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>

clients/__init__.py

@@ -0,0 +1,10 @@
+"""Client modules for external services."""
+from .pinecone import get_index
+from .vertex import get_embedding, merge_with_llm, analyze_relations_with_llm
+
+__all__ = [
+    "get_index",
+    "get_embedding",
+    "merge_with_llm",
+    "analyze_relations_with_llm"
+]