{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/vector-search.filtered-tenant/",
    "json": "https://www.anchorterminal.com/niches/vector-search.filtered-tenant/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/vector-search.filtered-tenant/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/vector-search.filtered-tenant/index.min.md"
  },
  "markdown": "Four or more companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 4 | 10 | 17 | 16 | 9 |\n\n## What counts as done\n\nEvery result matches the filter, the result count equals the requested k when k matches exist, and no other tenant's records appear.\n\nMeasured, for our own tests: p95 latency with a filter matching 1 per cent of records is within twice the unfiltered p95.\n\nHow agents ask for it: search only this customer's documents; results from 2025 only; only from the HR folder; this user's memories\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Meilisearch (Meili SAS)**: Results are first filtered, then ranked within the filtered set, and tenant tokens restrict each user's searches to their own records.\n- **Milvus and Zilliz Cloud API + MCP (Zilliz Inc.)**: Filtered search applies metadata filtering before the ANN search, so limit comes from matching entities, and multi-tenancy is offered at database, collection, partition or partition-key level.\n- **Pinecone API + MCP (Pinecone Systems Inc.)**: The optional filter narrows candidates before ranking, so top_k comes from matching documents, and namespaces separate tenants in one index.\n- **Vespa (Vespa.ai AS)**: nearestNeighbor combines with query filters and Vespa chooses pre- or post-filtering, and streaming mode searches one user's or tenant's subset without a shared index.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Chroma API + MCP (Chroma Inc.)**: Metadata where filters and tenant and database scoping exist, but #4089 reports where filters breaking queries over 20 million chunks on a Docker server, and pre- versus post-filtering is not stated on the pages read.\n- **Cloudflare AI Search (Cloudflare, Inc.)**: Metadata filters apply before retrieval, and namespaces and folders separate content, but filters match only the first 64 bytes of a string, and no latency figure for selective filters is given.\n- **Elasticsearch (Elasticsearch B.V.)**: A filter inside the knn clause is applied during approximate search so k matching documents return, but #162043 found a nested-field pre-filter returning nothing, the use case's named blocker; it is now closed.\n- **Epsilla Vector Database (Epsilla, Inc.)**: query takes a boolean filter expression, but the docs do not say whether it applies before or after ranking, and no tenant or namespace feature was found.\n- **LanceDB (LanceDB Systems, Inc.)**: where(..., prefilter=True) filters before the vector search, but #3095 found prefilter inverted on hybrid queries (now closed as fixed), and tenant separation means separate tables.\n- **OpenSearch (OpenSearch Software Foundation, a project of The Linux Foundation)**: Efficient k-NN filtering applies the filter during the vector search so k results return (Lucene HNSW, Faiss HNSW and IVF), but #203 (open) shows the MCP server ignoring filters in multi mode.\n- **Qdrant API + MCP (Qdrant Solutions GmbH)**: Filters apply inside the HNSW search via payload indexes, with ACORN for strict filters and is_tenant partitioning, but #7211 reports recall dropping with multitenancy and #7210 high filtered latency at 4.6M points.\n- **Typesense API + MCP (Typesense, Inc.)**: filter_by applies during the vector search and scoped search keys can embed a tenant filter, but #3159 shows a broad filter with a small intersection taking seconds, well past the twice-unfiltered latency bar.\n- **Upstash Vector API + MCP (Upstash, Inc.)**: Namespaces separate tenants, but filtering is in-filtering within a budget that falls back to post-filtering, and the docs say highly selective filters may return fewer than topK results.\n- **Weaviate API + MCP (Weaviate B.V.)**: Multi-tenancy stores each tenant on its own shard, invisible to others, and filters run with ACORN, but #7681 reports hybrid filters not acting as strict pre-filters.\n\n## What stops agents finishing\n\n- filter applied after ranking so fewer than k results come back\n- filter ignored in one tool mode\n- nested-field filter returns nothing without an error\n\n## Around it\n\nBefore: agent-auth.resolve-user. After: vector-search.rag-over-docs.\n\n## Where this comes from\n\nWeight 16 of 100 in Retrieval \u0026 vector search: 9 of 37 accounts, almost all failures (filters ignored, post-filtered, inverted, slow or returning nothing); weighted for how often filters decide correctness\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/vector-search.filtered-tenant.json, or the MCP tool get_use_case with id vector-search.filtered-tenant. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Search inside one tenant, user or metadata slice",
        "url": ""
      }
    ],
    "description": "Search inside one tenant, user or metadata slice: 4 companies fully do it, 10 with a limit, 17 carry the tag. Every listing in Retrieval \u0026 vector search with the reason and a source.",
    "facts": null,
    "h1": "Search inside one tenant, user or metadata slice",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/vector-search.filtered-tenant/",
    "published": "",
    "section": "agents",
    "title": "Search inside one tenant, user or metadata slice | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/vector-search.filtered-tenant/"
  },
  "tokens": {
    "markdown": 1400,
    "slim": 330
  },
  "version": 1
}
