new LlmService(parameters, logger);
}
}
}
return _instance;
}
}
Laten we nu LLM-generatie integreren in onze Windows-client van deel 5.
public class StatefulLlmService
{
private readonly InferenceParams _defaultParams;
private string _cachedPromptPrefix = string.Empty;
public async Task<string> GenerateWithPrefixAsync(string prefix, string newPrompt)
{
// If prefix matches cached, reuse KV cache
if (prefix == _cachedPromptPrefix)
{
// Only process new tokens
return await GenerateAsync(newPrompt);
}
// Process entire prompt and cache
_cachedPromptPrefix = prefix;
return await GenerateAsync(prefix + newPrompt);
}
}
SuggestieService bijwerken
Optimalisatie van de prestaties
public async Task<List<string>> GenerateBatchAsync(List<string> prompts)
{
var results = new List<string>();
foreach (var prompt in prompts)
{
// With KV cache reuse, subsequent prompts are faster
results.Add(await GenerateAsync(prompt));
}
return results;
}
Houd het model geladen tussen de verzoeken:
private string PromptContinueWriting(string currentText, List<string> context)
{
return $@"You are a technical blog writing assistant.
Here are excerpts from similar blog posts:
{string.Join("\n\n", context.Select((c, i) => $"--- Post {i + 1} ---\n{c}"))}
Current draft:
{currentText}
Task: Suggest 2-3 sentences to naturally continue the current paragraph.
Keep the same technical depth and casual, pragmatic tone.
Suggestion:";
}
private string PromptSectionStructure(string sectionTitle, List<string> context)
{
return $@"You are a technical blog writing assistant.
Similar sections from past posts:
{string.Join("\n\n", context)}
New section: {sectionTitle}
Task: Suggest 4-6 bullet points for what this section should cover.
Format as a markdown list.
Bullets:";
}
private string PromptCodeExample(string description, List<string> context)
{
return $@"You are a C# coding assistant.
Relevant code from past posts:
{string.Join("\n\n", context)}
Task: {description}
Provide a clean, well-commented C# code example.
Code:";
}
Voor meerdere suggesties, batch ze:
public class VramMonitor
{
[DllImport("nvml.dll")]
private static extern int nvmlDeviceGetMemoryInfo(IntPtr device, ref NvmlMemory memory);
[StructLayout(LayoutKind.Sequential)]
public struct NvmlMemory
{
public ulong Total;
public ulong Free;
public ulong Used;
}
public static (ulong used, ulong total) GetVramUsage()
{
// Simplified - actual implementation needs proper NVML initialization
var memory = new NvmlMemory();
// nvmlDeviceGetMemoryInfo(device, ref memory);
return (memory.Used / 1024 / 1024, memory.Total / 1024 / 1024); // Convert to MB
}
}
public class LlmServiceWithUnload : IDisposable
{
private LlmService? _service;
private readonly Timer _unloadTimer;
private DateTime _lastUsed;
public LlmServiceWithUnload()
{
_unloadTimer = new Timer(CheckForUnload, null, TimeSpan.FromMinutes(1), TimeSpan.FromMinutes(1));
}
private void CheckForUnload(object? state)
{
if (_service != null && (DateTime.Now - _lastUsed) > TimeSpan.FromMinutes(10))
{
_service.Dispose();
_service = null;
GC.Collect();
Console.WriteLine("Model unloaded due to inactivity");
}
}
public async Task<string> GenerateAsync(string prompt)
{
_lastUsed = DateTime.Now;
if (_service == null)
{
// Reload model
_service = CreateService();
}
return await _service.GenerateAsync(prompt);
}
}
Schrijven verder
public async Task<string> GenerateWithRetryAsync(string prompt, int maxRetries = 3)
{
for (int i = 0; i < maxRetries; i++)
{
try
{
return await GenerateAsync(prompt);
}
catch (OutOfMemoryException)
{
_logger.LogWarning("OOM error, reducing max tokens");
_parameters.MaxTokens = Math.Max(100, _parameters.MaxTokens / 2);
}
catch (Exception ex)
{
_logger.LogError(ex, "Generation failed, attempt {Attempt}/{Max}", i + 1, maxRetries);
if (i == maxRetries - 1) throw;
await Task.Delay(1000 * (i + 1)); // Exponential backoff
}
}
throw new Exception("Generation failed after retries");
}
Codevoorbeeld
We hebben de lokale LLM-inferentie succesvol geïntegreerd:**LLamaSharp**voor C# integratie
Deel 7: Content Generation & Prompt Engineering
Deel 6: Lokale LLM-integratie(dit bericht)!
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.