AlloyDB AI

AlloyDB AI’s ScaNN index is deeply integrated with the PostgreSQL query planner to enable simple yet powerful queries across structured and unstructured data. You don’t need to deploy or learn a separate vector database, nor suffer the latency of trips across multiple systems. Adaptive filtering ensures that filters, joins, and vector indexes deliver optimal performance when used together.

Use AlloyDB AI to provide users and agents with accurate responses to natural language questions. With  AlloyDB AI natural language  you can overcome the ambiguity, flexibility, and security issues typically encountered in natural language interfaces. AlloyDB AI can disambiguate user questions and incorporate data from the schema, sample data, and other sources to increase accuracy. It also locks down access to unauthorized data.

Access Google’s Gemini models or other foundation models hosted on  Vertex AI , and use  model endpoint management  to register model endpoints on any platform and call them from AlloyDB with a simple SQL function. Use retrieval augmented generation (RAG) to ground application responses in real-time context from the database without the need for complex glue code.

With  AlloyDB AI query engine , you can use natural language in SQL queries to express filtering conditions and ranking criteria. The power of AI models brings reasoning and real-world knowledge to SQL queries, unlocking deep semantic insights from your enterprise data. You can generate vector embeddings, perform similarity searches, and invoke AI models within a single query.