ΣτοΣειρά 8-μερών "Δικηγόρος GPT", σας έδειξα πώς να χτίσει μια πλήρη τοπική RAG-based βοηθός γραφής χρησιμοποιώντας GPU επιτάχυνση, τοπικές LLMs, και διανυσματική βάση δεδομένων.
Είναι πανίσχυρο, ιδιωτικό, και τρέχει εντελώς στο υλικό σας.
Αλλά ας είμαστε ειλικρινείς - δεν έχουν όλοι μια θέση εργασίας με μια NVIDIA GPU, 96GB της RAM, και την υπομονή να δημιουργήσει CUDA, cudNN, και wangle GGUF μοντέλα.
Κι αν θέλεις τα οφέλη ενός βοηθού στο blog χωρίς την επένδυση υλικού;
Το άρθρο αυτό παρουσιάζει την εναλλακτική λύση με βάση το σύννεφο: ίδια προσέγγιση RAG, ίδια Qdrant διανυσματική βάση δεδομένων, αλλά χρησιμοποιώντας cloud LLM APIs αντί για τοπικά συμπεράσματα.
Αυτό που μπορώ να πω είναι ότι αυτή η προσέγγιση σύννεφο έχει αποδειχθεί εξαιρετικά απλή για να συσταθεί σε σύγκριση με τη διαδρομή GPU.
Απαιτεί NVIDIA GPU (8GB+ VRAM)
Cross-platform (Windows, Mac, Linux)
Καλύτερη ποιότητα παραγωγής (μεγαλύτερη, πιο ικανή μοντέλα) |--------------------|-------------------| Κόστος API (αν και εύλογο για προσωπική χρήση) Δεδομένα που αποστέλλονται σε τρίτους APIs Η πληρότητα εξαρτάται από το δίκτυο Πότε να χρησιμοποιήσετε ποια;
Η προστασία της ιδιωτικής ζωής είναι ζωτικής σημασίας.
graph TB
A[Markdown Files] -->|Ingest| B[Chunking Service]
B -->|Text Chunks| C[Cloud Embedding API]
C -->|Vectors| D[Qdrant Vector DB]
E[User Writing] -->|Current Draft| F[Web/Desktop Client]
F -->|Embed Context| C
C -->|Query Vector| D
D -->|Similar Content| G[Context Builder]
G -->|Relevant Past Articles| H[Prompt Engineer]
H -->|Prompt + Context| I[Cloud LLM API]
I -->|Generated Suggestions| J[Response Handler]
J -->|Suggestions + Citations| F
F -->|Display| K[Editor with Suggestions]
class C,I cloud
class D,K local
classDef cloud stroke:#f96,stroke-width:4px
classDef local stroke:#333,stroke-width:2px
□ Έχετε GPU υλικό Είστε σε Mac / Linux / laptop
text-embedding-3-smallΑρχιτεκτονική επισκόπηση: Claude 3.5 Sonnet ή GPT-4 API αντί της τοπικής Mistral/Llama
Blazor WebAssembley
docker run -p 6333:6333 -p 6334:6334 \
-v $(pwd)/qdrant_storage:/qdrant/storage:z \
qdrant/qdrant
- Web-based, λειτουργεί οπουδήποτε
Εγκατάσταση Qdrant
**Επιλογή Β: Σύννεφο Qdrant (Ευκολότερο)**Εγγραφείτε στο
**2.**Πάρτε τα κλειδιά API
Δημιουργία κλειδιού APIappsettings.json:
{
"BlogRAG": {
"Embedding": {
"Provider": "OpenAI",
"Model": "text-embedding-3-small",
"ApiKey": "sk-..."
},
"LLM": {
"Provider": "Anthropic",
"Model": "claude-3-5-sonnet-20241022",
"ApiKey": "sk-ant-..."
