Amazon OpenSearch Ingestion now supports batch AI inference
News
Amazon OpenSearch Ingestion now supports batch AI inference, enabling users to efficiently enrich and ingest large datasets for OpenSearch Service domains.
- Previously supported real-time inference using AI connectors to Bedrock, SageMaker, and other services
- New batch inference feature allows asynchronous processing of large datasets
- Can generate and ingest up to billions of vector embeddings
- Supports enrichments like vector embeddings, predictions, translations, and recommendations
- Batch mode offers higher performance and cost efficiency compared to real-time inference
The feature is available in all regions supporting Amazon OpenSearch Ingestion and 2.17+ domains, providing more flexible AI-powered data processing capabilities.
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
Sep 19
2025
2025
Amazon OpenSearch Ingestion now supports cross-account ingestion
Aug 20
2025
2025
Amazon OpenSearch Service now supports AI-powered forecasting
Sep 19
2025
2025
Announcing cross-account ingestion for Amazon OpenSearch Service
Aug 18
2025
2025
Amazon Bedrock now supports Batch inference for Anthropic Claude Sonnet 4 and OpenAI GPT-OSS models
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.