Vector Database
In one sentence
A database that stores vectors and quickly finds semantically similar content, commonly used as a core component for RAG and knowledge base retrieval.
Documents are chunked, converted into vectors, and stored in a vector database. When a user asks a question, the query is also converted into a vector, and the database returns the most semantically similar original chunks.
Vector search excels at matching meaning, but for details that require exact matches—such as model numbers or part IDs—it is best paired with keyword search.
Example
Across 5,000 product documentation chunks in a knowledge base, a vector database finds the 5 most relevant chunks in less than a second when a user asks a question.
Related terms
- Vector (Embedding)
- Converting a block of text or an image into a series of numbers. Content with similar meanings gets similar numbers, making it possible to retrieve information by meaning.
- RAG (Retrieval-Augmented Generation)
- A method where AI retrieves relevant information from a knowledge base first, then generates an answer based on those materials.
- Text Chunking
- Splitting long documents into appropriately sized chunks before saving them to a knowledge base, making it easy to retrieve only the relevant sections.
