Loading...

MariaDB Vector

MariaDB Vector is an extension or feature of MariaDB, providing capabilities for handling and querying vector data within the MariaDB ecosystem.

🌐Visit Website

About this tool

Information

Rating

(0)

PublisherFox

Websitemariadb.org

PublishedJul 1, 2025

Categories

1 item

Vector Database Extensions

Tags

3 items

#relational database

Similar Products

6 result(s)

Lantern is a PostgreSQL extension that enables efficient vector search capabilities, allowing users to perform similarity searches directly within their PostgreSQL databases.

#PostgreSQL

#vector search

#extension

Neo4j Vector Search

An enhancement to the Neo4j graph database providing vector search capabilities through dedicated indexes.

#graph database

#vector search

#extension

Featured

An OpenSearch plugin that expands its capabilities with the custom `knn_vector` data type, enabling storage of embeddings and providing methods for k-NN similarity searches, including Approximate k-NN, Script Score k-NN, and Painless extensions.

#OpenSearch

#k-NN

#vector search

A feature for MySQL that integrates vector store capabilities, allowing users to store and process vector embeddings for AI applications.

#MySQL

#vector store

#extension

Amazon OpenSearch k-NN

Amazon OpenSearch's k-NN plugin enables scalable, efficient vector search using ANN algorithms (IVF, HNSW) directly within a managed OpenSearch cluster. It is directly relevant for building, querying, and scaling vector databases on AWS.

#vector search

#ANN

#managed service

#OpenSearch

Amazon Web Services Vector Search

AWS has introduced vector search in several of its managed database services, including OpenSearch, Bedrock, MemoryDB, Neptune, and Amazon Q, making it a comprehensive platform for vector search solutions.

#cloud-native

#vector search

#managed service

#enterprise

Comments

Overview

MariaDB Vector is an extension of MariaDB, guided by the MariaDB Foundation and built with the MariaDB Server community. It enables fast vector search directly within a relational database, simplifying the technology stack by removing the need for specialized datastores. Available in MariaDB since version 11.7 and now in 11.8 GA LTS, it introduces vector similarity search capabilities, including specialized syntax and a new index type for efficient searching of vectors based on distance functions.

Features

Dedicated Data Type: Introduces a VECTOR data type for storing vector embeddings.
Specialized Indexing: Provides a VECTOR index type, utilizing a modified version of the Hierarchical Navigable Small Worlds (HNSW) algorithm for fast search.
Vector Distance Functions: Supports functions like VEC_DISTANCE_EUCLIDEAN and VEC_DISTANCE_COSINE for calculating similarity.
Utility Functions: Includes VEC_FromText for converting text representations to vectors and VEC_ToText for converting vector bytes to text.
SQL Integration: Seamlessly integrates with SQL for creating tables with vector columns, inserting vector data, and performing vector searches.
Optimizer Tuning: The MariaDB optimizer is tuned to leverage the vector index for SELECT queries that include ORDER BY VEC_DISTANC_EUCLIDEAN (or VEC_DISTANC_COSINE) and a LIMIT clause.

Performance

MariaDB Vector's implementation of a modified HNSW algorithm offers search performance comparable to other vector search solutions. It demonstrates superior scalability, especially when handling multiple concurrent connections. Detailed benchmarks are available for further analysis.

Use Cases

MariaDB Vector supports a variety of applications:

Recommendation Systems: Build personalized product recommendations based on user preferences and behavior, supporting natural language interactions.
Similarity Search: Implement powerful search functionalities to find similar images, documents, or multimedia content. This includes building knowledge bases from documentation or finding related products without manual labeling.
Machine Learning: Efficiently store and retrieve vector representations of data for machine learning models, facilitating easy clustering and quick retrieval of closest data points.

How to Use

For developers, integrating MariaDB Vector involves:

Setting up an AI model (e.g., OpenAI, LLama, Hugging Face) to generate vector embeddings.
Adding a VECTOR column to your existing data tables.
Creating a specialized vector index on the new column to enable fast similarity searches.