VARNING: DETTA UTKASTS TILL POSTER SOM "FÖRSÄKRATS".
Det är troligt att mycket av det som är nedan inte kommer att fungera; Jag genererar dessa som hur-till för MIG och sedan göra alla steg och få provappen att fungera ... Du har varit smygande och sett dem! de kommer sannolikt att vara redo i mitten av december.
## Inledning
Välkommen till del 6Häfte 4), Windows-klient (Häfte 5), inbäddningar och vektorsökning (Häfte 3) och GPU-inställning (Häfte 2
Nu kommer den spännande delen: att integrera en lokal LLM för att faktiskt generera skrivförslag.
Samma röst, samma pragmatism, bara snabbare fingrar.
Vi kommer att köra stora språkmodeller lokalt på din A4000 GPU, generera sammanhangsmedvetna förslag baserat på dina tidigare blogginlägg. |--------|-----------|-------------------| | Varför lokal LLM? | ✅ Complete | ❌ Data sent to third party | | Innan du dyker in, låt oss förstå varför vi kör modeller lokalt istället för att använda OpenAI:s API. | ✅ Free after setup | ❌ Per-token pricing | | Lokal jämförelse mot API | ✅ <1 second | ⚠️ Network dependent | | (OpenAI, etc.) | ✅ Full control | ❌ Limited | | Sekretess | ✅ Any GGUF model | ❌ Provider's models only | | Kostnad | ✅ Works offline | ❌ Requires internet | | Tröskelvärde | ❌ Complex | ✅ Simple |
Anpassning
Avstängning
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
Ställ in
För en skrivassistent, privatliv och kostnad.
CUDA-acceleration inbyggdAktiv utveckling och stor gemenskap
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
Jobbar med Llama, Mistral, Phi, Gemma med mera:
Originalmodell: 32-bitars flottar (mycket stora, mycket exakta) |-------|---------------|------------|-----------|------------|------------|---------| | Q4: 4-bitars heltal (75% mindre, minimal kvalitetsförlust) | 2.3GB | ~4GB | ✅ Easy | ✅ Easy | ✅ Easy | ⭐⭐⭐ Good | | Q5/Q6: Söt plats för de flesta användningsfall | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐ Good | | Q8: Nära originalkvaliteten, fortfarande 4x mindre | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐ Better | | Modellval av maskinvara | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐ Better | | Förlaga på storlek (Q4_K_M) på VRAM-användning passar 8GB? och passar 12GB? och passar 16GB? | 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: eller försök13B-modellerEndast processor: Alla modeller fungerar, bara mycket långsammare (börja med Phi-3 Mini för hastighet)
Utmärkt kvalitet för tekniskt skrivande
"mistral 7b gguf"**Vi använder kvantiserade GGUF-versioner.**Hitta GGUF-modeller
# 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
Direktlänkar
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
Sök
[LLamaSharp](https://github.com/SciSharp/LLamaSharp)(~4,8GB)LLamaSharp.Backend.Cuda12 - Klicka på nedladdningSpara tillInstallera NuGet- paket
using LLama;
using LLama.Common;
// Check if CUDA is available
bool cudaAvailable = NativeLibraryConfig.Instance.CudaEnabled;
Console.WriteLine($"CUDA Available: {cudaAvailable}");
Varför två paket?false- Kärnbibliotek
LLamaSharp.Backend.Cuda1212 binärer för GPU-accelerationusing 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
}
}
, kontrollera::
**CUDA 12.x installerad (del 2)**paket installerat
Förlaga till parametrarParameter förklaringar
Större = mer sammanhang men långsammare och mer VRAMLandning av GpuLayer
Lägre värden = använd mindre VRAM men långsammareTemperatur
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+ = mycket kreativt (kan vara meningslöst):
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);
}
}
: Strömmar polletter som de genereras (realtidsutmatning):
=== 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.
Sammanhangsbyggnad
Anti-promptmedel
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;
}
}
}
Modellen fungerar och genererar sammanhängande, sammanhangsmedveten text.
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;
}
}
Låt oss nu integrera LLM-generationen i vår Windows-klient från del 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);
}
}
Uppdatera förslagstjänst
Prestandaoptimering
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;
}
Håll modellen laddad mellan förfrågningar:
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:";
}
För flera förslag, batch dem:
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);
}
}
Fortsätt skriva
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");
}
Exempel på kod
Vi har framgångsrikt integrerat lokala LLM-slutsatser:**LLamaSharp Ordförande**för integrering av C#
Del 7: Innehållsgenerering och snabbteknik
Del 6: Lokal LLM-integration(detta inlägg)!
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.