feat: initialize MCP RAG Prompts server with embedding management

- Add package.json for project configuration and dependencies.
- Create src/index.ts as the entry point for the MCP server.
- Implement vectorStore for managing embeddings with local and cloud providers.
- Add embeddingProviders for local and cloud-based embedding services (OpenAI, Aliyun, SiliconFlow).
- Define types for prompts and embeddings in types.ts.
- Implement searchPersona tool for semantic search of expert personas.
- Create test.ts for validating vector storage and search functionality.
- Configure TypeScript with tsconfig.json for strict type checking and module resolution.

.env.example

@@ -0,0 +1,53 @@
+# ============================================================
+# MCP RAG Prompts - Embedding 配置
+# 复制此文件为 .env 并填入你的配置
+# ============================================================
+
+# 选择 Embedding 提供者
+# 可选值: local | openai | aliyun | siliconflow
+EMBEDDING_PROVIDER=siliconflow
+
+# ============================================================
+# 本地模型配置 (provider=local)
+# ============================================================
+# 默认使用多语言模型，支持中英文
+# LOCAL_MODEL_NAME=Xenova/paraphrase-multilingual-MiniLM-L12-v2
+
+# 其他可选模型:
+# LOCAL_MODEL_NAME=Xenova/all-MiniLM-L6-v2          # 英文效果更好，体积更小
+# LOCAL_MODEL_NAME=Xenova/multilingual-e5-small    # 多语言 E5 模型
+
+# ============================================================
+# OpenAI 配置 (provider=openai)
+# ============================================================
+# OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxx
+# OPENAI_BASE_URL=https://api.openai.com/v1
+# OPENAI_EMBEDDING_MODEL=text-embedding-3-small
+
+# 可选模型:
+# text-embedding-3-small  (1536维，便宜)
+# text-embedding-3-large  (3072维，更精准)
+# text-embedding-ada-002  (1536维，旧版)
+
+# ============================================================
+# 阿里云百炼 DashScope 配置 (provider=aliyun)
+# ============================================================
+# DASHSCOPE_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxx
+# ALIYUN_EMBEDDING_MODEL=text-embedding-v3
+
+# 可选模型:
+# text-embedding-v3       (最新版，推荐)
+# text-embedding-v2       (旧版)
+# text-embedding-v1       (更旧)
+
+# ============================================================
+# SiliconFlow 硅基流动配置 (provider=siliconflow)
+# ============================================================
+SILICONFLOW_API_KEY=sk-fwemdoaytkxelpbjlnohiqvkeqjxxraoduadokrpvtynxoej
+SILICONFLOW_EMBEDDING_MODEL=Qwen/Qwen3-Embedding-8B
+
+# 可选模型 (开源模型，性价比高):
+# BAAI/bge-m3                    # 多语言，效果很好
+# BAAI/bge-large-zh-v1.5         # 中文专用
+# BAAI/bge-large-en-v1.5         # 英文专用
+# nomic-ai/nomic-embed-text-v1.5 # 多语言