},
"VectorStore": {
"Type": "Qdrant",
"Url": "http://localhost:6333",
"ApiKey": "",
"CollectionName": "blog_embeddings"
},
"Ingestion": {
"MarkdownPath": "/path/to/your/blog/Markdown",
"ChunkSize": 500,
"ChunkOverlap": 50
}
}
}
**Ορισμός ορίων χρήσης (σημαντικό!)**Ανθρωπιστικό
using OpenAI;
using OpenAI.Embeddings;
namespace BlogRAG.Services
{
public interface IEmbeddingService
{
Task<float[]> GenerateEmbeddingAsync(string text);
Task<List<float[]>> GenerateBatchEmbeddingsAsync(List<string> texts);
}
public class OpenAIEmbeddingService : IEmbeddingService
{
private readonly OpenAIClient _client;
private readonly string _model;
private readonly ILogger<OpenAIEmbeddingService> _logger;
public OpenAIEmbeddingService(
string apiKey,
string model,
ILogger<OpenAIEmbeddingService> logger)
{
_client = new OpenAIClient(apiKey);
_model = model;
_logger = logger;
}
public async Task<float[]> GenerateEmbeddingAsync(string text)
{
var embeddings = await GenerateBatchEmbeddingsAsync(new List<string> { text });
return embeddings.First();
}
public async Task<List<float[]>> GenerateBatchEmbeddingsAsync(List<string> texts)
{
_logger.LogInformation("Generating embeddings for {Count} texts", texts.Count);
var request = new EmbeddingRequest
{
Input = texts,
Model = _model
};
var response = await _client.CreateEmbeddingAsync(request);
return response.Data
.OrderBy(e => e.Index)
.Select(e => e.Embedding.ToArray())
.ToList();
}
}
}
Δημιουργία κλειδιού API
**Καμία ρύθμιση GPU, καμία λήψη μοντέλου (12GB αρχεία), καμία διαχείριση VRAM.**Εφαρμογή
using Anthropic.SDK;
using Anthropic.SDK.Messaging;
namespace BlogRAG.Services
{
public interface ILLMService
{
Task<string> GenerateCompletionAsync(
string systemPrompt,
string userPrompt,
float temperature = 0.7f);
IAsyncEnumerable<string> GenerateStreamingCompletionAsync(
string systemPrompt,
string userPrompt,
float temperature = 0.7f);
}
public class ClaudeLLMService : ILLMService
{
private readonly AnthropicClient _client;
private readonly string _model;
private readonly ILogger<ClaudeLLMService> _logger;
public ClaudeLLMService(
string apiKey,
string model,
ILogger<ClaudeLLMService> logger)
{
_client = new AnthropicClient(new APIAuthentication(apiKey));
_model = model;
_logger = logger;
}
public async Task<string> GenerateCompletionAsync(
string systemPrompt,
string userPrompt,
float temperature = 0.7f)
{
_logger.LogInformation("Generating completion with temperature {Temp}", temperature);
var messages = new List<Message>
{
new Message
{
Role = RoleType.User,
Content = userPrompt
}
};
var request = new MessageRequest
{
Model = _model,
MaxTokens = 2048,
Temperature = temperature,
System = systemPrompt,
Messages = messages
};
var response = await _client.Messages.CreateAsync(request);
return response.Content.First().Text;
}
public async IAsyncEnumerable<string> GenerateStreamingCompletionAsync(
string systemPrompt,
string userPrompt,
float temperature = 0.7f)
{
var messages = new List<Message>
{
new Message { Role = RoleType.User, Content = userPrompt }
};
var request = new MessageRequest
{
Model = _model,
MaxTokens = 2048,
Temperature = temperature,
System = systemPrompt,
Messages = messages,
Stream = true
};
await foreach (var chunk in _client.Messages.StreamAsync(request))
{
if (chunk.Delta?.Text != null)
{
yield return chunk.Delta.Text;
}
}
}
}
}
Βασικά οφέλη έναντι τοπικών:
Κόστος:
using Qdrant.Client;
using Qdrant.Client.Grpc;
namespace BlogRAG.Services
{
public class QdrantVectorStore
{
private readonly QdrantClient _client;
private readonly string _collectionName;
private readonly ILogger<QdrantVectorStore> _logger;
public QdrantVectorStore(
string url,
string apiKey,
string collectionName,
ILogger<QdrantVectorStore> logger)
{
