What is a vector database?
A vector database is any database that allows you to store, index, and query vector embeddings, or numerical representations of unstructured data, such as text, images, or audio.
What are vector embeddings?
Vector embeddings are useful representations of unstructured data because they map content in such a way that semantic similarity is represented by distance in n-dimensional vector space. This makes it easy to search for similarity, find relevant content in a knowledge base, or retrieve an item that best matches a complex user-generated query.
While some specialized databases only support vector embeddings, others support many other data and query types in addition to vector embeddings. Support for a wide range of datatypes and query types is critical for building generative AI applications on top of rich, real-world data. As the benefits of semantic query using vector embeddings becomes clear, most databases will add vector support. In the future, we believe that every database will be a vector database.
Learn how Google Cloud’s relational databases AlloyDB for PostgreSQL and Cloud SQL for PostgreSQL support building generative AI applications using the pgvector PostgreSQL extension, LangChain, and large language models (LLMs). Watch this demo video and read this blog to see how these capabilities work together using Google's PaLM models powered by VertexAI.
In addition, learn how AlloyDB AI offers an integrated set of capabilities for easily building enterprise generative AI applications. AlloyDB AI offers pg vector-compatible vector search that is up to 10x faster than standard PostgreSQL, allows you to easily generate embeddings from within your database, and fully integrates with Vertex AI and open source Gen AI tools.
How does a vector database work?
As with other data types, efficiently querying a large set of vectors requires an index—and vector databases support specialized indexes for vectors. Unlike many other data types (like text or numbers) which have a single logical ordering, vectors don’t have a natural ordering that corresponds to practical use cases. Instead, the most common use case is to query for the k vectors that are closest to some other vector in terms of a distance metric like dot product, cosine similarity, or euclidean distance. This kind of query is referred to as a “k (exact) nearest neighbors” or “KNN” query.
Unfortunately, there are no general algorithms for efficient KNN queries—to be guaranteed of finding the k nearest neighbors to a given vector, q, requires computing the distance between q and every other vector. However, there are efficient algorithms for finding the k approximate nearest neighbors (“ANN”). These ANN algorithms trade off some accuracy (specifically recall, the algorithm might omit some of the actual nearest neighbors) for big improvements in speed. Since many use cases already treat the process of computing vector embeddings as somewhat imprecise, they can often tolerate some loss in recall in return for big improvements in performance.
To enable ANN queries for vectors based on distance from some other vector, a vector index is structured in a way that clusters of nearby vectors are generally grouped together. Common vector index types can be structured as a set of lists in which each list represents the vectors in a given cluster; a graph in which each vector is connected to several of their nearest neighbors; trees in which the branches correspond to subsets of the parent node’s cluster; and more. Each index type provides tradeoffs between lookup speed, recall, memory consumption, index creation time, and other factors.
Most database queries aren’t just based on semantic similarity, though. For example, a user might be looking for a book whose description is similar to “a heartwarming story about a child and a dog” but they also want to limit it to books under $20 which are available in paperback format. Special-purpose vector databases may provide some limited additional filtering capability (sometimes called “restricts”) while general purpose databases can compose rich predicates using standard languages like SQL which can be combined with vector similarity ordering to enable very powerful, expressive queries.
Use cases for vector databases
The ability of vector embeddings to represent the semantic meaning of unstructured data combined with the ability for vector databases to efficiently search for nearby vectors unlocks many important use cases:
- Find messages from chat history that are relevant to the current conversation, thus enabling AI-powered chatbots to have “memory”
- Find video clips from a vast archive of sports broadcasts that match a simple description like “leaping over a defender to catch the ball and score a touchdown”
- Find products similar to something a user has purchased before and which fit within that user’s price and style preferences
- Look up documents that are relevant to a task like “replacing the filter on a vacuum” so that an AI-powered assistant can provide a relevant, factual response
Benefits of vector databases
Vector databases are important because they can be used to solve a variety of problems that are difficult or impossible to solve with relational predicates or text search techniques alone.
Vector databases are well-suited for generative AI applications because they make it easy to retrieve critical business and application context like relevant chat history or business-specific unstructured content to help LLMs respond to a complex user query.
They can also make it easy to search content using natural language or to query by example.
Solve your business challenges with Google Cloud
Related products and services
Google Cloud offers relational databases AlloyDB for PostgreSQL and Cloud SQL for PostgreSQL that support building generative AI applications using the pgvector PostgreSQL extension, LangChain, and large language models (LLMs).
