Cortexa research tool·cs ml·embedding

Embedding Database Search

Semantic search over a per-collection datastore using FAISS (cosine via L2-normalized vectors). Supports optional metadata filtering.

Livelast probed 2026-04-30 23:07Z· 142msCortexa

Status

The most recent probe succeeded. Safe to call from the agent today.

Last probed: 1d ago
Last success: 1d ago
Last latency: 142ms

Schema

JSON Schema the agent (or your API call) must match.

{
  "properties": {
    "action": {
      "const": "search",
      "type": "string"
    },
    "database_name": {
      "description": "Collection/database name to search",
      "type": "string"
    },
    "filters": {
      "additionalProperties": true,
      "default": {},
      "description": "Optional metadata filters ('$gte', '$lte', '$in', '$contains', exact match)",
      "type": "object"
    },
    "model": {
      "description": "Embedding model/deployment id for the query vector. Defaults to collection/env.",
      "type": "string"
    },
    "provider": {
      "description": "Embedding backend for the query vector. Defaults to collection/env.",
      "enum": [
        "openai",
        "azure",
        "huggingface",
        "local"
      ],
      "type": "string"
    },
    "query": {
      "description": "Query text to embed and search with",
      "type": "string"
    },
    "top_k": {
      "default": 5,
      "description": "Number of most similar documents to return",
      "maximum": 1000,
      "minimum": 1,
      "type": "integer"
    }
  },
  "required": [
    "database_name",
    "query"
  ],
  "type": "object"
}

Examples (1)

Default Embedding Database Search call

public-safeinput

{
  "database_name": "",
  "query": "BRCA1",
  "top_k": 1
}

Expected response keys: success

Anonymous-safe example. Rate-limited; no sign-in required.

Identifiers

Catalog ID: tu_embedding_database_search
Tool name: embedding_database_search
Added: 2026-04-30 22:47Z
Tags: tooluniverse

Schema

JSON Schema the agent (or your API call) must match.

{ "properties": { "action": { "const": "search", "type": "string" }, "database_name": { "description": "Collection/database name to search", "type": "string" }, "filters": { "additionalProperties": true, "default": {}, "description": "Optional metadata filters ('$gte', '$lte', '$in', '$contains', exact match)", "type": "object" }, "model": { "description": "Embedding model/deployment id for the query vector. Defaults to collection/env.", "type": "string" }, "provider": { "description": "Embedding backend for the query vector. Defaults to collection/env.", "enum": [ "openai", "azure", "huggingface", "local" ], "type": "string" }, "query": { "description": "Query text to embed and search with", "type": "string" }, "top_k": { "default": 5, "description": "Number of most similar documents to return", "maximum": 1000, "minimum": 1, "type": "integer" } }, "required": [ "database_name", "query" ], "type": "object" }