_client = new QdrantClient(url, apiKey: apiKey);
_collectionName = collectionName;
_logger = logger;
}
public async Task CreateCollectionAsync(int vectorSize)
{
var collections = await _client.ListCollectionsAsync();
if (collections.Any(c => c.Name == _collectionName))
{
_logger.LogInformation("Collection {Name} already exists", _collectionName);
return;
}
await _client.CreateCollectionAsync(
collectionName: _collectionName,
vectorsConfig: new VectorParams
{
Size = (ulong)vectorSize,
Distance = Distance.Cosine
});
_logger.LogInformation("Created collection {Name}", _collectionName);
}
public async Task UpsertAsync(
Guid id,
float[] vector,
Dictionary<string, object> payload)
{
var point = new PointStruct
{
Id = id,
Vectors = vector,
Payload = payload
};
await _client.UpsertAsync(_collectionName, new[] { point });
}
public async Task<List<ScoredPoint>> SearchAsync(
float[] queryVector,
int limit = 10,
float scoreThreshold = 0.7f)
{
var results = await _client.SearchAsync(
collectionName: _collectionName,
vector: queryVector,
limit: (ulong)limit,
scoreThreshold: scoreThreshold);
return results.ToList();
}
}
}
**Οφέλη έναντι τοπικών:**Κανένα μοντέλο φόρτωσης (άμεση εκκίνηση)
namespace BlogRAG.Services
{
public class IngestionService
{
private readonly IEmbeddingService _embedder;
private readonly QdrantVectorStore _vectorStore;
private readonly ILogger<IngestionService> _logger;
public IngestionService(
IEmbeddingService embedder,
QdrantVectorStore vectorStore,
ILogger<IngestionService> logger)
{
_embedder = embedder;
_vectorStore = vectorStore;
_logger = logger;
}
public async Task IngestMarkdownFilesAsync(string markdownPath)
{
var files = Directory.GetFiles(markdownPath, "*.md", SearchOption.AllDirectories);
_logger.LogInformation("Found {Count} markdown files", files.Length);
foreach (var file in files)
{
await IngestFileAsync(file);
}
}
private async Task IngestFileAsync(string filePath)
{
var content = await File.ReadAllTextAsync(filePath);
var metadata = ExtractMetadata(content);
var chunks = ChunkContent(content);
_logger.LogInformation("Processing {File}: {ChunkCount} chunks",
Path.GetFileName(filePath), chunks.Count);
// Batch embedding generation
var texts = chunks.Select(c => c.Text).ToList();
var embeddings = await _embedder.GenerateBatchEmbeddingsAsync(texts);
// Upload to Qdrant
for (int i = 0; i < chunks.Count; i++)
{
var chunk = chunks[i];
var embedding = embeddings[i];
var payload = new Dictionary<string, object>
{
["text"] = chunk.Text,
["file_path"] = filePath,
["blog_post_slug"] = metadata.Slug,
["blog_post_title"] = metadata.Title,
["chunk_index"] = i,
["category"] = metadata.Category
};
await _vectorStore.UpsertAsync(Guid.NewGuid(), embedding, payload);
}
_logger.LogInformation("Ingested {File}", Path.GetFileName(filePath));
}
private List<TextChunk> ChunkContent(string content, int chunkSize = 500, int overlap = 50)
{
// Simple sentence-aware chunking
var sentences = content.Split(new[] { ". ", ".\n", "!\n", "?\n" },
StringSplitOptions.RemoveEmptyEntries);
var chunks = new List<TextChunk>();
var currentChunk = new StringBuilder();
var currentLength = 0;
foreach (var sentence in sentences)
{
if (currentLength + sentence.Length > chunkSize && currentChunk.Length > 0)
{
chunks.Add(new TextChunk { Text = currentChunk.ToString() });
// Overlap: keep last sentence
currentChunk.Clear();
currentLength = 0;
}
currentChunk.Append(sentence).Append(". ");
currentLength += sentence.Length;
}
if (currentChunk.Length > 0)
{
chunks.Add(new TextChunk { Text = currentChunk.ToString() });
}
return chunks;
}
private BlogMetadata ExtractMetadata(string content)
{
// Extract from markdown frontmatter or HTML comments
var titleMatch = Regex.Match(content, @"^#\s+(.+)$", RegexOptions.Multiline);
