获取答案和后续跟进

本页介绍了 Vertex AI Search 的搜索功能，包括回答和后续跟进，并展示了如何使用方法调用为通用搜索应用实现此功能。

提供总结答案和后续问题的搜索基于答案方法。answer 方法取代了旧版 search 方法的摘要功能以及已废弃的 converse 方法的所有功能。回答方法还具有一些重要的附加功能，例如能够处理复杂的查询。

回答方法的特点

该回答方法的主要特点如下：

  • 能够生成复杂查询的答案。例如，回答方法可以将复合查询（例如以下查询）拆解为多个较小的查询，以返回更好的结果，从而提供更准确的回答：

    • “2024 年 Google Cloud 和 Google Ads 分别的收入是多少？”
    • “Google 成立多少年后收入达到 10 亿美元？”

  • 能够在多轮对话中通过在每轮对话中调用 answer 方法来组合搜索和回答生成。

  • 能够与搜索方法搭配使用，以缩短搜索延迟时间。您可以单独调用搜索方法和回答方法，并在不同时间在不同的 iframe 中呈现搜索结果和回答。这意味着，您可以在几毫秒内向用户显示搜索结果（10 个蓝色链接）。您无需等待系统生成回答，即可显示搜索结果。

回答和跟进功能可分为查询、搜索和回答三个阶段：

何时使用“回答”功能，何时使用“搜索”功能

Vertex AI Search 有两种用于查询应用的方法。它们具有不同的但重叠的功能。

在以下情况下，请使用 answer 方法：

  • 您希望 AI 生成搜索结果的答案（或摘要）。

  • 您希望实现多轮搜索，也就是说，搜索能够保留上下文，以便进行后续问题。

在以下情况下，请使用搜索方法：

  • 您只需要搜索结果，而不需要生成的回答。

  • 您希望返回的搜索结果（“蓝色链接”）超过 10 条。

  • 您有以下任一情况：

    • 媒体或医疗保健数据
    • 您自己的嵌入
    • 同义词控件或重定向控件
    • 分面
    • 用户的国家/地区代码

在以下情况下，请结合使用“回答”和“搜索”方法：

  • 您希望返回超过 10 条搜索结果，并且希望系统生成回答。

  • 您遇到了延迟问题，希望在系统返回生成的回答之前快速返回并显示搜索结果。

查询阶段功能

“回答和跟进”功能支持自然语言查询处理。

本部分介绍并展示了查询重述和分类的各种选项。

重述查询

查询重述功能默认处于开启状态。此功能会自动选择最佳方式来重写查询，以便改进搜索结果。此功能还可以处理不需要重述的询问。

  • 将复杂查询分解为多个查询，并执行同步子查询。

    例如：将一个复杂的查询拆分为四个更小、更简单的查询。

    用户输入 基于复杂查询创建的子查询
    Andie Ram 和 Arnaud Clément 有哪些共同的工作和爱好？
    • Andie Ram 的职业
    • Arnaud Clément 的职业
    • Andie Ram 的爱好
    • Arnaud Clément 的爱好

  • 合成多轮查询，使后续问题具有上下文感知能力和状态。

    例如：每次根据用户输入内容合成的查询可能如下所示：

    用户输入 合成的查询
    第 1 回：适合上学的笔记本电脑 适合学校使用的笔记本电脑
    第 2 步：不是 Mac 学校用笔记本电脑，不是 Mac
    第 3 个选项：大屏幕，我还需要无线键盘和鼠标 适用于学校的大屏笔记本电脑（不是 Mac），配有无线键盘和鼠标
    第 4 页：和一个背包 适用于学校的大屏笔记本电脑（不是 Mac），配有无线键盘和鼠标，以及一个背包

  • 简化长查询，以提高检索效率。

    例如：长查询会缩短为简单查询。

    用户输入 简化了查询
    我正在尝试找出我们网站上的“添加到购物车”按钮无法正常运行的原因。似乎当用户点击该按钮时，商品不会添加到购物车，并且他们会收到错误消息。我检查了代码，发现代码似乎没有问题，因此我不确定问题可能出在哪里。您能帮我排查这个问题吗？ 网站上的“添加到购物车”按钮无法正常使用。

  • 执行多步推理

    多步推理基于 ReAct（推理 + 行动）范式，该范式使 LLM 能够使用自然语言推理来解决复杂任务。默认情况下，步骤数量上限为 5。

    例如：

    用户输入 生成回答的两步
    Google 成立多少年后，收入达到了 10 亿美元？ 第 1 步：
    [思考]：我需要知道 Google 成立的时间，然后才能查询自那时起的收入。
    [行动] 搜索：Google 是什么时候成立的？[观察搜索结果]：“1998 年”

