using-vector-databases - Implement vector search and RAG systems
Provides implementation guidance for vector databases, semantic search, embeddings, chunking, hybrid retrieval, and RAG pipelines.
Tags
Updated: 2026-09-28Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Select vector databases
- Generate document embeddings
- Design chunking strategies
- Build hybrid search
- Implement RAG pipelines
- Evaluate retrieval quality
Inputs
- Source documents
- User queries
- Document metadata
- Vector database configuration
- Embedding model configuration
Outputs
- Indexed document vectors
- Ranked search results
- Generated RAG responses
- Retrieval evaluation metrics
Requirements
- Supported vector database
- Embedding model or API
- LLM inference support