使用 Gemini 1.0 Pro 模型生成关联标准答案的文本

使用 Gemini 1.0 Pro 模型生成文本,该模型关联来自 Vertex AI Search 数据存储区或 Google Search 的标准答案。

深入探索

如需查看包含此代码示例的详细文档,请参阅以下内容:

代码示例

Python

在尝试此示例之前,请按照《Vertex AI 快速入门:使用客户端库》中的 Python 设置说明执行操作。如需了解详情,请参阅 Vertex AI Python API 参考文档

如需向 Vertex AI 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

from typing import Optional

import vertexai
from vertexai.preview.generative_models import (
    GenerationResponse,
    GenerativeModel,
    grounding,
    Tool,
)

def generate_text_with_grounding(
    project_id: str, location: str, data_store_path: Optional[str] = None
) -> GenerationResponse:
    # Initialize Vertex AI
    vertexai.init(project=project_id, location=location)

    # Load the model
    model = GenerativeModel(model_name="gemini-1.0-pro")

    # Create Tool for grounding
    if data_store_path:
        # Use Vertex AI Search data store
        # Format: projects/{project_id}/locations/{location}/collections/default_collection/dataStores/{data_store_id}
        tool = Tool.from_retrieval(
            grounding.Retrieval(grounding.VertexAISearch(datastore=data_store_path))
        )
    else:
        # Use Google Search for grounding (Private Preview)
        tool = Tool.from_google_search_retrieval(grounding.GoogleSearchRetrieval())

    prompt = "What are the price, available colors, and storage size options of a Pixel Tablet?"
    response = model.generate_content(prompt, tools=[tool])

    print(response)

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例,请参阅 Google Cloud 示例浏览器