{
  "id": 14773212,
  "title": "Vector search on S3, without a hosted vector database",
  "url": "https://urgent.news/2026/10/15/vector-search-on-s3-without-a-hosted-vector-database",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-10-15T19:35:01.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/mixpeek/vector-search-on-s3-without-a-hosted-vector-database-d6d"
  },
  "original_language": "en",
  "account": "You can store and search vectors directly in S3, without needing a hosted vector database. Three options are available today. AWS S3 Vectors handles embeddings in a special bucket type, answering similarity queries via an API. LanceDB writes columnar vectors to any S3 path and queries from your process. Mixpeek's MVS is a vector store built on object storage, keeping index and payloads in your bucket, and running dense, sparse, and BM25 search over them. Factors to consider in switching include cold latency, hybrid search capabilities, query-time filters, and write paths. MVS, in particular, imports vectors from other vector stores like Pinecone, Qdrant, or Weaviate without re-embedding.",
  "summary": "You can keep your vectors in S3 and search them there. Three ways work today. AWS S3 Vectors stores embeddings in a special bucket type and answers similarity queries through an API. LanceDB writes a columnar vector format to any S3 path and queries it from your process. A vector store built on object storage, such as Mixpeek's MVS, keeps the index and payloads in your bucket and runs dense,…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}