LLM JSON Example

llm_example.json

{
  "model": "llm-model-name-goes-here", // Example: "gpt-4-turbo"
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a specified location.",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and optionally state/country, e.g., 'London' or 'Paris, France'"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"],
              "description": "The temperature unit to use."
            }
          },
          "required": ["location"]
        }
      }
    }
    // You could define other tools here
  ],
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant. When asked for the weather, please use the get_weather tool. Default to celsius if no unit is specified by the user."
    },
    {
      "role": "user",
      "content": "What's the weather like in London?"
    },
    {
      "role": "assistant",
      "content": null,
      "tool_calls": [
        {
          "id": "tool_call_london_weather_123",
          "type": "function",
          "function": {
            "name": "get_weather",
            "arguments": "{\"location\": \"London\", \"unit\": \"celsius\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "tool_call_id": "tool_call_london_weather_123",
      "name": "get_weather",
      "content": "{\"temperature\": \"15\", \"unit\": \"celsius\", \"conditions\": \"Cloudy\"}"
    },
    {
      "role": "assistant",
      "content": "The weather in London is 15°C and Cloudy."
    },
    {
      "role": "user",
      "content": "Thanks! And what about Paris, but in Fahrenheit?"
    }

  ]
}