Mixpeek Logo
    Login / Signup
    C++/PythonVector IndexingApache 2.0

    scann

    by google

    Anisotropic vector quantization for efficient similarity search

    N/A (library)params
    Identifiers
    Model ID
    google/scann
    Feature URI
    mixpeek://vector_index@v1/google_scann_v1

    Overview

    ScaNN (Scalable nearest Neighbors) is Google's vector similarity search library optimized for maximum inner-product search on high-dimensional embeddings. It introduces anisotropic vector quantization that outperformed other ANN libraries by 2x on standard benchmarks.

    On Mixpeek, ScaNN provides an alternative vector indexing backend with particularly strong performance on inner-product similarity workloads.

    Architecture

    Uses anisotropic vector quantization — a novel compression technique that significantly boosts accuracy of approximate distance computations compared to standard quantization. Supports asymmetric hashing and tree-based partitioning.

    Mixpeek SDK Integration

    # ScaNN is used as a vector indexing backend.
    # Mixpeek manages the index lifecycle automatically.
    
    import { Mixpeek } from "mixpeek";
    const mx = new Mixpeek({ apiKey: "API_KEY" });
    
    await mx.collections.ingest({
      collection_id: "my-collection",
      source: { url: "https://example.com/data.mp4" },
      feature_extractors: [{
        name: "image_embedding",
        version: "v1"
      }]
    });

    Capabilities

    • 2x faster than competing ANN libraries (at time of release)
    • Anisotropic vector quantization for better accuracy
    • Optimized for maximum inner-product search (MIPS)
    • Scales to billion-vector datasets

    Use Cases on Mixpeek

    High-throughput embedding search at scale
    Semantic search over large knowledge bases
    Recommendation and personalization systems

    Specification

    FrameworkC++/Python
    Organizationgoogle
    FeatureVector Indexing
    Outputindex + results
    Modalitiesvideo, image, audio, document
    RetrieverVector Search
    ParametersN/A (library)
    LicenseApache 2.0
    Downloads/moN/A

    Build a pipeline with scann

    Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

    Open Pipeline Builder