Your AI SaaS business, ready by this week!
Try demoYour AI SaaS business, ready by this week!
Try demoA vector database stores embeddings and finds the ones closest to a query vector quickly, which makes it the search engine behind RAG and semantic search.
A normal database finds rows that match exact values. A vector database finds the nearest neighbours of a vector, using indexes built for that job, so it can search millions of chunks by meaning in milliseconds.
Dedicated options include Qdrant, Pinecone, Weaviate and Milvus. Many general databases, such as PostgreSQL with pgvector, can also store and search vectors.
For small knowledge bases a built-in store is enough. A dedicated vector database pays off when you have many users, large document sets or need filtering at scale.
Aikeedo includes a built-in vector store for knowledge bases and can use Qdrant through a plugin when you need a dedicated vector database.
Discover more terms connected to this one
Embeddings are lists of numbers that represent the meaning of a piece of text, so that texts with similar meaning end up close together and can be found by similarity search.
RAG (retrieval-augmented generation) is a technique where relevant passages are first retrieved from a knowledge base and then given to an AI model with the question, so the answer is grounded in that content.
Semantic search finds results by meaning rather than exact keywords, by comparing embeddings of the query and the content.