AI & Technical
Vector Database
A database optimised for storing and searching embedding vectors at scale.
A vector database stores embeddings and enables fast similarity search — finding the most semantically relevant chunks of text for a given query. Popular vector databases include Pinecone, Weaviate, and pgvector (PostgreSQL extension). In a RAG-powered chat agent, the knowledge base is indexed as embeddings in a vector database. When a visitor sends a message, it is embedded and compared against the stored vectors to retrieve the most relevant knowledge before generating a response.
Related Terms
Embeddings
Numerical representations of text that allow AI to measure semantic similarity.
Retrieval-Augmented Generation (RAG)
Enhancing AI responses by retrieving relevant documents before generating an answer.
Knowledge Base
A curated set of documents and FAQs that an AI agent uses to answer questions.