    Google
    [思考]：现在，我需要查询 Google 自 1998 年以来的年收入，并找出其首次超过 10 亿美元的时间。
    [操作] 搜索：1998 年以来的 Google 收入
    [观察搜索结果] 1998 年 Google 收入、1999 年 Google 收入……
    [答案]：Google 于 1998 年成立 [2]，在 5 年后的 2003 年收入就超过了 10 亿美元 [1]。

查询分类

查询分类选项用于识别对抗性查询和非查询答案查询。默认情况下，查询分类选项处于关闭状态。

如需详细了解对抗性询问和非回答询问，请参阅忽略对抗性询问和忽略非摘要询问。

搜索阶段功能

对于搜索，答案方法与搜索方法具有相同的选项。例如：

回答阶段功能

在回答阶段，系统会根据搜索结果生成回答，您可以启用与搜索方法相同的功能。例如：

  • 获取引用，以指明回答中每个句子的来源。如需了解详情，请参阅添加引文。

  • 使用提示前言可自定义回答的语气、风格和详细程度等。如需了解详情，请参阅指定自定义前言。

  • 选择要用于生成回答的 Vertex AI 模型。如需了解详情，请参阅回答生成模型版本和生命周期。

  • 选择是否忽略被归类为对抗性或非查询性质的询问。

    如需详细了解对抗性询问和非回答询问，请参阅忽略对抗性询问和忽略非摘要询问。非答案查询也称为非摘要查询。

搜索方法中不提供的其他回答阶段功能包括：

  • 为每个断言（生成的回答中的句子）获取支持得分。 支持得分是一个介于 [0,1] 范围内的浮点值，表示声明在数据存储区中的数据中有多可靠。如需了解详情，请参阅返回接地支持得分。

  • 获取答案的汇总支持得分。支持得分表示回答与数据存储区中的数据的相关程度。如需了解详情，请参阅返回接地支持得分。

  • 仅返回有依据的回答。您可以选择仅返回满足特定支持得分阈值的回答。如需了解详情，请参阅仅显示有依据的回答。

准备工作

根据您应用的类型，满足以下要求：

  • 如果您有结构化或非结构化搜索应用，请确保已启用以下功能：高级 LLM 功能

  • 如果您有网站搜索应用，请确保已开启以下功能：

  • 如果您有混合搜索应用（即与多个数据存储区关联的应用），请与您的 Google 客户支持团队联系，请求将您的应用添加到支持混合搜索的 Answer API 的许可名单中。

搜索和回答（基本）

以下命令展示了如何调用 answer 方法，并返回生成的答案和搜索结果列表（包含指向来源的链接）。

此命令仅显示必需的输入。将选项保留为默认值。

REST

如需进行搜索并获取包含生成的回答的结果，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"}
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。例如，“比较 BigQuery 和 Spanner 数据库？”。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

查询阶段命令

本部分介绍了如何为 answer 方法调用的查询阶段指定选项。

搜索和回答（已停用重述功能）

以下命令展示了如何调用 answer 方法并返回生成的答案和搜索结果列表。由于重述选项已停用，因此回答可能会与上一个回答不同。

REST

如需搜索并获取包含生成答案的结果，而不应用查询重述功能，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "queryUnderstandingSpec": {
           "queryRephraserSpec": {
              "disable": true
        }
    }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。例如，“比较 BigQuery 和 Spanner 数据库？”。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

搜索和回答（指定步骤数上限）

以下命令展示了如何调用 answer 方法并返回生成的答案和搜索结果列表。由于重述步骤的数量增加，因此答案与之前的答案不同。

REST

如需搜索并获取包含生成的答案的结果（最多允许 5 次重述步骤），请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "queryUnderstandingSpec": {
            "queryRephraserSpec": {
                "maxRephraseSteps": MAX_REPHRASE
             }
         }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。例如，“比较 BigQuery 和 Spanner 数据库？”。
    • MAX_REPHRASE：重述步骤的数量上限。允许的最大值为 5。如果未设置或设置的值小于 1，则值为默认值 1。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

使用查询分类进行搜索和回答

以下命令展示了如何调用 answer 方法来询问询问是敌对性询问、非答案询问，还是两者都不是。

响应包含查询的分类类型，但答案本身不会受到分类的影响。如果您想根据询问类型更改回答行为，可以在回答阶段执行此操作。请参阅忽略对抗性询问和忽略非摘要查询。

REST

如需确定询问是恶意询问还是非答案询问，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "queryUnderstandingSpec": {
            "queryClassificationSpec": {
                "types": ["QUERY_CLASSIFICATION_TYPE"]
             }
         }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。例如“hello”。
    • QUERY_CLASSIFICATION_TYPE：您要识别的查询类型：ADVERSARIAL_QUERY 和/或 NON_ANSWER_SEEKING_QUERY。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

