A vector database, vector store or vector search engine is a
database
In computing, a database is an organized collection of data or a type of data store based on the use of a database management system (DBMS), the software that interacts with end users, applications, and the database itself to capture and a ...
that uses the
vector space model
Vector space model or term vector model is an algebraic model for representing text documents (or more generally, items) as vector space, vectors such that the distance between vectors represents the relevance between the documents. It is used in i ...
to store vectors (fixed-length lists of numbers) along with other data items. Vector databases typically implement one or more
Approximate Nearest Neighbor algorithms,
so that one can search the database with a query vector to retrieve the closest matching database records.
Vectors are mathematical representations of data in a high-dimensional space. In this space, each dimension corresponds to a
feature
Feature may refer to:
Computing
* Feature recognition, could be a hole, pocket, or notch
* Feature (computer vision), could be an edge, corner or blob
* Feature (machine learning), in statistics: individual measurable properties of the phenome ...
of the data, with the number of dimensions ranging from a few hundred to tens of thousands, depending on the complexity of the data being represented. A vector's position in this space represents its characteristics. Words, phrases, or entire documents, as well as images, audio, and other types of data, can all be vectorized.
These feature vectors may be computed from the raw data using machine learning methods such as
feature extraction
Feature may refer to:
Computing
* Feature recognition, could be a hole, pocket, or notch
* Feature (computer vision), could be an edge, corner or blob
* Feature (machine learning), in statistics: individual measurable properties of the phenome ...
algorithms,
word embeddings or
deep learning
Deep learning is a subset of machine learning that focuses on utilizing multilayered neural networks to perform tasks such as classification, regression, and representation learning. The field takes inspiration from biological neuroscience a ...
networks. The goal is that semantically similar data items receive feature vectors close to each other.
Vector databases can be used for
similarity search,
semantic search
Semantic search denotes search with meaning, as distinguished from lexical search where the search engine looks for literal matches of the query words or variants of them, without understanding the overall meaning of the query. Semantic search seek ...
,
multi-modal search,
recommendations engines,
large language models
A large language model (LLM) is a language model trained with Self-supervised learning, self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially Natural language generation, language g ...
(LLMs),
object detection
Object detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos. Well-researched ...
, etc.
Vector databases are also often used to implement
retrieval-augmented generation
Retrieval-augmented generation (RAG) is a technique that enables large language model, large language models (LLMs) to retrieve and incorporate new information. With RAG, LLMs do not respond to user queries until they refer to a specified set of d ...
(RAG), a method to improve domain-specific responses of large language models. The retrieval component of a RAG can be any search system, but is most often implemented as a vector database. Text documents describing the domain of interest are collected, and for each document or document section, a feature vector (known as an "
embedding
In mathematics, an embedding (or imbedding) is one instance of some mathematical structure contained within another instance, such as a group (mathematics), group that is a subgroup.
When some object X is said to be embedded in another object Y ...
") is computed, typically using a deep learning network, and stored in a vector database. Given a user prompt, the feature vector of the prompt is computed, and the database is queried to retrieve the most relevant documents. These are then automatically added into the context window of the large language model, and the large language model proceeds to create a response to the prompt given this context.
Techniques
The most important techniques for similarity search on high-dimensional vectors include:
*
Hierarchical Navigable Small World (HNSW) graphs
*
Locality-sensitive Hashing (LSH) and Sketching
*
Product Quantization (PQ)
*
Inverted Files
and combinations of these techniques.
In recent benchmarks, HNSW-based implementations have been among the best performers.
Conferences such as the International Conference on Similarity Search and Applications, SISAP and the
Conference on Neural Information Processing Systems (NeurIPS) host competitions on vector search in large databases.
Implementations
See also
*
*
*
*
References
External links
* {{cite web , last=Sawers , first=Paul , title=Why vector databases are having a moment as the AI hype cycle peaks , website=TechCrunch , date=2024-04-20 , url=https://techcrunch.com/2024/04/20/why-vector-databases-are-having-a-moment-as-the-ai-hype-cycle-peaks/ , access-date=2024-04-23
Machine learning
Types of databases