var categoryMatch = Regex.Match(content, @"");
return new BlogMetadata
{
Title = titleMatch.Success ? titleMatch.Groups[1].Value : "Untitled",
Category = categoryMatch.Success ? categoryMatch.Groups[1].Value : "General",
Slug = Path.GetFileNameWithoutExtension(content)
};
}
}
public class TextChunk
{
public string Text { get; set; } = string.Empty;
}
public class BlogMetadata
{
public string Title { get; set; } = string.Empty;
public string Category { get; set; } = string.Empty;
public string Slug { get; set; } = string.Empty;
}
}
namespace BlogRAG.Services
{
public class RAGGenerationService
{
private readonly IEmbeddingService _embedder;
private readonly QdrantVectorStore _vectorStore;
private readonly ILLMService _llm;
private readonly ILogger<RAGGenerationService> _logger;
public RAGGenerationService(
IEmbeddingService embedder,
QdrantVectorStore vectorStore,
ILLMService llm,
ILogger<RAGGenerationService> logger)
{
_embedder = embedder;
_vectorStore = vectorStore;
_llm = llm;
_logger = logger;
}
public async Task<string> GenerateSuggestionAsync(
string currentDraft,
string requestType = "continue")
{
// 1. Generate embedding for current draft
var draftEmbedding = await _embedder.GenerateEmbeddingAsync(currentDraft);
// 2. Search for relevant past content
var results = await _vectorStore.SearchAsync(
queryVector: draftEmbedding,
limit: 5,
scoreThreshold: 0.7f);
_logger.LogInformation("Found {Count} relevant chunks", results.Count);
// 3. Build context from results
var contextBuilder = new StringBuilder();
foreach (var result in results)
{
var text = result.Payload["text"].ToString();
var title = result.Payload["blog_post_title"].ToString();
var score = result.Score;
contextBuilder.AppendLine($"## From: {title} (relevance: {score:F2})");
contextBuilder.AppendLine(text);
contextBuilder.AppendLine();
}
// 4. Build prompt
var systemPrompt = BuildSystemPrompt(requestType);
var userPrompt = BuildUserPrompt(currentDraft, contextBuilder.ToString(), requestType);
// 5. Generate with LLM
var suggestion = await _llm.GenerateCompletionAsync(
systemPrompt: systemPrompt,
userPrompt: userPrompt,
temperature: 0.7f);
return suggestion;
}
private string BuildSystemPrompt(string requestType)
{
return requestType switch
{
"continue" => @"You are a technical blog writing assistant. Your role is to suggest
continuations for blog posts based on the author's past writing style and content.
Guidelines:
- Match the author's voice and technical depth
- Use similar patterns and structures from past posts
- Be specific and technical, not generic
- Include code examples when relevant
- Maintain consistency with past content",
"improve" => @"You are a technical blog editor. Your role is to improve sections
of blog posts while maintaining the author's voice.
Guidelines:
- Preserve the author's style
- Improve clarity and flow
- Add technical depth where appropriate
- Suggest better examples from past posts
- Fix unclear explanations",
"outline" => @"You are a technical blog outline generator. Your role is to suggest
outlines for new blog posts based on past structures.
Guidelines:
- Study the author's typical post structure
- Suggest sections based on successful past posts
- Include technical depth appropriate to topic
- Reference similar past articles",
_ => "You are a helpful technical writing assistant."
};
}
private string BuildUserPrompt(string currentDraft, string context, string requestType)
{
return $@"
# Current Draft
{currentDraft}
# Relevant Past Content
{context}
# Request
{GetRequestDescription(requestType)}
Please provide your suggestion based on the current draft and the relevant past content shown above.
Remember to maintain consistency with the author's past writing style and technical approach.
