语义搜索服务

                         rag-mcp-claude
                         Port: 3020
┌──────────────────────────────────────────────────┐
│                                                  │
│  ┌──────────┐    ┌─────────────┐                 │
│  │  Ingest   │───▶│ Text Splitter│                 │
│  │  Pipeline │    │ (chunk 500   │                 │
│  └──────────┘    │  overlap 50) │                 │
│                   └──────┬──────┘                 │
│                          ▼                        │
│                  ┌───────────────┐                │
│                  │ OpenAI API     │                │
│                  │ text-embedding │                │
│    ┌──────┐      │ -3-small       │                │
│    │Search│─────▶│ (1536 dims)   │                │
│    └──────┘      └───────┬───────┘                │
│                          ▼                        │
│                  ┌───────────────┐                │
│                  │  ChromaDB      │                │
│                  │  Vector Store  │                │
│                  │  (cosine sim)  │                │
│                  └───────────────┘                │
│                                                  │
└──────────────────────────────────────────────────┘

cp .env.example .env
# แก้ไข .env ใส่ API key

OPENAI_API_KEY=sk-your-api-key-here

docker compose up -d

curl http://localhost:3020/health

# Ingest ทุกไฟล์ใน data/sources/
node src/cli-ingest.js --dir ./data/sources

# Ingest ไฟล์เดียว
node src/cli-ingest.js data/sources/SF6Tskjx6Qw.md

{
  "mcpServers": {
    "rag": {
      "url": "http://localhost:3020/mcp"
    }
  }
}

rag-mcp-claude/
├── src/
│   ├── server-sse.js    # Streamable HTTP transport server (port 3020)
│   ├── index.js         # Stdio transport server
│   ├── config.js        # Configuration
│   ├── embeddings.js    # OpenAI embedding API wrapper
│   ├── vectorstore.js   # ChromaDB operations (CRUD)
│   ├── ingest.js        # Chunk → Embed → Store pipeline
│   ├── search.js        # Semantic search
│   └── cli-ingest.js    # CLI batch ingest tool
├── data/
│   └── sources/         # Transcript files (.md)
├── docs/
│   ├── concept-comparison.md  # RAG vs FTS5 comparison
│   ├── guide-ingest.md        # คู่มือ ingest ข้อมูล
│   ├── guide-search.md        # คู่มือ search
│   └── guide-openai-key.md    # คู่มือสร้าง OpenAI API Key
├── Dockerfile
├── docker-compose.yml
├── .env.example
└── package.json

{
  "query": "สมาธิเปลี่ยนสมองได้อย่างไร",
  "collection": "youtube_transcripts",
  "totalResults": 3,
  "sources": [
    {
      "source": "SF6Tskjx6Qw",
      "title": "Ep0 - Journey Within: สำรวจโลกในหัวคุณ",
      "url": "https://www.youtube.com/watch?v=SF6Tskjx6Qw",
      "channel": "The Mind Architect",
      "chunks": [
        {
          "text": "สมาธิทำให้สมองส่วน Prefrontal Cortex หนาขึ้น...",
          "score": 0.892,
          "chunk_index": 3
        }
      ]
    }
  ]
}

{
  "total": 1,
  "collections": [
    { "name": "youtube_transcripts", "count": 45 }
  ]
}

YouTube Video
     │  (youtube-mcp-claude ดึง transcript)
     ▼
data/sources/*.md        ← Transcript files
     │
     ▼ (rag_ingest / cli-ingest.js)
┌────────────────┐
│ 1. Parse        │  แยก metadata + transcript text
│ 2. Chunk        │  ตัดเป็นท่อนๆ (500 tokens, overlap 50)
│ 3. Embed        │  OpenAI API → vector [1536 dims]
│ 4. Store        │  ChromaDB (cosine similarity index)
└────────────────┘
     │
     ▼ (rag_search)
┌────────────────┐
│ 1. Embed query  │  แปลงคำถามเป็น vector
│ 2. Search       │  หา vectors ที่ใกล้เคียงที่สุด
│ 3. Return       │  ส่งกลับ chunks + metadata + score
└────────────────┘