All case studies

    Case study · Industry benchmark

    Green Vectors vs Elastic BBQ: a head-to-head benchmark.

    Morphos AI benchmarked Green Vectors against Elastic's Better Binary Quantization (BBQ), one of the most widely used vector compression methods, using the complete Project Gutenberg dataset. The benchmark measured three configurations: Green Vectors alone, BBQ alone, and Green Vectors combined with BBQ.

    Over 2.1xHigher search accuracyUp to 77%Faster search queries99%Reduction in storage footprint

    The challenge

    Tested against an established industry solution.

    A next-generation vectorization technology must be tested against established industry solutions. Elastic BBQ is a powerful compression method for large-scale vector workloads. The benchmark measured not only storage but the often-overlooked metrics of accuracy and latency, at the scale of the full Project Gutenberg corpus.

    The results

    Three configurations, one corpus.

    BBQ alone

    • Storage: 175 GB
    • Relevancy: .4576

    Green Vectors alone

    • Storage: 1.5 GB
    • Relevancy: .9658

    Green Vectors with BBQ

    • Storage: 2.6 GB
    • Relevancy: .9653

    Relevancy score: closer to 1 is more accurate. Green Vectors alone achieved 1.5GB of storage at a .9658 relevancy score. BBQ alone required 175GB at a .4576 relevancy score. That makes Green Vectors roughly 116 times more storage-efficient and more than twice as accurate as BBQ on this benchmark.

    Layering, in context

    Quantization becomes optional.

    Green Vectors and quantization operate on different axes, so they can be layered. In this benchmark, however, Green Vectors alone was the optimal configuration. Combining Green Vectors with BBQ held relevancy at .9653 but used 2.6GB, more storage than Green Vectors alone at 1.5GB, because on an already-minimal index BBQ's rotation and correction overhead costs more than it saves. The practical takeaway is that Green Vectors delivers the efficiency quantization aims for, which makes a separate quantization step optional.

    Why this matters

    Efficiency achieved without sacrificing accuracy.

    The key finding is that Green Vectors achieves its efficiency while improving accuracy, where compression alone sacrifices accuracy to save space. Green Vectors eliminates redundancy at the source rather than degrading precision.

    Frequently asked

    Questions about this benchmark.

    1. Q1

      Is Green Vectors better than Elastic BBQ?

      On the Project Gutenberg benchmark, Green Vectors alone was roughly 116x more storage-efficient and more than twice as accurate as BBQ alone. They can also be combined.

    2. Q2

      Can I use Green Vectors and BBQ together?

      They can be layered, since they work on different axes, but the benchmark showed Green Vectors alone was the optimal configuration. Adding BBQ increased storage without improving relevancy. With Green Vectors, quantization becomes optional.

    3. Q3

      Does Green Vectors compress vectors like BBQ?

      No. BBQ compresses by lowering precision. Green Vectors reduces the number of vectors by eliminating redundancy, preserving precision.

    Related

    • Related

      Vector Reduction

      Read
    • Related

      Project Gutenberg Benchmark

      Read
    • Related

      Vector Quantization vs Vector Reduction

      Read

    See Green Vectors on your data.

    Bring a dataset worth testing and define the constraint that matters to you.

    Get in touch