关于GPT的Open API，看这一篇就够了（可搭建自己的ChatGPT）

[
    {
        "role":"system",
        "content":"You are a helpful assistant."
    },
    {
        "role":"user",
        "content":"Who won the world series in 2020?"
    },
    {
        "role":"assistant",
        "content":"The Los Angeles Dodgers won the World Series in 2020."
    }
]

{
  "id": "chatcmpl-123", 
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "\n\nHello there, how may I assist you today?",   // AI的回答内容
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,  // 请求的token长度
    "completion_tokens": 12, // 响应的token长度
    "total_tokens": 21  // 总长度
  }
}

{
  "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7",
  "object": "text_completion",
  "created": 1589478378,
  "model": "text-davinci-003",
  "choices": [
    {
      "text": "\n\nThis is indeed a test",  // AI'的回答
      "index": 0,
      "logprobs": null,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 5, //同上
    "completion_tokens": 7,
    "total_tokens": 12
  }
}

{
  "object": "edit",
  "created": 1589478378,
  "choices": [
    {
      "text": "What day of the week is it?", // AI回复
      "index": 0,
    }
  ],
  "usage": {
    "prompt_tokens": 25,            // 同上
    "completion_tokens": 32,
    "total_tokens": 57
  }
}

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://..." // 图片地址
    },
    {
      "url": "https://..."
    }
  ]
}

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        -0.009327292,
        .... (1536 floats total for ada-002)
        -0.0028842222,     
      ], // 向量
      "index": 0
    }
  ],
  "model": "text-embedding-ada-002",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

{
  "file": "mydata.jsonl",   // 文件路径
  "purpose": "create fine-tunes"
}

{
  "id": "file-XjGxS3KTG0uNmNOK362iJua3", // 文件Id，用于后边创建自己的fine-tunes模型
  "object": "file",
  "bytes": 140,
  "created_at": 1613779121,
  "filename": "mydata.jsonl",
  "purpose": "fine-tune"
}

{
  "id": "ft-AF1WoRqd3aJAHsqc9NY7iL8F",
  "object": "fine-tune",
  "model": "curie",
  "created_at": 1614807352,
  "events": [ // 这里是创建fine-tune过程中的事件，如果创建完成，这里也会对应信息
    {
      "object": "fine-tune-event",
      "created_at": 1614807352,
      "level": "info",
      "message": "Job enqueued. Waiting for jobs ahead to complete. Queue number: 0."
    }
  ],
  "fine_tuned_model": null,
  "hyperparams": {
    "batch_size": 4,
    "learning_rate_multiplier": 0.1,
    "n_epochs": 4,
    "prompt_loss_weight": 0.1,
  },
  "organization_id": "org-...",
  "result_files": [],
  "status": "pending",
  "validation_files": [],
  "training_files": [
    {
      "id": "file-XGinujblHPwGLSztz8cPS8XY",
      "object": "file",
      "bytes": 1547276,
      "created_at": 1610062281,
      "filename": "my-data-train.jsonl",
      "purpose": "fine-tune-train"
    }
  ],
  "updated_at": 1614807352,
}