Announcing AlloyDB AI for building generative AI applications with PostgreSQL. Read the blog.
Jump to

AlloyDB AI Preview

Build enterprise generative AI apps with AlloyDB for PostgreSQL.

  • Familiar PostgreSQL interface for working with vectors, models, and data

  • Provides up-to-date data and contextual experiences for gen AI apps

  • Built into AlloyDB for superior performance and availability and simplified management

  • Available in AlloyDB on Google Cloud and in AlloyDB Omni, so you can run it anywhere


PostgreSQL-based generative AI apps

Build generative AI applications with the familiar PostgreSQL interface and open, standard technologies like pgvector and LangChain.

High-performance vector operations

Run vector queries up to 10x faster compared to standard PostgreSQL, and generate vector embeddings from within your database.

State-of-the-art gen AI models

Use Google’s models in Vertex AI or your own custom models, and access them in your application via familiar SQL queries.

Key features

Key features

AlloyDB AI runs vector queries up to 10x faster compared to standard PostgreSQL. It supports 8-bit quantization for a 3x reduction in index size when enabled, and offers vectors with 4x more dimensions when enabled. Your apps can perform fast similarity searches on complex data types such as text and images.

Vector embeddings within the database

Automated embeddings generation helps you easily transform operational data, including text and images, into vector embeddings using the AI model of your choice. Store embeddings in AlloyDB, and query them with a SQL interface.

Access to local or remote models and data

Access both local models in AlloyDB and remote models hosted in Vertex AI, including custom and pretrained models. You can train and fine-tune models with the data stored in AlloyDB, and then deploy them as endpoints on Vertex AI. It's also easy to access data stored in open source gen AI tools such as LangChain and combine it with the data in your AlloyDB database.

Enterprise-level scalability, availability, and security

As part of AlloyDB, AlloyDB AI benefits from the best of Google and the best of PostgreSQL. Give your application superior performance and scale, a high availability SLA of 99.99% that's inclusive of maintenance, automatic detection of and recovery from most database failures, and comprehensive security and compliance.



AlloyDB AI is an integral part of AlloyDB and is available at no additional charge.

If you choose to run additional services such as Vertex AI, you will be charged for those services separately.