Amazon OpenSearch Serverless adds support for Hybrid Search, AI connectors, and automations

Amazon OpenSearch Serverless announces support for Neural Search, Hybrid Search, Workflow API, and AI connectors. This new set of APIs facilitates use cases such as retrieval augmented generation (RAG) and semantic search.

Neural search enables semantic queries through text and images instead of vectors. Neural search uses a high-level API with connectors to Amazon SageMaker, Amazon Bedrock, and other AI services to generate enrichments like dense or sparse vectors during query and ingestion. Hybrid search enables combining lexical, neural, and k-NN (vector) queries to deliver higher search relevancy. The workflow API allows you to package OpenSearch AI resources like models, connectors, and pipelines into templates to automate multi-step configurations required to enable AI features such as neural search, and simplified integration with specific model providers like Amazon Bedrock, Cohere, OpenAI or DeepSeek.

Neural Search, Hybrid Search, Workflow API, and AI connectors are enabled for all serverless collections in the following regions: US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Europe (Frankfurt), Europe (Ireland), Europe (Spain), Europe (Stockholm). Check the AWS Regional Services List for availability in your region.

For more information about these features, please see the documentation for Neural Search, Hybrid Search, Workflow API, and AI connectors. To learn more about Amazon OpenSearch Serverless, please visit the product page.