{
  "request": {
    "method": "POST",
    "url": "http://localhost:11434/api/generate",
    "headers": {},
    "body": {
      "model": "llama3.2:3b-instruct-fp16",
      "raw": true,
      "prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant. You have access to functions, but you should only use them if they are required.\nYou are an expert in composing functions. You are given a question and a set of possible functions.\nBased on the question, you may or may not need to make one function/tool call to achieve the purpose.\n\nIf you decide to invoke any of the function(s), you MUST put it in the format of [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]\nIf you decide to invoke a function, you SHOULD NOT include any other text in the response. besides the function call in the above format.\nFor a boolean parameter, be sure to use `True` or `False` (capitalized) for the value.\n\n\nHere is a list of functions in JSON format that you can invoke.\n\n[\n    {\n        \"name\": \"get_weather\",\n        \"description\": \"Get the current weather\",\n        \"parameters\": {\n            \"type\": \"dict\",\n            \"required\": [\"location\"],\n            \"properties\": {\n                \"location\": {\n                    \"type\": \"string\",\n                    \"description\": \"The city and state (both required), e.g. San Francisco, CA.\"\n                }\n            }\n        }\n    }\n]\n\nYou can answer general questions or invoke tools when necessary.\nIn addition to tool calls, you should also augment your responses by using the tool outputs.\nPretend you are a weather assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat's the weather like in San Francisco, CA?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
      "options": {
        "temperature": 0.0
      },
      "stream": false
    },
    "endpoint": "/api/generate",
    "model": "llama3.2:3b-instruct-fp16"
  },
  "response": {
    "body": {
      "__type__": "ollama._types.GenerateResponse",
      "__data__": {
        "model": "llama3.2:3b-instruct-fp16",
        "created_at": "2025-08-04T22:55:13.25248Z",
        "done": true,
        "done_reason": "stop",
        "total_duration": 1344654917,
        "load_duration": 200585375,
        "prompt_eval_count": 326,
        "prompt_eval_duration": 564000000,
        "eval_count": 11,
        "eval_duration": 578000000,
        "response": "[get_weather(location=\"San Francisco, CA\")]",
        "thinking": null,
        "context": null
      }
    },
    "is_streaming": false
  }
}