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」。
建立參數化提示範本
透過集合功能整理內容
你可以依據偏好儲存及分類內容。
這個程式碼範例說明如何建構參數化提示範本,以產生多組變數的內容。
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,["# Create a parameterized prompt template\n\nThis code sample shows how to build a parameterized prompt template to generate content with multiple variable sets.\n\nCode sample\n-----------\n\n### Python\n\n\nBefore trying this sample, follow the Python 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 Python API\nreference documentation](/python/docs/reference/aiplatform/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 import https://cloud.google.com/python/docs/reference/vertexai/latest/\n from vertexai.preview.prompts import Prompt\n\n # Initialize vertexai\n https://cloud.google.com/python/docs/reference/vertexai/latest/.init(project=PROJECT_ID, location=\"us-central1\")\n\n variables = [\n {\"animal\": \"Eagles\", \"activity\": \"eat berries\"},\n {\"animal\": \"Coyotes\", \"activity\": \"jump\"},\n {\"animal\": \"Squirrels\", \"activity\": \"fly\"}\n ]\n\n # define prompt template\n prompt = Prompt(\n prompt_data=\"Do {animal} {activity}?\",\n model_name=\"gemini-2.0-flash-001\",\n variables=variables,\n system_instruction=\"You are a helpful zoologist\"\n # generation_config=generation_config, # Optional\n # safety_settings=safety_settings, # Optional\n )\n\n # Generates content using the assembled prompt.\n responses = []\n for variable_set in prompt.variables:\n response = prompt.https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.prompts.Prompt.html#vertexai_preview_prompts_Prompt_generate_content(\n contents=prompt.https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.prompts.Prompt.html#vertexai_preview_prompts_Prompt_assemble_contents(**variable_set)\n )\n responses.append(response)\n\n for response in responses:\n print(response.text, end=\"\")\n\n # Example response\n # Assembled prompt replacing: 1 instances of variable animal, 1 instances of variable activity\n # Eagles are primarily carnivorous. While they might *accidentally* ingest a berry......\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)."]]