Initial setup: Knowledge base RAG system with LlamaIndex and ChromaDB

- Add Python project with uv package manager
- Implement LlamaIndex + ChromaDB RAG pipeline
- Add sentence-transformers for local embeddings (all-MiniLM-L6-v2)
- Create MCP server with semantic search, indexing, and stats tools
- Add Markdown chunker with heading/wikilink/frontmatter support
- Add Dockerfile and docker-compose.yaml for self-hosted deployment
- Include sample Obsidian vault files for testing
- Add .gitignore and .env.example

.env.example

@@ -0,0 +1,15 @@
+# Knowledge RAG Configuration
+
+# Path to your Obsidian vault (must contain markdown files)
+# This should be an absolute path or relative to where you run docker-compose
+VAULT_PATH=./knowledge
+
+# Embedding model to use
+# Default: all-MiniLM-L6-v2 (fast, good quality, ~90MB)
+# Other options:
+#   - all-mpnet-base-v2 (higher quality, slower, ~420MB)
+#   - BAAI/bge-small-en-v1.5 (good quality, ~130MB)
+EMBEDDING_MODEL=all-MiniLM-L6-v2
+
+# Optional: Log level (DEBUG, INFO, WARNING, ERROR)
+LOG_LEVEL=INFO