搜索阶段命令：使用搜索结果选项进行搜索和回答

本部分介绍了如何为 answer 方法调用的搜索阶段部分指定选项，例如设置返回的文档数量上限、提升和过滤等选项，以及如何在您提供自己的搜索结果时获取回答。

以下命令展示了如何调用 answer 方法，以及如何指定返回搜索结果的方式的各种选项。（搜索结果与答案无关。）

REST

如需设置与搜索结果的返回内容和方式相关的各种选项，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
          "searchSpec": {
          "searchParams": {
            "maxReturnResults": MAX_RETURN_RESULTS,
            "filter": "FILTER",
            "boostSpec": BOOST_SPEC,
            "orderBy": "ORDER_BY",
            "searchResultMode": SEARCH_RESULT_MODE
           }
         }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。例如，“比较 BigQuery 和 Spanner 数据库？”
    • MAX_RETURN_RESULTS：要返回的搜索结果数。默认值为 10。
    • FILTER：过滤条件用于指定要查询的文档。如果文档的元数据符合过滤条件规范，则系统会对该文档进行查询。如需了解详情（包括过滤条件语法），请参阅过滤结构化或非结构化数据的通用搜索。
    • BOOST_SPEC：借助提升规范，您可以在搜索结果中提升某些文档的排名，这可能会影响回答。如需了解详情（包括提升幅度规范的语法），请参阅提升搜索结果的排名。
    • ORDER_BY：文档的返回顺序。文档可以按 Document 对象中的字段进行排序。orderBy 表达式区分大小写。 如果无法识别此字段，则返回 INVALID_ARGUMENT。
    • SEARCH_RESULT_MODE：用于指定搜索结果模式：DOCUMENTS 或 CHUNKS。如需了解详情，请参阅解析和分块文档以及 ContentSearchSpec。 此字段仅在 v1alpha 版的 API 中可用。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

回答阶段命令

本部分介绍了如何为 answer 方法调用指定特定于答案的选项。

忽略对抗性查询和非查询答案的查询

以下命令展示了如何在调用 answer 方法时避免回答对抗性询问和非查询询问。

REST

如需跳过回答对抗性或非查询性质的询问，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "answerGenerationSpec": {
           "ignoreAdversarialQuery": true,
           "ignoreNonAnswerSeekingQuery": true
        }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

仅显示相关回答

Vertex AI Search 可以评估搜索结果与查询的相关性。如果没有结果被判定为足够相关，那么您可以选择返回回退回答“We do not have a summary for your query.”，而不是根据不相关或相关性较低的结果生成回答

以下命令展示了如何在调用 answer 方法时返回不相关的结果时的回退回答。

REST

如需在未找到任何相关结果时返回后备答案，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "answerGenerationSpec": {
           "ignoreLowRelevantContent": true
        }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

返回基准支持分数

以下命令展示了如何返回回答和声明的依据支持得分。

如需了解 Vertex AI 中的依据的一般信息，请参阅使用 RAG 检查依据。回答方法会调用 groundingConfigs.check 方法。

REST

如需返回每个断言（答案中的句子）的支持得分以及答案的汇总支持得分，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "groundingSpec": {
           "includeGroundingSupports": true,
        }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。

仅显示有依据的回答

以下命令展示了如何仅返回被认为在语料库（数据存储区中的信息）中扎实可靠的答案。系统会滤除缺乏依据的回答。

您可以为接地支持分数选择低或高级别阈值。然后，只有当回答达到或超过该水平时，系统才会返回该回答。您可以使用这两个过滤阈值和不使用任何阈值进行实验，以确定哪种过滤级别最有可能为用户提供最佳结果。

如需了解 Vertex AI 中的依据的一般信息，请参阅使用 RAG 检查依据。回答方法会调用 groundingConfigs.check 方法。

REST

如需仅在答案达到支持得分阈值时返回该答案，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "groundingSpec": {
           "filteringLevel": "FILTER_LEVEL"
        }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。
    • FILTER_LEVEL：用于根据基准支持得分过滤回答的枚举。选项包括：FILTERING_LEVEL_LOW 和 FILTERING_LEVEL_HIGH。如果未包含 filteringLevel，则不会对答案应用支持得分过滤器。

