docs: align README.md with Turbovec architecture and link new documents

README.md

@@ -11,7 +11,7 @@ pinned: false
 
 **Tipitaka Web App** — เว็บอ่านพระไตรปิฎก ฉบับ มจร. แบบจิตวิเวก พร้อม AI ผู้ช่วยอัจฉริยะ
 
-> **Stack:** React + Vite | FastAPI + Python | SQLite FTS5 | Qdrant Vector | ONNX Reranker | DeepSeek API
+> **Stack:** React + Vite | FastAPI + Python | SQLite FTS5 | Turbovec In-Process (Primary) / Qdrant (Secondary) | ONNX Reranker | DeepSeek API
 
 ---
 
@@ -20,9 +20,9 @@ pinned: false
 | Feature | Description |
 |---------|-------------|
 | **📖 Reader** | 45+ เล่มพระไตรปิฎก — หน้า-ต่อ-หน้า, ปรับขนาดตัวอักษร, 3 themes (dark/light/classic) |
-| **🔍 Hybrid Search** | FTS5 + Vector (Qdrant) + ONNX Reranker — ถูกต้องทั้ง keyword และความหมาย |
+| **🔍 Hybrid Search** | FTS5 + Vector (Turbovec / Qdrant) + ONNX Reranker — ถูกต้องทั้ง keyword และความหมาย |
 | **🤖 AI Assistant** | Floating chat พร้อม RAG context, รองรับ DeepSeek-chat / DeepSeek-reasoner |
-| **🔗 Cross-Volume RAG** | ค้นข้ามเล่มจาก Qdrant vector store + jina-embeddings-v3, rerank ด้วย jina-reranker-v2 |
+| **🔗 Cross-Volume RAG** | ค้นข้ามเล่มจาก Turbovec index / Qdrant + jina-embeddings-v5, rerank ด้วย jina-reranker-v2 |
 | **📱 Responsive** | Desktop + Mobile, swipe gesture, keyboard nav |
 | **🎨 Markdown Rendering** | AI ตอบเป็น markdown พร้อม prose-invert สำหรับ dark mode |
 | **↔️ Resizable Panel** | ลากขอบขวาเพื่อปรับขนาด AI chat — persist ขนาดไว้ |
@@ -30,7 +30,7 @@ pinned: false
 
 ---
 
-## 🏗️ Architecture (V2)
+## 🏗️ Architecture (Turbovec Edition)
 
 ```
 ┌──────────────────────────────────────────────────────────────────┐
@@ -41,7 +41,7 @@ pinned: false
 └────────────────────────────────┬─────────────────────────────────┘
                                  │ HTTP / SSE
 ┌────────────────────────────────┴─────────────────────────────────┐
-│                   Backend (FastAPI Python 3.11)                   │
+│                   Backend (FastAPI Python 3.13)                   │
 │                                                                   │
 │  ┌────────────┐  ┌────────────┐  ┌────────────┐  ┌───────────┐ │
 │  │ Page       │  │ Search     │  │ RAG        │  │ LLM       │ │
@@ -49,12 +49,12 @@ pinned: false
 │  └─────┬──────┘  └─────┬──────┘  └─────┬──────┘  └─────┬─────┘ │
 │        │               │               │               │        │
 │   ┌────▼────┐    ┌─────▼─────┐    ┌────▼────┐    ┌────▼─────┐ │
-│   │ SQLite  │    │ SQLite    │    │ Qdrant  │    │ DeepSeek │ │
-│   │ FTS5    │    │ LIKE      │    │ Vector  │    │ API      │ │
-│   │ (memory)│    │ fallback  │    │ + ONNX  │    │ Streaming│ │
-│   └─────────┘    └───────────┘    │ Reranker│    └──────────┘ │
-│                                   └─────────┘                  │
-│  Services: page_service · search_service · pali_utils          │
+│   │ SQLite  │    │ SQLite    │    │ Turbovec│    │ DeepSeek │ │
+│   │ FTS5    │    │ LIKE      │    │ Index / │    │ API      │ │
+│   │ (memory)│    │ fallback  │    │ Qdrant  │    │ Streaming│ │
+│   └─────────┘    └───────────┘    └─────────┘    └──────────┘ │
+│                                                                 │
+│  Services: page_service · search_service · pali_utils           │
 │            rag_service · onnx_reranker · llm_service            │
 └─────────────────────────────────────────────────────────────────┘
 ```
@@ -63,7 +63,8 @@ pinned: false
 
 ```
 ���ำถาม → Pali Autocorrect → FTS5 (SQLite, 30 results)
-                        ─→ Qdrant Vector (jina-embeddings-v3, 30 results)
+                        ─→ Turbovec Index (jina-embeddings-v5, 30 results)
+                        → SQLite Content Enrichment
                         → Merge & Deduplicate
                         → ONNX Rerank (jina-reranker-v2)
                         → Top N → AI context
@@ -95,10 +96,11 @@ RAG/
 │           ├── hooks/         # swipe, keyboard
 │           └── lib/           # api.ts
 │
-├── qdrant_storage/            # Local Qdrant data
-├── snapshots/                 # Qdrant snapshot files
+├── qdrant_storage/            # Local Qdrant data (optional fallback)
+├── snapshots/                 # Qdrant snapshot files (optional fallback)
 ├── Dockerfile                 # Multi-stage build
-└── TIPITAKA_WEB_ARCHITECTURE_V2.md   # Full architecture doc
+├── TIPITAKA_WEB_ARCHITECTURE_TURBOVEC.md   # Main architecture doc (Turbovec)
+└── SEARCH_ARCHITECTURE_TURBOVEC.md         # Search specification (Turbovec)
 ```
 
