vector_search

Perform vector similarity searches within Typesense collections by specifying a vector query, optional filters, and hybrid text queries to retrieve precise results.

Instructions

Performs a vector similarity search on a specific collection.

Args:
    ctx (Context): The MCP context.
    collection_name (str): The name of the collection to search within.
    vector_query (str): The vector query string, formatted as 'vector_field:([v1,v2,...], k: num_neighbors)'.
    query_by (str | None): Optional: Comma-separated list of text fields for hybrid search query ('q' parameter). Defaults to None.
    filter_by (str | None): Filter conditions to apply before vector search. Defaults to None.
    sort_by (str | None): Optional sorting criteria (less common for pure vector search). Defaults to None.
    per_page (int): Number of results per page. Defaults to 10.
    page (int): Page number to retrieve. Defaults to 1.

Returns:
    dict | str: The vector search results dictionary from Typesense or an error message string.

Input Schema

Name	Required	Description	Default
`collection_name`	Yes
`filter_by`	No
`page`	No
`per_page`	No
`query_by`	No
`sort_by`	No
`vector_query`	Yes

Input Schema (JSON Schema)

{
  "properties": {
    "collection_name": {
      "title": "Collection Name",
      "type": "string"
    },
    "filter_by": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Filter By"
    },
    "page": {
      "default": 1,
      "title": "Page",
      "type": "integer"
    },
    "per_page": {
      "default": 10,
      "title": "Per Page",
      "type": "integer"
    },
    "query_by": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Query By"
    },
    "sort_by": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Sort By"
    },
    "vector_query": {
      "title": "Vector Query",
      "type": "string"
    }
  },
  "required": [
    "collection_name",
    "vector_query"
  ],
  "title": "vector_searchArguments",
  "type": "object"
}

Typesense MCP Server

vector_search

Instructions

Input Schema

Input Schema (JSON Schema)

Other Tools from Typesense MCP Server

Related Tools