> ## Documentation Index
> Fetch the complete documentation index at: https://incredible-42686482-cursor-create-detailed-ai-agent-cookboo.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# How to implement Function Calling

> Define functions, detect calls, execute them, and return results

### **Defining functions**

This request is an example of **function calling**. You’re telling the AI model not only *what the user said* but also *what tools (functions) are available* for it to use.

<table style={{ width: '100%', borderCollapse: 'separate' }}>
  <thead>
    <tr>
      <th style={{ textAlign: 'left', padding: '12px 16px', width: '26%' }}>Field</th>
      <th style={{ textAlign: 'left', padding: '12px 16px' }}>Description</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{ padding: '12px 16px' }}><code>model</code></td>
      <td style={{ padding: '12px 16px' }}>Specifies which AI model will process the request.</td>
    </tr>

    <tr>
      <td style={{ padding: '12px 16px' }}><code>functions</code></td>
      <td style={{ padding: '12px 16px' }}>A cookbook of tools. Each function has a name, description, and parameters. Here, <code>get\_weather</code> is defined to fetch weather details.</td>
    </tr>

    <tr>
      <td style={{ padding: '12px 16px' }}><code>parameters</code></td>
      <td style={{ padding: '12px 16px' }}>Describes the function inputs. Requires <code>location</code>; optionally <code>unit</code> (<code>celsius</code> or <code>fahrenheit</code>).</td>
    </tr>

    <tr>
      <td style={{ padding: '12px 16px' }}><code>messages</code></td>
      <td style={{ padding: '12px 16px' }}>Represents the conversation history. The user asked, “What is the weather like in San Francisco?”</td>
    </tr>
  </tbody>
</table>

Here is an example function definition for a `get_weather` function:

```jsx
{
    "model": "small-1",
    "functions": [
      {
        "name": "get_weather",
        "description": "Get current weather information for a specific location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "City name or coordinates"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"],
              "description": "Temperature unit"
            }
          },
          "required": ["location"]
        }
      }
    ],
    "messages": [
      {
        "role": "user",
        "content": "What is the weather like in San Francisco?"
      }
    ]
}
```

### Handling Function Calls

When the model calls a function, you must execute it and return the result. Since model responses can include zero, one, or multiple calls, it is best practice to assume there are several.

Sample response with multiple function calls:

```jsx
{
    "result": {
        "response": [
	        {
	            "content": "\nI'll get the current weather information for San Francisco for you.\n",
	            "role": "assistant"
	        }, 
	        {
	            "type": "function_call"
	            "function_call_id": "664fdcb1-f26b-4a3c-a96d-beb733f321b1",
	            "function_calls": [
		            {
		                "name": "get_weather"
		                "input": {
		                    "location": "San Francisco"
		                },
		            }
	            ],
	        }
        ],
        "thinking": "The user is asking about the weather in San Francisco. I need to use the `get_weather` function to get this information. Looking at the function description:\n\n- `location` (required): City name or coordinates (type: string)\n- `unit` (optional): Temperature unit (type: string), allowed values: celsius, fahrenheit\n\nThe user provided \"San Francisco\" as the location, which is a city name. They didn't specify a temperature unit, and since it's optional, I don't need to ask for it. I'll just call the function with the location parameter.\n\nI need to use the `run_function` tool to write code that calls the `get_weather` function."
    }
}
```

<p><code>function\_call\_id</code> is a unique identifier for a specific function call. You will use this ID when you later submit the <em>result</em> of that call back to the model so it can associate the output with the correct request.</p>

<p><code>function\_calls</code> contains one or more function invocations in the order the model wants them executed. If multiple functions are requested, execute them and return their results <strong>in the same order</strong> so the model can reason correctly over each output.</p>

<div style={{ border: '1px solid #FF6200', borderRadius: '12px', padding: '16px', margin: '16px 0', background: 'rgba(255, 98, 0, 0.08)' }}>
  <strong>Quick note:</strong> The model can also perform other types of server-side actions, and will include the results from those in the response. The full response needs to be added to future messages. Tip: copy all items from the response into your messages so the model can use them in subsequent steps.
</div>

### Providing Tool Results

After executing the function, send the results back in a follow-up message to let the agentic model continue.

```jsx
{
    "model": "small-1",
    "functions": [ ...same as before ],
    "messages": [
      { 
	      "role": "user", 
	      "content": "What is the weather like in San Francisco?" 
      },
      {
          "content": "\nI'll get the current weather information for San Francisco for you.\n",
          "role": "assistant"
      }, 
      {
          "type": "function_call"
          "function_call_id": "664fdcb1-f26b-4a3c-a96d-beb733f321b1",
          "function_calls": [
            {
                "name": "get_weather"
                "input": {
                    "location": "San Francisco"
                },
            }
          ],
	    },
	    {
	        "type": "function_call_result",
	        "function_call_id": "664fdcb1-f26b-4a3c-a96d-beb733f321b1",
	        "function_call_results": [
		        { "degrees": 14 }
	        ]
      }
    ]
}
```