Amazon OpenSearch Service improves vector database performance and cost with GPU acceleration and auto-optimization
AWS News Blog
This article announces GPU acceleration and auto-optimization features for Amazon OpenSearch Service to improve vector database performance and reduce costs.
- GPU acceleration builds vector databases up to 10x faster at quarter the indexing cost
- Create billion-scale vector databases in under one hour
- Auto-optimization balances search latency, quality, and memory without vector expertise
- No GPU provisioning or idle time charges; pay only for processing via OCU pricing
- Vector ingestion feature automates embedding generation and index optimization from S3
- Available in multiple AWS regions including US East, US West, Asia Pacific, and Europe
These features enable faster, more cost-effective vector database deployment for generative AI applications and large-scale search workloads.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Dec 2
2025
2025
Amazon OpenSearch Service adds GPU-accelerated and auto-optimized vector indexes
Dec 9
2025
2025
Build billion-scale vector databases in under an hour with GPU acceleration on Amazon OpenSearch Service
Dec 9
2025
2025
Auto-optimize your Amazon OpenSearch Service vector database
Nov 19
2024
2024
Disk-optimized vector engine now available on the Amazon OpenSearch Service
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.