如何使用curl从Gemini 1.5 API获取JSON格式的数据？下面的代码可以正常工作：

curl -H 'Content-Type: application/json'      -H "x-goog-api-key: ${API_KEY}"      -d '{"contents":[            {"role": "user",              "parts":[{"text": "Give me five subcategories of jazz?"}]}]}'      "https://generativelanguage.googleapis.com/v1/models/gemini-pro:generateContent"

但是当我尝试添加以下内容时：

,"generation_config": {"response_mime_type": "application/json"}}

结果如下：

curl -H 'Content-Type: application/json' -H "x-goog-api-key: ${API_KEY}" -d '{"contents":[            {"role": "user",              "parts":[{"text": "Give me five subcategories of jazz?"}]},"generation_config": {"response_mime_type": "application/json"},]'      "https://generativelanguage.googleapis.com/v1/models/gemini-1.5-flash:generateContent"

我收到了以下错误响应：

"error": {    "code": 400,    "message": "Invalid JSON payload received. Unknown name \"response_mime_type\" at 'generation_config': Cannot find field.",    "status": "INVALID_ARGUMENT",    "details": [      {        "@type": "type.googleapis.com/google.rpc.BadRequest",        "fieldViolations": [          {            "field": "generation_config",            "description": "Invalid JSON payload received. Unknown name \"response_mime_type\" at 'generation_config': Cannot find field."          }        ]      }    ]  }

我尝试了几个不同的模型（例如gemini-1.5-pro-latest），结果总是相同。

回答：

试试这个。

curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY \    -H 'Content-Type: application/json' \    -X POST \    -d '{        "contents": [{            "parts":[                {"text": "Write a story about a magic backpack."}            ]        }],        "safetySettings": [            {                "category": "HARM_CATEGORY_DANGEROUS_CONTENT",                "threshold": "BLOCK_ONLY_HIGH"            }        ],        "generationConfig": {            "stopSequences": [                "Title"            ],            "temperature": 1.0,            "maxOutputTokens": 800,            "topP": 0.8,            "topK": 10,            "responseMimeType": "application/json"        }    }'  2> /dev/null | grep "text"