Semantic Search

A comprehensive reference guide for selecting and optimizing embedding models for vector search and RAG applications. Covers model comparisons (OpenAI, Voyage, BGE, E5), chunking strategies (token-based, sentence-based, semantic), domain-specific pipelines, and retrieval quality evaluation metrics.

This skill provides comprehensive documentation for building RAG (Retrieval-Augmented Generation) systems. It covers vector database selection (Pinecone, Weaviate, Chroma), embedding models, document chunking strategies, retrieval optimization techniques, and prompt engineering patterns for knowledge-grounded LLM applications.

Enables personalized AI conversations by integrating user personas, AI personas, and semantic search over markdown notes. Uses local vector database (ChromaDB) with bge-m3 embeddings to retrieve relevant context from your notes during conversations.