";
}
private string GetRequestDescription(string requestType)
{
return requestType switch
{
"continue" => "Continue writing from where the draft ends. Suggest the next 1-2 paragraphs.",
"improve" => "Improve the current draft. Suggest specific edits and enhancements.",
"outline" => "Create a detailed outline for completing this post.",
_ => "Provide helpful suggestions."
};
}
}
}
using Microsoft.Extensions.Configuration;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Logging;
namespace BlogRAG.Console
{
class Program
{
static async Task Main(string[] args)
{
// Setup DI and configuration
var services = new ServiceCollection();
var configuration = new ConfigurationBuilder()
.SetBasePath(Directory.GetCurrentDirectory())
.AddJsonFile("appsettings.json")
.AddUserSecrets<Program>() // For API keys
.Build();
services.AddLogging(builder => builder.AddConsole());
// Register services
var embeddingConfig = configuration.GetSection("BlogRAG:Embedding");
services.AddSingleton<IEmbeddingService>(sp =>
new OpenAIEmbeddingService(
embeddingConfig["ApiKey"]!,
embeddingConfig["Model"]!,
sp.GetRequiredService<ILogger<OpenAIEmbeddingService>>()));
var llmConfig = configuration.GetSection("BlogRAG:LLM");
services.AddSingleton<ILLMService>(sp =>
new ClaudeLLMService(
llmConfig["ApiKey"]!,
llmConfig["Model"]!,
sp.GetRequiredService<ILogger<ClaudeLLMService>>()));
var vectorConfig = configuration.GetSection("BlogRAG:VectorStore");
services.AddSingleton(sp =>
new QdrantVectorStore(
vectorConfig["Url"]!,
vectorConfig["ApiKey"] ?? "",
vectorConfig["CollectionName"]!,
sp.GetRequiredService<ILogger<QdrantVectorStore>>()));
services.AddSingleton<IngestionService>();
services.AddSingleton<RAGGenerationService>();
var serviceProvider = services.BuildServiceProvider();
// Run CLI
await RunCLI(serviceProvider, configuration);
}
static async Task RunCLI(ServiceProvider serviceProvider, IConfiguration configuration)
{
System.Console.WriteLine("=== Blog RAG Assistant ===\n");
System.Console.WriteLine("Commands:");
System.Console.WriteLine(" ingest - Ingest markdown files");
System.Console.WriteLine(" write - Start writing session");
System.Console.WriteLine(" quit - Exit\n");
while (true)
{
System.Console.Write("> ");
var command = System.Console.ReadLine()?.Trim().ToLower();
switch (command)
{
case "ingest":
await IngestCommand(serviceProvider, configuration);
break;
case "write":
await WriteCommand(serviceProvider);
break;
case "quit":
return;
default:
System.Console.WriteLine("Unknown command");
break;
}
}
}
static async Task IngestCommand(ServiceProvider serviceProvider, IConfiguration configuration)
{
var ingestion = serviceProvider.GetRequiredService<IngestionService>();
var markdownPath = configuration["BlogRAG:Ingestion:MarkdownPath"];
System.Console.WriteLine($"Ingesting from {markdownPath}...");
await ingestion.IngestMarkdownFilesAsync(markdownPath!);
System.Console.WriteLine("Ingestion complete!\n");
}
static async Task WriteCommand(ServiceProvider serviceProvider)
{
var rag = serviceProvider.GetRequiredService<RAGGenerationService>();
System.Console.WriteLine("\nEnter your draft (end with empty line):");
var draft = new StringBuilder();
string? line;
while (!string.IsNullOrWhiteSpace(line = System.Console.ReadLine()))
{
draft.AppendLine(line);
}
System.Console.WriteLine("\nGenerating suggestion...\n");
var suggestion = await rag.GenerateSuggestionAsync(draft.ToString());
System.Console.WriteLine("=== Suggestion ===");
System.Console.WriteLine(suggestion);
System.Console.WriteLine("\n");
}
}
}
# 1. Clone/create project
dotnet new console -n BlogRAG
cd BlogRAG
# 2. Add packages
dotnet add package Qdrant.Client
dotnet add package OpenAI
dotnet add package Anthropic.SDK
dotnet add package Microsoft.Extensions.Configuration.Json
dotnet add package Microsoft.Extensions.Configuration.UserSecrets
# 3. Set API keys (stored securely)
dotnet user-secrets init
dotnet user-secrets set "BlogRAG:Embedding:ApiKey" "sk-..."
dotnet user-secrets set "BlogRAG:LLM:ApiKey" "sk-ant-..."