指定回答模型

以下命令展示了如何更改用于生成回答的模型版本。

如需了解支持的模型，请参阅回答生成模型版本和生命周期。

REST

如需使用与默认模型不同的模型生成回答，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "answerGenerationSpec": {
           "modelSpec": {
              "modelVersion": "MODEL_VERSION",
           }
         }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。
    • MODEL_VERSION：您要用于生成回答的模型版本。如需了解详情，请参阅回答生成模型版本和生命周期。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

指定自定义前导码

以下命令展示了如何为生成的回答设置序言。前言包含用于自定义回答的自然语言说明。您可以请求自定义设置，例如长度、详细程度、输出风格（例如“简单”）、输出语言、答案重点和格式（例如表格、项目符号和 XML）。例如，前言可以是“用 10 岁孩子的语言进行说明”。

序言可能会对生成的回答的质量产生重大影响。如需了解应在前言中写入的内容以及优秀前言的示例，请参阅自定义前言简介。

REST

如需使用与默认模型不同的模型生成回答，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "answerGenerationSpec": {
           "promptSpec": {
               "preamble": "PREAMBLE",
           }
        }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。
    • PREAMBLE：用于自定义回答的自然语言说明。例如，请尝试使用 show the answer format in an ordered list 或 give a very detailed answer。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

添加引用

以下命令展示了如何请求在回答中添加引文。

REST

如需使用与默认模型不同的模型生成回答，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "answerGenerationSpec": {
           "includeCitations": INCLUDE_CITATIONS
        }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。
    • INCLUDE_CITATIONS：指定是否要在回答中添加引文元数据。默认值为 false。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

设置答案语言代码

以下命令展示了如何为回答设置语言代码。

REST

如需使用与默认模型不同的模型生成回答，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "answerGenerationSpec": {
           "answerLanguageCode": "ANSWER_LANGUAGE_CODE"
           }
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：您要查询的 Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。
    • ANSWER_LANGUAGE_CODE：答案的语言代码。请使用 BCP47：用于标识语言的标记中定义的语言标记。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# engine_id = "YOUR_APP_ID"


def answer_query_sample(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.AnswerQueryResponse:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.ConversationalSearchServiceClient(
        client_options=client_options
    )

    # The full resource name of the Search serving config
    serving_config = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/servingConfigs/default_serving_config"

    # Optional: Options for query phase
    # The `query_understanding_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/QueryUnderstandingSpec
    query_understanding_spec = discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec(
        query_rephraser_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec(
            disable=False,  # Optional: Disable query rephraser
            max_rephrase_steps=1,  # Optional: Number of rephrase steps
        ),
        # Optional: Classify query types
        query_classification_spec=discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec(
            types=[
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.ADVERSARIAL_QUERY,
                discoveryengine.AnswerQueryRequest.QueryUnderstandingSpec.QueryClassificationSpec.Type.NON_ANSWER_SEEKING_QUERY,
            ]  # Options: ADVERSARIAL_QUERY, NON_ANSWER_SEEKING_QUERY or both
        ),
    )

    # Optional: Options for answer phase
    # The `answer_generation_spec` below includes all available query phase options.
    # For more details, refer to https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1/AnswerGenerationSpec
    answer_generation_spec = discoveryengine.AnswerQueryRequest.AnswerGenerationSpec(
        ignore_adversarial_query=False,  # Optional: Ignore adversarial query
        ignore_non_answer_seeking_query=False,  # Optional: Ignore non-answer seeking query
        ignore_low_relevant_content=False,  # Optional: Return fallback answer when content is not relevant
        model_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.ModelSpec(
            model_version="gemini-1.5-flash-001/answer_gen/v2",  # Optional: Model to use for answer generation
        ),
        prompt_spec=discoveryengine.AnswerQueryRequest.AnswerGenerationSpec.PromptSpec(
            preamble="Give a detailed answer.",  # Optional: Natural language instructions for customizing the answer.
        ),
        include_citations=True,  # Optional: Include citations in the response
        answer_language_code="en",  # Optional: Language code of the answer
    )

    # Initialize request argument(s)
    request = discoveryengine.AnswerQueryRequest(
        serving_config=serving_config,
        query=discoveryengine.Query(text="What is Vertex AI Search?"),
        session=None,  # Optional: include previous session ID to continue a conversation
        query_understanding_spec=query_understanding_spec,
        answer_generation_spec=answer_generation_spec,
    )

    # Make the request
    response = client.answer_query(request)

    # Handle the response
    print(response)

    return response

用于提问的命令

跟进问题是多轮询问。在后续会话中的首次询问之后，系统会在后续的“回合”中考虑之前的互动。借助跟进问题，回答方法还可以建议相关问题，供用户选择，而无需输入自己的跟进问题。

