# Build RAG-ready indexes from Amazon S3 with Amazon OpenSearch intelligent ingestion

DevFeed: [Build RAG-ready indexes from Amazon S3 with Amazon OpenSearch intelligent ingestion](<https://devfeed.tech/articles/build-rag-ready-indexes-from-amazon-s3-with-amazon-opensearch-intelligent-ingestion-98493.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/build-rag-ready-indexes-from-amazon-s3-with-amazon-opensearch-intelligent-ingestion/>)

Author: Hang Zuo

Published: 2026-10-23T21:50:38Z

Content type: release

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [opensearch](<https://devfeed.tech/topics/opensearch.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [etl](<https://devfeed.tech/topics/etl.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-opensearch-serverless](<https://devfeed.tech/tags/amazon-opensearch-serverless.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-simple-storage-service-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-s3.md>), [amazon-sqs](<https://devfeed.tech/tags/amazon-sqs.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [aws-management-console](<https://devfeed.tech/tags/aws-management-console.md>), [foundational-100](<https://devfeed.tech/tags/foundational-100.md>), [indexes](<https://devfeed.tech/tags/indexes.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [rag](<https://devfeed.tech/tags/rag.md>)

## AI overview

Amazon OpenSearch intelligent ingestion turns data in Amazon S3 into searchable indexes in OpenSearch Serverless (NextGen): it discovers objects, parses PDF and Word documents while retaining structure and tables, describes embedded images, chunks content, generates embeddings, and indexes the results. It also ingests JSON, NDJSON, and CSV, with optional semantic enrichment and transformations. Choose a one-time batch for a static load, continuous streaming for new objects, or batch then stream to backfill existing data and continue monitoring S3 notifications. Setup requires a source bucket and prefix, destination index, and IAM permissions; streams use SQS notifications. Capacity scales within configured OCU limits, and billing covers active processing. Unstructured parsing and image descriptions add costs; the article gives illustrative estimates based on internal testing and notes availability in six AWS Regions.

## Source excerpt

Amazon OpenSearch intelligent ingestion is a fully managed, serverless capability that turns documents and structured data in Amazon S3 into RAG-ready, searchable indexes with no pipelines to manage. Learn how it works and when to use Ingestion Jobs or Ingestion Streams.