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」。
使用 Vertex AI 最佳化文字產生提示
透過集合功能整理內容
你可以依據偏好儲存及分類內容。
這個範例示範如何使用 Vertex AI 提示最佳化工具,為文字生成模型最佳化提示。
深入探索
如需包含這個程式碼範例的詳細說明文件,請參閱下列內容:
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,["# Optimize prompts for text generation with Vertex AI\n\nThis sample demonstrates how to use the Vertex AI Prompt Optimizer to optimize prompts for a text generation model.\n\nExplore further\n---------------\n\n\nFor detailed documentation that includes this code sample, see the following:\n\n- [Optimize prompts](/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer)\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 from google.cloud import aiplatform\n\n # Initialize Vertex AI platform\n aiplatform.https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform.html(project=PROJECT_ID, location=\"us-central1\")\n\n # TODO(Developer): Check and update lines below\n # cloud_bucket = \"gs://cloud-samples-data\"\n # config_path = f\"{cloud_bucket}/instructions/sample_configuration.json\"\n # output_path = \"custom_job/output/\"\n\n custom_job = aiplatform.https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.types.CustomJob.html(\n display_name=\"Prompt Optimizer example\",\n worker_pool_specs=[\n {\n \"replica_count\": 1,\n \"container_spec\": {\n \"image_uri\": \"us-docker.pkg.dev/vertex-ai-restricted/builtin-algorithm/apd:preview_v1_0\",\n \"args\": [f\"--config={cloud_bucket}/{config_path}\"],\n },\n \"machine_spec\": {\n \"machine_type\": \"n1-standard-4\",\n },\n }\n ],\n staging_bucket=cloud_bucket,\n base_output_dir=f\"{cloud_bucket}/{output_path}\",\n )\n\n custom_job.submit()\n print(f\"Job resource name: {custom_job.resource_name}\")\n # Example response:\n # 'projects/123412341234/locations/us-central1/customJobs/12341234123412341234'\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)."]]