您可以将前面部分中介绍的所有回答和跟进功能（例如引文、过滤器、安全搜索、忽略某些类型的询问，以及使用前言自定义回答）与跟进问题一起使用。

后续会话示例

以下是包含跟进信息的会话示例。假设您想了解墨西哥的度假信息：

  • 第 1 步：

    • 您：一年中什么时候去墨西哥度假最合适？

    • 回答并进行跟进：在墨西哥度假的最佳时间是从 11 月到 4 月的旱季。

  • 第 2 步：

    • 您：汇率是多少？

    • 回答并进行跟进：1 美元约等于 17.65 墨西哥比索。

  • 第 3 个回合：

    • 您：12 月的平均温度是多少？

    • 回答并进行跟进：平均温度在 70-78°F 之间。 坎昆的平均温度约为 77°F。

如果不进行跟进，系统就无法回答“汇率是多少？”这一问题，因为常规搜索无法知道您想要的是墨西哥汇率。同样，如果没有跟进，我们就无法获得提供墨西哥具体温度所需的背景信息。

当您询问“去墨西哥度假的最佳季节是什么？”时，除了回答您的问题外，回答和跟进问题还可以建议您可能要问的其他问题，例如“去墨西哥度假最便宜的月份是什么？”和“墨西哥的旅游旺季是什么月份？”

启用相关问题功能后，系统会在 ConverseConversationResponse 中以字符串的形式返回问题。

关于会话

如需了解跟进在 Vertex AI Search 中的运作方式，您需要了解会话。

会话由用户提供的文本查询和 Vertex AI Search 提供的回答组成。

这些询问和回答对有时也称为“回合”。在上例中，第二轮对话由“汇率是多少？”和“1 美元大约相当于 17.65 墨西哥比索”组成。

会话会与应用一起存储。在应用中，会话由会话资源表示。

除了包含查询和响应消息之外，会话资源还包含：

  • 唯一名称（会话 ID）。

  • 状态（进行中或已完成）。

  • 用户伪 ID，即用于跟踪用户的访问者 ID。可以通过编程方式进行分配。

  • 开始时间和结束时间。

  • 回合，即询问-回答对。

存储会话信息并获取响应

您可以使用命令行生成搜索回答和解答，并将这些内容以及会话中的每个查询存储起来。

REST

如需使用命令行创建会话并根据用户的输入生成回答，请按以下步骤操作：

  1. 指定要存储会话的应用：

    curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/sessions" \
  -d '{
        "userPseudoId": "USER_PSEUDO_ID"
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。

    • APP_ID：Vertex AI Search 应用的 ID。

    • USER_PSEUDO_ID：这是用于跟踪搜索访问者的唯一标识符。例如，您可以使用 HTTP Cookie 来实现此功能，HTTP Cookie 可唯一标识单个设备上的访问者。

    命令和结果示例

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)"
-H "Content-Type: application/json"
"https://discoveryengine.googleapis.com/v1/projects/my-project-123/locations/global/collections/default_collection/engines/my-app/sessions"
-d '{
"userPseudoId": "test_user"
}'

    
{
  "name": "projects/123456/locations/global/collections/default_collection/engines/my-app/sessions/16002628354770206943",
  "state": "IN_PROGRESS",
  "userPseudoId": "test_user",
  "startTime": "2024-09-13T18:47:10.465311Z",
  "endTime": "2024-09-13T18:47:10.465311Z"
}

  2. 记下 JSON 响应中 name: 字段末尾的数字，即会话 ID。在示例结果中，ID 为 5386462384953257772。下一步中需要用到此 ID。

  3. 生成回答并将其添加到应用中的会话：

    curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "session": "projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/sessions/SESSION_ID",
          "searchSpec":{ "searchParams": {"filter": "FILTER"} }
}'
    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：Vertex AI Search 应用的 ID。
    • QUERY：包含问题或搜索查询的自由文本字符串。
    • SESSION_ID：您在第 1 步中创建的会话的 ID。这是 name: 字段末尾的数字，请参阅第 2 步。对于会话，请在每轮对话中使用相同的会话 ID。
    • FILTER：用于使用过滤条件表达式过滤搜索结果的文本字段。默认值为空字符串。过滤条件的构建方式因您拥有的非结构化数据是否包含元数据、结构化数据或网站数据而异。如需了解详情，请参阅过滤结构化或非结构化数据的通用搜索和过滤网站搜索。

    命令和结果示例

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)"
-H "Content-Type: application/json"
"https://discoveryengine.googleapis.com/v1/projects/my-project-123/locations/global/collections/default_collection/engines/my-app/servingConfigs/default_search:answer"
-d '{
"query": { "text": "Compare bigquery with spanner database?"},
"session":  "projects/123456/locations/global/collections/default_collection/engines/my-app/sessions/16002628354770206943",
}'
    