 ---
@@ -106,10 +108,9 @@ RAG/
 ## 🚀 Quick Start
 
 ### Prerequisites
-- Python 3.11+
+- Python 3.13+
 - Node.js 20+
-- Ollama (for embedding — **jina-embeddings-v3**)
-- Qdrant (optional — auto-detect localhost:6333)
+- Ollama (for embedding — **jina-embeddings-v5-small-retrieval**)
 - DeepSeek API key
 
 ### 1. Setup Backend
@@ -132,8 +133,8 @@ npm run dev               # starts on :5173
 
 ### 3. Setup Embedding
 ```bash
-# Download jina-embeddings-v3 GGUF
-ollama pull hf.co/second-state/jina-embeddings-v3-GGUF:jina-embeddings-v3-Q4_K_M.gguf
+# Download jina-embeddings-v5 GGUF
+ollama pull hf.co/second-state/jina-embeddings-v5-text-small-retrieval-GGUF:v5-small-retrieval-Q6_K.gguf
 ```
 
 ### 4. Run Tests
@@ -155,7 +156,7 @@ python -m pytest tests/ -v    # 35 tests, all passing
 | `GET` | `/api/search/suggestions?q=` | Autocomplete |
 | `POST` | `/api/ask/stream` | AI ถาม-ตอบ (SSE streaming) |
 | `POST` | `/api/ask` | AI ถาม-ตอบ (non-stream — Discord) |
-| `GET` | `/api/ask/rag-status` | สถานะ Qdrant |
+| `GET` | `/api/ask/rag-status` | สถานะ Turbovec/Qdrant |
 | `GET` | `/health` | Health check |
 
 ---
@@ -184,8 +185,8 @@ Total: 35 tests ✅
 | **Markdown** | react-markdown + remark-gfm |
 | **Backend** | FastAPI, Python 3.11 |
 | **Database** | SQLite (FTS5, loaded to `:memory:` at startup) |
-| **Vector Store** | Qdrant (local/server dual-mode, snapshot restore) |
-| **Embedding** | jina-embeddings-v3 (Q4_K_M GGUF via Ollama, 1024 dims) |
+| **Vector Store** | Turbovec (Primary in-process index), Qdrant (Secondary fallback) |
+| **Embedding** | jina-embeddings-v5-small-retrieval (GGUF via Ollama / sentence-transformers) |
 | **Reranker** | jina-reranker-v2-base-multilingual (ONNX, CPU) |
 | **AI** | DeepSeek API (OpenAI-compatible, SSE streaming) |
 | **CI/CD** | HF Spaces (Docker multi-stage, auto-build) |
@@ -198,15 +199,18 @@ Total: 35 tests ✅
 |------|-------------|
 | `DESIGN.md` | Design system — colors, typography, components, themes |
 | `PRODUCT.md` | Product vision, users, principles |
-| `TIPITAKA_WEB_ARCHITECTURE_V2.md` | Full architecture V2 document |
-| `TIPITAKA_WEB_ARCHITECTURE.md` | Original V1 architecture (legacy reference) |
+| `TIPITAKA_WEB_ARCHITECTURE_TURBOVEC.md` | Main architecture document (Turbovec Edition) |
+| `SEARCH_ARCHITECTURE_TURBOVEC.md` | Search Architecture Specification (Turbovec Edition) |
+| `Tipitaka-Web-Application-Tech-Stack-TURBOVEC-HF.md` | Tech Stack & HF Spaces Deployment (Turbovec Edition) |
+| `TIPITAKA_WEB_ARCHITECTURE_V2.md` | Full architecture V2 document (Legacy Qdrant version) |
 
 ---
 
 ## 🙏 Acknowledgements
 
 - **มหาจุฬาลงกรณราชวิทยาลัย (MCU)** — เนื้อหาพระไตรปิฎก
-- **Qdrant** — Vector database
+- **Turbovec** — In-process vector database
+- **Qdrant** — Vector database (Legacy/Alternative)
 - **jina.ai** — Embedding + Reranker models
 - **Ollama** — Local model serving
 - **Hugging Face Spaces** — Deployment platform