Vector Search Pipeline with Embedding Model

Scenario

Deploy an embedding model via OpenSearch to generate text embeddings, then store and index those vectors in OSS for similarity search retrieval — forming a complete semantic search pipeline.

How the products combine

1. opensearch · opensearch-deploy-model — OpenSearch — Deploy embedding model for inference

See opensearch/opensearch-deploy-model.

2. oss · oss-manage-data — Object Storage Service — Manage vector data and indexes

See oss/oss-manage-data.

Typical questions

• build vector search system
• deploy embedding model and store vectors
• semantic search pipeline
• vector similarity search setup
• 部署embedding模型并存储向量索引
• 构建语义搜索系统
• 向量检索pipeline
• embed and index data

Q: How do I set up a semantic search pipeline with an embedding model? A: You can build this pipeline by deploying an embedding model via OpenSearch to generate text embeddings and then storing and indexing those vectors in OSS for similarity search retrieval. This combination uses OpenSearch for inference and OSS for managing vector data and indexes to form a complete semantic search workflow.