End-to-End Vector Search Pipeline

Scenario

Upload source documents to OSS, deploy an embedding model on OpenSearch to generate vector embeddings from those documents, then store and index the resulting vectors in OSS for similarity search retrieval — a complete semantic search or RAG ingestion pipeline.

How the products combine

1. oss · oss-manage-objects — Object Storage Service — Manage storage objects (upload, download, copy, etc.)

See oss/oss-manage-objects.

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

See opensearch/opensearch-deploy-model.

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

See oss/oss-manage-data.

Typical questions

• build vector search pipeline
• RAG ingestion with OSS
• upload documents and create vector index
• semantic search end to end
• store embeddings in OSS
• deploy model then index vectors
• 向量搜索流水线
• 上传文档生成向量索引

Q: How do I build an end-to-end vector search or RAG ingestion pipeline using OpenSearch and OSS? A: You can build this pipeline by uploading source documents to OSS, deploying an embedding model on OpenSearch to generate vectors, and indexing those vectors back in OSS for similarity search or RAG ingestion. The workflow integrates object management, model deployment, and vector index management across both services.