    
{
  "answer": {
    "name": "projects/123456/locations/global/collections/default_collection/engines/my-app/sessions/16002628354770206943/answers/4861507376861383072",
    "state": "SUCCEEDED",
    "answerText": "BigQuery and Spanner are both powerful tools that can be used together to handle transactional and analytical workloads. Spanner is a fully managed relational database optimized for transactional workloads, while BigQuery is a serverless data warehouse designed for business agility. Spanner provides seamless replication across regions in Google Cloud and processes over 1 billion requests per second at peak. BigQuery analyzes over 110 terabytes of data per second. Users can leverage federated queries to read data from Spanner and write to a native BigQuery table. \n",
    "steps": [
      {
        "state": "SUCCEEDED",
        "description": "Rephrase the query and search.",
        "actions": [
          {
            "searchAction": {
              "query": "Compare bigquery with spanner database?"
            },
            "observation": {
              "searchResults": [
                {
                  "document": "projects/123456/locations/global/collections/default_collection/dataStores/my-data-store/branches/0/documents/ecc0e7547253f4ca3ff3328ce89995af",
                  "uri": "https://cloud.google.com/blog/topics/developers-practitioners/how-spanner-and-bigquery-work-together-handle-transactional-and-analytical-workloads",
                  "title": "How Spanner and BigQuery work together to handle transactional and analytical workloads | Google Cloud Blog",
                  "snippetInfo": [
                    {
                      "snippet": "Using Cloud \u003cb\u003eSpanner\u003c/b\u003e and \u003cb\u003eBigQuery\u003c/b\u003e also allows customers to build their \u003cb\u003edata\u003c/b\u003e clouds using Google Cloud, a unified, open approach to \u003cb\u003edata\u003c/b\u003e-driven transformation ...",
                      "snippetStatus": "SUCCESS"
                    }
                  ]
                },
                {
                  "document": "projects/123456/locations/global/collections/default_collection/dataStores/my-data-store/branches/0/documents/d7e238f73608a860e00b752ef80e2941",
                  "uri": "https://cloud.google.com/blog/products/databases/cloud-spanner-gets-stronger-with-bigquery-federated-queries",
                  "title": "Cloud Spanner gets stronger with BigQuery-federated queries | Google Cloud Blog",
                  "snippetInfo": [
                    {
                      "snippet": "As enterprises compete for market share, their need for real-time insights has given rise to increased demand for transactional \u003cb\u003edatabases\u003c/b\u003e to support \u003cb\u003edata\u003c/b\u003e ...",
                      "snippetStatus": "SUCCESS"
                    }
                  ]
                },
                {
                  "document": "projects/123456/locations/global/collections/default_collection/dataStores/my-data-store/branches/0/documents/e10a5a3c267dc61579e7c00fefe656eb",
                  "uri": "https://cloud.google.com/blog/topics/developers-practitioners/replicating-cloud-spanner-bigquery-scale",
                  "title": "Replicating from Cloud Spanner to BigQuery at scale | Google Cloud Blog",
                  "snippetInfo": [
                    {
                      "snippet": "... \u003cb\u003eSpanner data\u003c/b\u003e into \u003cb\u003eBigQuery\u003c/b\u003e for analytics. In this post, you will learn how to efficiently use this feature to replicate large tables with high throughput ...",
                      "snippetStatus": "SUCCESS"
                    }
                  ]
                },
                ...
                {
                  "document": "projects/123456/locations/global/collections/default_collection/dataStores/my-data-store/branches/0/documents/8100ad36e1cac149eb9fc180a41d8f25",
                  "uri": "https://cloud.google.com/blog/products/gcp/from-nosql-to-new-sql-how-spanner-became-a-global-mission-critical-database",
                  "title": "How Spanner became a global, mission-critical database | Google Cloud Blog",
                  "snippetInfo": [
                    {
                      "snippet": "... SQL \u003cb\u003evs\u003c/b\u003e. NoSQL dichotomy may no longer be relevant." The \u003cb\u003eSpanner\u003c/b\u003e SQL query processor, while recognizable as a standard implementation, has unique ...",
                      "snippetStatus": "SUCCESS"
                    }
                  ]
                }
              ]
            }
          }
        ]
      }
    ]
  },
  "session": {
    "name": "projects/123456/locations/global/collections/default_collection/engines/my-app/sessions/16002628354770206943",
    "state": "IN_PROGRESS",
    "userPseudoId": "test_user",
    "turns": [
      {
        "query": {
          "queryId": "projects/123456/locations/global/questions/741830",
          "text": "Compare bigquery with spanner database?"
        },
        "answer": "projects/123456/locations/global/collections/default_collection/engines/my-app/sessions/16002628354770206943/answers/4861507376861383072"
      }
    ],
    "startTime": "2024-09-13T18:47:10.465311Z",
    "endTime": "2024-09-13T18:47:10.465311Z"
  },
  "answerQueryToken": "NMwKDAjFkpK3BhDU24uZAhIkNjZlNDIyZWYtMDAwMC0yMjVmLWIxMmQtZjQwMzA0M2FkYmNj"
}

