// AI
Vector Database
A database that stores and searches high-dimensional embeddings, the retrieval layer of every RAG pipeline.
In depth
Pinecone, Weaviate, Postgres+pgvector, Turbopuffer. Vector DBs enable semantic search: 'find CRM notes similar in meaning to this query', not 'find CRM notes with these keywords'.
Related terms
RAG
Retrieval-Augmented Generation, grounding an LLM's response in retrieved documents to reduce hallucination.
Embedding
A dense numeric vector representation of text, image or audio, the input format for semantic search and RAG.
LLM
Large Language Model, the transformer-based foundation model behind ChatGPT, Claude, Gemini and every 2024+ AI product.