
    OpenSearch Vector Engine now supports a disk-optimized mode for vector search, enabling lower-cost, accurate searches with up to 67% cost reduction and latencies under 200 milliseconds.


<div>
<p>
AWS has announced disk optimization for the OpenSearch Vector Engine, enabling vector search at a significantly reduced cost while maintaining high search quality.
</p>
<ul>
<li>Disk mode can reduce deployment costs by up to 67% compared to memory mode</li>
<li>Supports vector search across billions of vectors with 90th percentile latency between 100-200 milliseconds</li>
<li>Compresses vectors by 32 times, reducing memory requirements by 97%</li>
<li>Uses a two-step search process: compressed in-memory index followed by disk-based re-scoring</li>
<li>Compatible with OpenSearch 2.17+ and supports various vector embedding types and algorithms</li>
</ul>
<p>
Early adopters like Asana and DevRev have already implemented disk-optimized vector search, demonstrating its potential for cost-effective, high-quality semantic search capabilities.
</p>
</div>


Related articles