Vector search

OpenSearch vector search provides a complete vector database solution for building efficient AI applications. Store and search vector embeddings alongside your existing data, making it easy to implement semantic search, retrieval-augmented generation (RAG), recommendation systems, and other AI-powered applications.

Get started with vector search

Build powerful similarity search applications using your existing vectors or embeddings

Generate embeddings automatically

Streamline your vector search using OpenSearch's built-in embedding generation

Overview

You can bring your own vectors or let OpenSearch generate embeddings automatically from your data. See Preparing vectors.

1

Create an index

Create a vector index for storing your embeddings.

2

Ingest your data into the index.

3

Use raw vector search or AI-powered methods like semantic, hybrid, multimodal, or neural sparse search. Add RAG to build conversational search.

Build your solution

AI search

Discover AI search, from semantic, hybrid, and multimodal search to RAG

Tutorials

Follow step-by-step tutorials to build AI-powered search for your applications

Advanced filtering

Refine search results while maintaining semantic relevance

Memory-efficient search

Reduce memory footprint using vector compression methods

Sparse vector support

Combine semantic understanding with traditional search efficiency using neural sparse search

Multi-vector support

Store and search multiple vectors per document using nested fields

Overview
Build your solution

WAS THIS PAGE HELPFUL?

✔ Yes ✖ No

Tell us why

350 characters left

Have a question? Ask us on the OpenSearch forum.

Want to contribute? Edit this page or create an issue.