create_embeddings

Generate embeddings for text using the Grok API, specifying model, input, encoding format, and dimensions for accurate vector representations.

Instructions

Create embeddings for text with the Grok API

Input Schema

Name	Required	Description
`dimensions`	No	The number of dimensions the resulting output embeddings should have
`encoding_format`	No	The format to return the embeddings in
`input`	Yes	Input text to get embeddings for
`model`	Yes	ID of the model to use
`user`	No	A unique user identifier

Input Schema (JSON Schema)

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "dimensions": {
      "description": "The number of dimensions the resulting output embeddings should have",
      "exclusiveMinimum": 0,
      "type": "integer"
    },
    "encoding_format": {
      "description": "The format to return the embeddings in",
      "enum": [
        "float",
        "base64"
      ],
      "type": "string"
    },
    "input": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "items": {
            "type": "number"
          },
          "type": "array"
        },
        {
          "items": {
            "items": {
              "type": "number"
            },
            "type": "array"
          },
          "type": "array"
        }
      ],
      "description": "Input text to get embeddings for"
    },
    "model": {
      "description": "ID of the model to use",
      "type": "string"
    },
    "user": {
      "description": "A unique user identifier",
      "type": "string"
    }
  },
  "required": [
    "model",
    "input"
  ],
  "type": "object"
}

Grok MCP Server

create_embeddings

Instructions

Input Schema

Input Schema (JSON Schema)

Other Tools from Grok MCP Server

Related Tools

MCP directory API