This feature automates the ingestion process with minimal setup, supporting structured data formats like JSON and unstructured documents such as PDFs and Word files stored in S3. It detects data types, parses text, generates vector embeddings, and indexes content for semantic search without customers needing to manage ingestion infrastructure.
Additionally, visual elements within documents are analyzed using vision-language models to create searchable text descriptions. Intelligent ingestion supports one-time and continuous syncing ingestion jobs, scales capacity automatically, and is available across multiple AWS regions, enhancing search capabilities for both logs and complex document data.
Source & further reading
Amazon OpenSearch Service introduces intelligent ingestion for logs and documents in Amazon S3 ↗Source published 2026-10-22. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.