AVERTISSEMENT: CES PROJETS DE POSTES QUI 'ESCAPÉ'.
Il est probable qu'une grande partie de ce qui est ci-dessous ne fonctionnera pas; je les génère comme comment faire pour MOI, puis faire toutes les étapes et obtenir le travail de l'application d'échantillon ... Vous avez été sournois et les a vus! ils seront probablement prêts à la mi-décembre.
## Présentation
Bienvenue dans la 6ème partieQuatrième partie), client Windows (Cinquième partie) , l'intégration et la recherche vectorielle (Troisième partie) et configuration du GPU (Deuxième partie
Maintenant vient la partie passionnante: l'intégration d'un LLM local pour générer des suggestions d'écriture.
Même voix, même pragmatisme, juste des doigts plus rapides.
Nous allons exécuter de grands modèles de langue localement sur votre A4000 GPU, générant des suggestions contextuelles basées sur vos messages de blog passés. |--------|-----------|-------------------| | Pourquoi le LLM local ? | ✅ Complete | ❌ Data sent to third party | | Avant de plonger, comprenons pourquoi nous utilisons des modèles localement au lieu d'utiliser l'API d'OpenAI. | ✅ Free after setup | ❌ Per-token pricing | | Comparaison locale par rapport à l'API | ✅ <1 second | ⚠️ Network dependent | | L'API locale LLM (OpenAI, etc.) | ✅ Full control | ❌ Limited | | Vie privée | ✅ Any GGUF model | ❌ Provider's models only | | Coût | ✅ Works offline | ❌ Requires internet | | Latence | ❌ Complex | ✅ Simple |
Personnalisation
Hors ligne
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
Configuration
Pour un assistant à l'écriture, la vie privée et les coûts sont importants.
Accélération CUDA intégréeDéveloppement actif et grande communauté
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
Travaille avec Llama, Mistral, Phi, Gemma, et plus encore:
Modèle original : flotteurs 32 bits (très gros, très précis) |-------|---------------|------------|-----------|------------|------------|---------| | Q4 : 4 bits entiers (75% de plus petite taille, perte de qualité minimale) | 2.3GB | ~4GB | ✅ Easy | ✅ Easy | ✅ Easy | ⭐⭐⭐ Good | | Q5/Q6: Spot doux pour la plupart des cas d'utilisation | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐ Good | | Q8: Qualité presque originale, encore 4x plus petite | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐ Better | | Sélection du modèle par matériel | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐ Better | | Modèle Taille (Q4_K_M) Utilisation de VRAM Adapté à 8 Go? Adapté à 12 Go? Adapté à 16 Go? Adapté à la qualité | 4.7GB | ~7GB | ⚠️ Very Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐⭐ Best | | Mini Phi-3 (3.8B) | 7.4GB | ~10GB | ❌ No | ⚠️ Tight | ✅ Good | ⭐⭐⭐⭐ Better |
Lama 2 7B
Lama 3 8B: ou essayerModèles 13BCPU seulement: N'importe quel modèle fonctionne, juste beaucoup plus lentement (démarrer avec Phi-3 Mini pour la vitesse)
Excellente qualité pour l'écriture technique
"mistral 7b gguf"**Nous utiliserons des versions GGUF quantifiées.**Trouver des modèles GGUF
# 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
Liens directs
mistral-7b-instruct-v0.2.Q5_K_M.ggufLama-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
Rechercher
[LLamaSharp](https://github.com/SciSharp/LLamaSharp)(~4.8 Go)LLamaSharp.Backend.Cuda12 - Cliquez sur téléchargerEnregistrer dansInstaller le paquet NuGet
using LLama;
using LLama.Common;
// Check if CUDA is available
bool cudaAvailable = NativeLibraryConfig.Instance.CudaEnabled;
Console.WriteLine($"CUDA Available: {cudaAvailable}");
Pourquoi deux paquets ?false- Bibliothèque de base
LLamaSharp.Backend.Cuda1212 binaires pour accélération GPUusing 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
}
}
, vérifier::
**CUDA 12.x installé (partie 2)**paquet installé
Paramètres du modèleExplications des paramètres
Plus grand = plus de contexte mais plus lent et plus VRAMGpuLayerCount
Valeurs inférieures = utiliser moins de VRAM mais plus lentementTempérature
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+ = très créatif (peut être non sensoriel):
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);
}
}
: Jetons de flux tels qu'ils sont générés (sortie en temps réel):
=== 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.
Mise en place du contexte
Anti-promptes
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;
}
}
}
Le modèle fonctionne et génère un texte cohérent, conscient du contexte.
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;
}
}
Maintenant, intégrons la génération LLM dans notre client Windows à partir de la partie 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);
}
}
Mettre à jour le service Suggestions
Optimisation des performances
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;
}
Maintenez le modèle chargé entre les demandes :
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:";
}
Pour de multiples suggestions, faites-les par lots :
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);
}
}
Continuer d'écrire
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");
}
Exemple de code
Nous avons intégré avec succès l'inférence locale LLM :**LLamaSharp**pour l'intégration C#
Partie 7: Génération de contenu et génie rapide
Partie 6: Intégration locale des LLM(ce poste)!
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.