Initial commit: RAG MCP Server with relationship graph

Features:
- Vector search with Pinecone + Vertex AI embeddings
- Document relationships (link, unlink, related, graph)
- Auto-link with LLM analysis
- Intelligent merge with Gemini

Modular structure:
- clients/: Pinecone, Vertex AI
- tools/: core, relations, stats
- utils/: validation, logging

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.env.example

@@ -0,0 +1,19 @@
+# RAG MCP Server Configuration
+# API keys stored in Vault (api/*)
+
+# Vault: api/pinecone
+PINECONE_API_KEY=your-pinecone-api-key
+
+# Vault: api/vertex
+VERTEX_API_KEY=your-vertex-api-key
+GOOGLE_CLOUD_PROJECT=your-gcp-project-id
+GOOGLE_CLOUD_LOCATION=us-central1
+
+# Service Configuration
+PINECONE_INDEX_NAME=memory-index
+FASTMCP_HOST=0.0.0.0
+FASTMCP_PORT=8000
+
+# Auto-link settings
+AUTO_LINK_THRESHOLD=0.75
+AUTO_LINK_TOP_K=5