Core Concepts
Vector Database
A database optimized for storing and searching high-dimensional embedding vectors.
Vector databases (Pinecone, Weaviate, Qdrant, pgvector) store embedding vectors and support approximate nearest-neighbor (ANN) search. This enables semantic search at scale: given a query embedding, the database finds the most semantically similar documents in milliseconds. They are a core infrastructure component for any RAG-based application.
Related Terms
Embedding
A dense numerical vector that encodes the semantic meaning of text.
RAG (Retrieval-Augmented Generation)
Enhancing model responses by fetching relevant documents from an external knowledge base at query time.
Semantic Search
Search that retrieves results based on meaning rather than exact keyword matching.
Inference
The process of running a trained model to generate outputs from new inputs.