semantic-search

Features and purpose

Build production-ready semantic search systems using vector databases, embeddings, and retrieval-augmented generation (RAG). Covers vector DB selection (Pinecone/Qdrant/Weaviate), embedding models (OpenAI/Voyage/Cohere), chunking strategies, hybrid search, and reranking for high-quality retrieval. Use when ", vector-search, embeddings, rag, pinecone, qdrant, weaviate, llama-index, langchain, hybrid-search, reranking" mentioned.

Quick start

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.