  4. 针对会话中的每个新查询重复第 3 步。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.cloud import discoveryengine_v1 as discoveryengine


def create_session(
    project_id: str,
    location: str,
    engine_id: str,
    user_pseudo_id: str,
) -> discoveryengine.Session:
    """Creates a session.

    Args:
        project_id: The ID of your Google Cloud project.
        location: The location of the app.
        engine_id: The ID of the app.
        user_pseudo_id: A unique identifier for tracking visitors. For example, this
          could be implemented with an HTTP cookie, which should be able to
          uniquely identify a visitor on a single device.
    Returns:
        discoveryengine.Session: The newly created Session.
    """

    client = discoveryengine.ConversationalSearchServiceClient()

    session = client.create_session(
        # The full resource name of the engine
        parent=f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}",
        session=discoveryengine.Session(user_pseudo_id=user_pseudo_id),
    )

    # Send Session name in `answer_query()`
    print(f"Session: {session.name}")
    return session

从数据存储区获取会话

以下命令展示了如何调用 get 方法并从数据存储区获取会话。

REST

如需从数据存储区获取会话，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/sessions/SESSION_ID"

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：Vertex AI Search 应用的 ID。
    • SESSION_ID：您要获取的会话的 ID。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.cloud import discoveryengine_v1 as discoveryengine


def get_session(
    project_id: str,
    location: str,
    engine_id: str,
    session_id: str,
) -> discoveryengine.Session:
    """Retrieves a session.

    Args:
        project_id: The ID of your Google Cloud project.
        location: The location of the app.
        engine_id: The ID of the app.
        session_id: The ID of the session.
    """

    client = discoveryengine.ConversationalSearchServiceClient()

    # The full resource name of the session
    name = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/sessions/{session_id}"

    session = client.get_session(name=name)

    print(f"Session details: {session}")
    return session

从应用中删除会话

以下命令展示了如何调用 delete 方法并从数据存储区中删除会话。

默认情况下，系统会自动删除超过 60 天的会话。不过，如果您想删除特定会话（例如，如果它包含敏感内容），请使用此 API 调用进行删除。

REST

如需从应用中删除会话，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X DELETE -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/sessions/SESSION_ID"

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：Vertex AI Search 应用的 ID。
    • SESSION_ID：您要删除的会话的 ID。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.cloud import discoveryengine_v1 as discoveryengine


def delete_session(
    project_id: str,
    location: str,
    engine_id: str,
    session_id: str,
) -> None:
    """Deletes a session.

    Args:
        project_id: The ID of your Google Cloud project.
        location: The location of the app.
        engine_id: The ID of the app.
        session_id: The ID of the session.
    """

    client = discoveryengine.ConversationalSearchServiceClient()

    # The full resource name of the session
    name = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/sessions/{session_id}"

    client.delete_session(name=name)

    print(f"Session {name} deleted.")

更新会话

您可能因下列多种原因而需要更新会话。例如，执行以下任一操作：

  • 将会话标记为已完成
  • 将一个会话中的邮件合并到另一个会话中
  • 更改用户的伪 ID

以下命令展示了如何调用 patch 方法并更新数据存储区中的会话。

REST

如需通过应用更新会话，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X PATCH \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/sessions/SESSION_ID?updateMask=state" \
  -d '{
        "state": "NEW_STATE"
      }'

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：Vertex AI Search 应用的 ID。
    • SESSION_ID：您要更新的会话的 ID。
    • NEW_STATE：状态的新值，例如 IN_PROGRESS。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.cloud import discoveryengine_v1 as discoveryengine
from google.protobuf import field_mask_pb2


def update_session(
    project_id: str,
    location: str,
    engine_id: str,
    session_id: str,
) -> discoveryengine.Session:
    """Updates a session.

