{
  "listings": [
    {
      "slug": "meilisearch",
      "name": "Meilisearch",
      "company": "Meili SAS",
      "grade": "A",
      "fit": "yes",
      "why": "Results are first filtered, then ranked within the filtered set, and tenant tokens restrict each user's searches to their own records.",
      "source": "https://www.meilisearch.com/docs/capabilities/filtering_sorting_faceting/how_to/search_and_filter_together.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/meilisearch"
    },
    {
      "slug": "milvus-zilliz",
      "name": "Milvus and Zilliz Cloud API + MCP",
      "company": "Zilliz Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "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.",
      "source": "https://raw.githubusercontent.com/milvus-io/milvus-docs/v3.0.x/site/en/userGuide/search-query-get/filtered-search.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/milvus-zilliz"
    },
    {
      "slug": "pinecone",
      "name": "Pinecone API + MCP",
      "company": "Pinecone Systems Inc.",
      "grade": "A",
      "fit": "yes",
      "why": "The optional filter narrows candidates before ranking, so top_k comes from matching documents, and namespaces separate tenants in one index.",
      "source": "https://docs.pinecone.io/guides/get-started/documents-api.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/pinecone"
    },
    {
      "slug": "vespa",
      "name": "Vespa",
      "company": "Vespa.ai AS",
      "grade": "BB",
      "fit": "yes",
      "why": "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.",
      "source": "https://docs.vespa.ai/en/querying/approximate-nn-hnsw.html.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/vespa"
    },
    {
      "slug": "chroma",
      "name": "Chroma API + MCP",
      "company": "Chroma Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.trychroma.com/llms.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/chroma"
    },
    {
      "slug": "cloudflare-ai-search",
      "name": "Cloudflare AI Search",
      "company": "Cloudflare, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://developers.cloudflare.com/ai-search/configuration/retrieval/filtering/index.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cloudflare-ai-search"
    },
    {
      "slug": "elasticsearch",
      "name": "Elasticsearch",
      "company": "Elasticsearch B.V.",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://www.elastic.co/docs/solutions/search/vector/knn/filtered-knn-search",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/elasticsearch"
    },
    {
      "slug": "epsilla",
      "name": "Epsilla Vector Database",
      "company": "Epsilla, Inc.",
      "grade": "E",
      "fit": "caveat",
      "why": "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.",
      "source": "https://epsilla-inc.gitbook.io/epsilladb/epsilla-vector-database/user-manual/search-the-top-k-semantically-similar-records.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/epsilla"
    },
    {
      "slug": "lancedb",
      "name": "LanceDB",
      "company": "LanceDB Systems, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.lancedb.com/oss/v0-41-0/search/filtering.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/lancedb"
    },
    {
      "slug": "opensearch",
      "name": "OpenSearch",
      "company": "OpenSearch Software Foundation, a project of The Linux Foundation",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.opensearch.org/latest/vector-search/filter-search-knn/index/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/opensearch"
    },
    {
      "slug": "qdrant",
      "name": "Qdrant API + MCP",
      "company": "Qdrant Solutions GmbH",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://qdrant.tech/documentation/search/search.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/qdrant"
    },
    {
      "slug": "typesense",
      "name": "Typesense API + MCP",
      "company": "Typesense, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://typesense.org/docs/30.2/api/vector-search.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/typesense"
    },
    {
      "slug": "upstash-vector",
      "name": "Upstash Vector API + MCP",
      "company": "Upstash, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://upstash.com/docs/vector/features/filtering.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/upstash-vector"
    },
    {
      "slug": "weaviate",
      "name": "Weaviate API + MCP",
      "company": "Weaviate B.V.",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.weaviate.io/weaviate/manage-collections/multi-tenancy.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/weaviate"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "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"
  },
  "useCase": {
    "accounts": 9,
    "after": [
      "vector-search.rag-over-docs"
    ],
    "area": "developer",
    "asks": [
      "search only this customer's documents",
      "results from 2025 only",
      "only from the HR folder",
      "this user's memories"
    ],
    "before": [
      "agent-auth.resolve-user"
    ],
    "blockers": [
      "filter applied after ranking so fewer than k results come back",
      "filter ignored in one tool mode",
      "nested-field filter returns nothing without an error"
    ],
    "capabilities": [
      "db.filters",
      "db.vector"
    ],
    "category": "vector-search",
    "categoryName": "Retrieval \u0026 vector search",
    "checked": "2026-11-15",
    "companies": {
      "fit": 4,
      "fitWithLimit": 10,
      "tagged": 17
    },
    "competition": "crowded",
    "fits": [
      "meilisearch",
      "milvus-zilliz",
      "pinecone",
      "vespa"
    ],
    "fitsWithLimit": [
      "chroma",
      "cloudflare-ai-search",
      "elasticsearch",
      "epsilla",
      "lancedb",
      "opensearch",
      "qdrant",
      "typesense",
      "upstash-vector",
      "weaviate"
    ],
    "id": "vector-search.filtered-tenant",
    "listings": {
      "caveat": 10,
      "no": 0,
      "notRead": 0,
      "tagged": 17,
      "unchecked": 0,
      "yes": 4
    },
    "name": "Search inside one tenant, user or metadata slice",
    "status": "draft",
    "success": "Every result matches the filter, the result count equals the requested k when k matches exist, and no other tenant's records appear. Measured: p95 latency with a filter matching 1 per cent of records is within twice the unfiltered p95.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/vector-search.filtered-tenant.json",
    "weight": 16,
    "weightBasis": "9 of 37 accounts, almost all failures (filters ignored, post-filtered, inverted, slow or returning nothing); weighted for how often filters decide correctness"
  }
}