# 4. Start Qdrant (local)
docker run -d -p 6333:6333 qdrant/qdrant
# 5. Run ingestion
dotnet run
> ingest
# 6. Start writing
> write
Τυπική συνεδρία γραφής blog (20K εισόδου, 2K εξόδου): περίπου $0.09Μηνιαία χρήση (10 συνεδρίες): περίπου $ 0,90 / μήνα
# Start Qdrant (if using local Docker)
docker start qdrant
# Run assistant
dotnet run
> write
# Enter your draft
I've been working on a new feature that uses Entity Framework Core...
[Ctrl+D or empty line]
# Get AI suggestion based on your past EF posts!
Ίδιο API με την τοπική εγκατάσταση- απλά δείξε το τοπικό Ντόκερ ή Qdrant Cloud!
Αγωγός κατάποσης |-----------|--------|------| RAG Generation Service Απλή Κονσόλα Πελάτης Εκτέλεση του συστήματος | Ρύθμιση πρώτης φοράς | | ~$3.65 |
Συνολικός χρόνος εγκατάστασης
**Μηνιαία εκτίμηση κόστους (Personal Blog)**Σενάριο
Δραστηριότητα - Τόμος - Κόστος:
text-embedding-3-smallΑρχική κατάποση (100 δημοσιεύσεις) Μια φορά, 500K μάρκες... 0.05 δολάρια...text-embedding-3-largeΕνδυμασίες (κατασχέσεις, 40/μήνα)Σύνολο μηνιαίουΓια σύγκριση:
// Use OpenAI Batch API for ingestion
var batch = await client.CreateBatchAsync(requests);
// Wait hours, pay half price
Τοπική ρύθμιση: $0/μήνα (αλλά $ 800+ GPU προκαταβολικά):
// Don't re-embed identical text
var cache = new Dictionary<string, float[]>();
ChatGPT Plus: $20/μήνα (χωρίς RAG, γενικό):
: Αν το χρησιμοποιείτε αυτό για 18+ μήνες, η τοπική GPU πληρώνει για τον εαυτό της.:
// Retrieve top 3 instead of top 10 chunks
limit: 3 // 70% less input tokens
Συμβουλές βελτιστοποίησης κόστους |-------|---------|---------|--------|--------| Χρήση μικρότερων μοντέλων για την ενσωμάτωση : $0.00002/1K μάρκες : $0.00013/1K μάρκες 6,5x διαφορά κόστους!
Η παρτίδα API καλεί(50% φθηνότερο για μη-επείγον):
// Switch models with one line
services.AddSingleton<ILLMService>(sp =>
new ClaudeLLMService( // Was GPT-4, now Claude
config["ApiKey"],
"claude-3-5-sonnet-20241022", // Latest model
sp.GetRequiredService<ILogger<ClaudeLLMService>>()));
Χρησιμοποιήστε φθηνότερα μοντέλα για τα σχέδιαClaude 3.5 Haiku: $0,25/M εισόδου (12x φθηνότερα από Sonnet)
# Works on Mac (no CUDA support)
dotnet run # Just works!
# Works on Linux ARM (Raspberry Pi?)
dotnet run # Just works!
# Works in Codespaces/Gitpod
dotnet run # Just works!
Όριο παραθύρου πλαισίου
// Handle 100 concurrent users? Easy with APIs
await Task.WhenAll(users.Select(u =>
rag.GenerateSuggestionAsync(u.Draft)));
// Local? Limited by your single GPU
bash
dotnet publish -c Release
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.