    Args:
        project_id: The ID of your Google Cloud project.
        location: The location of the app.
        engine_id: The ID of the app.
        session_id: The ID of the session.
    Returns:
        discoveryengine.Session: The updated Session.
    """
    client = discoveryengine.ConversationalSearchServiceClient()

    # The full resource name of the session
    name = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}/sessions/{session_id}"

    session = discoveryengine.Session(
        name=name,
        state=discoveryengine.Session.State.IN_PROGRESS,  # Options: IN_PROGRESS, STATE_UNSPECIFIED
    )

    # Fields to Update
    update_mask = field_mask_pb2.FieldMask(paths=["state"])

    session = client.update_session(session=session, update_mask=update_mask)
    print(f"Updated session: {session.name}")
    return session

列出所有会话

以下命令展示了如何调用 list 方法并列出数据存储区中的会话。

REST

如需列出应用的会话，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X GET \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/sessions"

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：Vertex AI Search 应用的 ID。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.cloud import discoveryengine_v1 as discoveryengine


def list_sessions(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.ListSessionsResponse:
    """Lists all sessions associated with a data store.

    Args:
        project_id: The ID of your Google Cloud project.
        location: The location of the app.
        engine_id: The ID of the app.
    Returns:
        discoveryengine.ListSessionsResponse: The list of sessions.
    """

    client = discoveryengine.ConversationalSearchServiceClient()

    # The full resource name of the engine
    parent = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}"

    response = client.list_sessions(
        request=discoveryengine.ListSessionsRequest(
            parent=parent,
            filter='state="IN_PROGRESS"',  # Optional: Filter requests by userPseudoId or state
            order_by="update_time",  # Optional: Sort results
        )
    )

    print("Sessions:")
    for session in response.sessions:
        print(session)

    return response

列出用户的会话

以下命令展示了如何调用 list 方法来列出与用户或访问者关联的会话。

REST

如需列出与用户或访问者关联的会话，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X GET \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/sessions?filter=userPseudoId=USER_PSEUDO_ID"

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：Vertex AI Search 应用的 ID。
    • USER_PSEUDO_ID：您要列出其会话的用户的伪 ID。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.cloud import discoveryengine_v1 as discoveryengine


def list_sessions(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.ListSessionsResponse:
    """Lists all sessions associated with a data store.

    Args:
        project_id: The ID of your Google Cloud project.
        location: The location of the app.
        engine_id: The ID of the app.
    Returns:
        discoveryengine.ListSessionsResponse: The list of sessions.
    """

    client = discoveryengine.ConversationalSearchServiceClient()

    # The full resource name of the engine
    parent = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}"

    response = client.list_sessions(
        request=discoveryengine.ListSessionsRequest(
            parent=parent,
            filter='state="IN_PROGRESS"',  # Optional: Filter requests by userPseudoId or state
            order_by="update_time",  # Optional: Sort results
        )
    )

    print("Sessions:")
    for session in response.sessions:
        print(session)

    return response

列出用户和状态的会话

以下命令展示了如何调用 list 方法，以列出特定用户处于给定状态的会话。

REST

如需列出与给定用户或访问者关联的处于打开或关闭状态的用户会话，请执行以下操作：

  1. 运行以下 curl 命令：

    curl -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/sessions?filter=userPseudoId=USER_PSEUDO_ID%20AND%20state=STATE"

    替换以下内容：

    • PROJECT_ID：您的 Google Cloud 项目的 ID。
    • APP_ID：Vertex AI Search 应用的 ID。
    • USER_PSEUDO_ID：您要列出其会话的用户的伪 ID。
    • STATE：会话状态：STATE_UNSPECIFIED（已关闭或未知）或 IN_PROGRESS（未结）。

Python

如需了解详情，请参阅 Vertex AI Agent Builder Python API 参考文档。

如需向 Vertex AI Agent Builder 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 google.cloud import discoveryengine_v1 as discoveryengine


def list_sessions(
    project_id: str,
    location: str,
    engine_id: str,
) -> discoveryengine.ListSessionsResponse:
    """Lists all sessions associated with a data store.

    Args:
        project_id: The ID of your Google Cloud project.
        location: The location of the app.
        engine_id: The ID of the app.
    Returns:
        discoveryengine.ListSessionsResponse: The list of sessions.
    """

    client = discoveryengine.ConversationalSearchServiceClient()

    # The full resource name of the engine
    parent = f"projects/{project_id}/locations/{location}/collections/default_collection/engines/{engine_id}"

    response = client.list_sessions(
        request=discoveryengine.ListSessionsRequest(
            parent=parent,
            filter='state="IN_PROGRESS"',  # Optional: Filter requests by userPseudoId or state
            order_by="update_time",  # Optional: Sort results
        )
    )

    print("Sessions:")
    for session in response.sessions:
        print(session)

    return response