Vector search overview

AlloyDB AI enhances the open-source pgvector extension, providing full compatibility with its standard index types such as HNSW while supercharging performance with Google's cutting-edge ScaNN vector search technology. This unique integration lets you build scalable, production-ready generative AI, semantic search, and recommendation engines without moving your data or managing a separate vector database.

Visual overview of AlloyDB vector search

Build faster, smarter AI applications

AlloyDB AI eliminates the complexity of managing a separate vector database. Keep operational data and embeddings in one place, and use built-in functions to generate batch embeddings (Preview) for large tables, scaling your AI pipeline from a single, secure source.

  • RAG thumbnail
    Retrieval-augmented generation (RAG)

    Enhance LLM responses by using vector search to find and retrieve the most relevant, up-to-date context from your private data in AlloyDB, directly feeding it into the prompt to reduce hallucinations.

  • Semantic search thumbnail
    Semantic search

    Enable concept-based search by converting your data into vector embeddings. AlloyDB AI's fast vector queries then find items based on their semantic meaning, not just keyword matches.

  • Recommendation engine thumbnail
    Recommendation engines

    Power real-time personalization by using ultra-fast vector search to identify similar items or users (nearest neighbors) directly within your database, enabling dynamic and relevant recommendations.

ScaNN vector search performance

  • bolt

    Up to 10x faster ScaNN index creation than HNSW.

  • filter_alt

    Up to 10x faster filtered vector search than HNSW.

  • memory

    Uses 3x less memory than HNSW.

  • rocket_launch

    Up to 4x faster vector search queries than HNSW.

Learn more and get started

Explore our developer resources to build AI applications with AlloyDB's vector search capabilities.