Action: Create Chat Completion

Mistral AI Operation

The Create Chat Completion action generates a response from the model based on the provided conversation history and input.

Example User Story

I want to get a quick, helpful response from the AI so I can ask questions and receive clear answers in real time.

Fields

Field Name	Field Type	Required
model	String	Yes
messages	Array	Yes
temperature	Float	No
max_tokens	Integer	No

Related Connections

Mistral AI

Related Automations

Example link

Code (Apache v2.0): Operation

{
  "handle": "create-chat-completion",
  "state": "inDev",
  "meta": {
    "short": "Create Chat Completion",
    "description": "Generates a chat completion response using the Mistral AI API."
  },
  "input": [
    {
      "name": "model",
      "type": "String",
      "required": true,
      "meta": {
        "description": "ID of the model to use for chat completion."
      }
    },
    {
      "name": "messages",
      "type": "Array",
      "required": true,
      "meta": {
        "description": "List of messages in the chat."
      }
    },
    {
      "name": "temperature",
      "type": "Float",
      "required": false,
      "meta": {
        "description": "Controls randomness in the response (0.0 to 1.0)."
      }
    },
    {
      "name": "max_tokens",
      "type": "Integer",
      "required": false,
      "meta": {
        "description": "Maximum number of tokens to generate."
      }
    }
  ],
  "output": [
    {
      "name": "response",
      "type": "String",
      "selector": ["choices", "0", "message", "content"],
      "meta": {
        "description": "Generated chat completion response."
      }
    }
  ],
  "steps": [
    {
      "type": "http",
      "http": {
        "method": "POST",
        "path": "/v1/chat/completions",
        "headers": {
          "Content-Type": "application/json"
        },
        "bodyTemplate": {
          "value": "{\"model\": \"{{model}}\", \"messages\": {{messages}}, \"temperature\": {{temperature}}, \"max_tokens\": {{max_tokens}}}",
          "placeholders": [
            {
              "name": "model",
              "type": "String",
              "description": "ID of the model to use.",
              "required": true
            },
            {
              "name": "messages",
              "type": "Array",
              "description": "List of messages in the chat.",
              "required": true
            },
            {
              "name": "temperature",
              "type": "Float",
              "description": "Controls randomness in the response.",
              "required": false
            },
            {
              "name": "max_tokens",
              "type": "Integer",
              "description": "Maximum number of tokens to generate.",
              "required": false
            }
          ]
        }
      }
    }
  ]
}