我正在尝试通过cURL请求将聊天历史传送到Google Gemini API。我希望在请求中同时提供用户的上一次输入和模型的上一次回应。以下是我使用的cURL命令：

curl --location 'https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=' \--header 'Content-Type: application/json' \--data '{    "contents": [        {            "role": "model",            "parts": [                {                    "text": "...model data"                }            ]        },        {            "role": "user",            "parts": [                {                    "text": "...user input"                }            ]        }    ],    "history": [        {            "role": "user",            "parts": [                {                    "text": "Hello, I have 2 dogs in my house."                }            ]        },        {            "role": "model",            "parts": [                {                    "text": "Great to meet you. What would you like to know?"                }            ]        }    ]}'

我不确定我是否正确地格式化了内容和历史部分。

我期望模型能理解之前的交流并相应地继续对话。

回答：

您需要将聊天内容添加到"parts"列表中，这样Gemini才能记住聊天历史。

示例数据：

{    "contents": [        {            "parts": [                {"text": "User: Hello"},                {"text": "User: What was my previous message?"}            ]        }    ]}

响应：

{  "candidates": [    {      "content": {        "parts": [          {            "text": "Your previous message was: \"Hello\"\n"          }        ],        "role": "model"      },      "finishReason": "STOP",      "avgLogprobs": -0.08453522125879924    }  ],  "usageMetadata": {    "promptTokenCount": 11,    "candidatesTokenCount": 9,    "totalTokenCount": 20  },  "modelVersion": "gemini-1.5-flash"}

对于交互模式，您需要将内容添加到contents列表中，这样Gemini才能记住聊天历史：

示例数据：

{        "contents": [          {"role":"user",           "parts":[{             "text": "Hello"}]},          {"role": "model",           "parts":[{             "text": "Great to meet you. What would you like to know?"}]},          {"role":"user",           "parts":[{             "text": "What was my previous message"}]},        ]}

响应：

{  "candidates": [    {      "content": {        "parts": [          {            "text": "Your previous message was \"Hello\".\n"          }        ],        "role": "model"      },      "finishReason": "STOP",      "avgLogprobs": -0.30310314893722534    }  ],  "usageMetadata": {    "promptTokenCount": 21,    "candidatesTokenCount": 8,    "totalTokenCount": 29  },  "modelVersion": "gemini-1.5-flash"}