自 2025 年 4 月 29 日起,Gemini 1.5 Pro 和 Gemini 1.5 Flash 模型將無法用於先前未使用這些模型的專案,包括新專案。詳情請參閱「
模型版本和生命週期」。
控管產生 JSON 輸出內容,並包含空值
透過集合功能整理內容
你可以依據偏好儲存及分類內容。
如果模型沒有足夠的脈絡資訊來生成有意義的回覆,請允許模型輸出空值回覆。
程式碼範例
除非另有註明,否則本頁面中的內容是採用創用 CC 姓名標示 4.0 授權,程式碼範例則為阿帕契 2.0 授權。詳情請參閱《Google Developers 網站政策》。Java 是 Oracle 和/或其關聯企業的註冊商標。
[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["難以理解","hardToUnderstand","thumb-down"],["資訊或程式碼範例有誤","incorrectInformationOrSampleCode","thumb-down"],["缺少我需要的資訊/範例","missingTheInformationSamplesINeed","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],[],[],[],null,["# Controlled generation JSON output with null values\n\nAllow the model to output null responses when it doesn't have enough context to generate a meaningful response.\n\nCode sample\n-----------\n\n### C#\n\n\nBefore trying this sample, follow the C# setup instructions in the\n[Vertex AI quickstart using\nclient libraries](/vertex-ai/docs/start/client-libraries).\n\n\nFor more information, see the\n[Vertex AI C# API\nreference documentation](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1/latest).\n\n\nTo authenticate to Vertex AI, set up Application Default Credentials.\nFor more information, see\n\n[Set up authentication for a local development environment](/docs/authentication/set-up-adc-local-dev-environment).\n\n public async Task\u003cstring\u003e GenerateContentWithResponseSchema3(\n string projectId = \"your-project-id\",\n string location = \"us-central1\",\n string publisher = \"google\",\n string model = \"gemini-2.0-flash-001\")\n {\n\n var predictionServiceClient = new PredictionServiceClientBuilder\n {\n Endpoint = $\"{location}-aiplatform.googleapis.com\"\n }.Build();\n\n var responseSchema = new OpenApiSchema\n {\n Type = Type.Object,\n Properties =\n {\n [\"forecast\"] = new()\n {\n Type = Type.Array,\n Items = new()\n {\n Type = Type.Object,\n Properties =\n {\n [\"Forecast\"] = new() { Type = Type.String },\n [\"Humidity\"] = new() { Type = Type.String },\n [\"Temperature\"] = new() { Type = Type.Integer },\n [\"Wind Speed\"] = new() { Type = Type.Integer }\n }\n }\n }\n }\n };\n\n string prompt = @\"\n The week ahead brings a mix of weather conditions.\n Sunday is expected to be sunny with a temperature of 77°F and a humidity level of 50%. Winds will be light at around 10 km/h.\n Monday will see partly cloudy skies with a slightly cooler temperature of 72°F and humidity increasing to 55%. Winds will pick up slightly to around 15 km/h.\n Tuesday brings rain showers, with temperatures dropping to 64°F and humidity rising to 70%. Expect stronger winds at 20 km/h.\n Wednesday may see thunderstorms, with a temperature of 68°F and high humidity of 75%. Winds will be gusty at 25 km/h.\n Thursday will be cloudy with a temperature of 66°F and moderate humidity at 60%. Winds will ease slightly to 18 km/h.\n Friday returns to partly cloudy conditions, with a temperature of 73°F and lower humidity at 45%. Winds will be light at 12 km/h.\n Finally, Saturday rounds off the week with sunny skies, a temperature of 80°F, and a humidity level of 40%. Winds will be gentle at 8 km/h.\";\n\n var generateContentRequest = new GenerateContentRequest\n {\n Model = $\"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}\",\n Contents =\n {\n new Content\n {\n Role = \"USER\",\n Parts =\n {\n new Part { Text = prompt }\n }\n }\n },\n GenerationConfig = new GenerationConfig\n {\n ResponseMimeType = \"application/json\",\n ResponseSchema = responseSchema\n },\n };\n\n GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);\n\n string responseText = response.Candidates[0].Content.Parts[0].Text;\n Console.WriteLine(responseText);\n\n return responseText;\n }\n\nWhat's next\n-----------\n\n\nTo search and filter code samples for other Google Cloud products, see the\n[Google Cloud sample browser](/docs/samples?product=generativeaionvertexai)."]]