取得解答和後續追蹤

本頁面將介紹 Vertex AI Search 的搜尋與回答和後續追蹤功能，並說明如何使用方法呼叫，為自訂搜尋應用程式實作這項功能。

「搜尋答案並追問」功能採用回答方法。answer 方法會取代舊版 search 方法的摘要功能，以及已淘汰 converse 方法的所有功能。此外，回答方法還提供一些重要的額外功能，例如處理複雜查詢的能力。

回答方法的特色

回答方法的主要功能如下：

  • 能夠生成複雜查詢的答案。舉例來說，回答方法可以將複合查詢 (如下所示) 分解為多個較小的查詢，以傳回更準確的結果，進而提供更優質的答案：

    • 「2024 年 Google Cloud 和 Google Ads 的營收分別是多少？」
    • 「Google 成立幾年後，營收達到 10 億美元？」

  • 在多輪對話中，每次呼叫回答方法時，都能結合搜尋和答案生成功能。

  • 可與搜尋方法配對，以減少搜尋延遲。您可以分別呼叫搜尋方法和答案方法，並在不同時間點，於不同的 iframe 中算繪搜尋結果和答案。也就是說，您可以在幾毫秒內向使用者顯示搜尋結果 (10 個藍色連結)。您不必等待系統生成答案，即可顯示搜尋結果。

回答和後續追問功能可分為查詢、搜尋和回答這三個階段：

何時使用「回答」，何時使用「搜尋」

Vertex AI Search 提供兩種查詢應用程式的方法。兩者功能不同，但有部分重疊。

在下列情況下，請使用 answer 方法：

  • 您希望 AI 生成搜尋結果的答案 (或摘要)。

  • 您想要多輪搜尋，也就是搜尋時保留脈絡，以便提出後續問題。

在下列情況下使用 search 方法：

  • 您只需要搜尋結果，不需要生成的答案。

  • 您具備下列任一條件：

    • 媒體或醫療照護資料
    • 您自己的嵌入
    • 同義詞或重新導向控制項
    • facet
    • 使用者國家/地區代碼

  • 您需要瀏覽一般資料儲存庫中的資料。

在下列情況下，請同時使用回答和搜尋方法：

  • 您想傳回超過十筆搜尋結果，且想取得生成的答案。

  • 您有延遲問題，且希望在系統傳回生成的答案前，先傳回並顯示搜尋結果。

查詢階段功能

「回答和後續問題」功能支援自然語言查詢處理。

本節將說明並展示查詢重述和分類的各種選項。

重新措辭查詢

查詢重述功能預設為開啟。這項功能會自動選擇最佳方式重新措辭查詢，以改善搜尋結果。這項功能也能處理不需要重新措辭的查詢。

  • 將複雜查詢拆分為多項查詢，並執行同步子查詢。

    例如：將複雜的查詢拆解成四個較小且簡單的查詢。

    使用者輸入內容 從複雜查詢建立的子查詢
    Andie Ram 和 Arnaud Clément 有哪些共同的工作和嗜好？
    • Andie Ram 職業
    • Arnaud Clément 職業
    • Andie Ram hobby
    • Arnaud Clément 的嗜好

  • 綜合多輪查詢，讓後續問題瞭解背景資訊和狀態。

    舉例來說，在每個回合中，從使用者輸入內容合成的查詢可能如下所示：

    使用者輸入內容 查詢合成
    第 1 季：學校適用的筆記型電腦 學校適用的筆記型電腦
    第 2 輪：不是 Mac 非 Mac 的學校用筆電
    第 3 輪：更大的螢幕，我也需要無線鍵盤和滑鼠 學校適用的筆電 (螢幕較大)，非 Mac，搭配無線鍵盤和滑鼠
    第 4 輪：和一個背包 學校用的筆電，螢幕要大一點，不要 Mac，要有無線鍵盤和滑鼠，還要能裝進背包

  • 簡化長查詢內容，提升檢索效果 (需要進階 LLM 功能)。

    例如：將長查詢縮短為一般查詢。

    使用者輸入內容 簡化查詢
    我們網站上的「加入購物車」按鈕無法正常運作，我想找出原因。使用者點選按鈕時，商品似乎不會加入購物車，且會收到錯誤訊息。我檢查了程式碼，看起來正確無誤，因此不確定問題出在哪裡。可以幫我排解這個問題嗎？ 網站上的「加入購物車」按鈕無法運作。

  • 執行多步驟推論

    多步驟推論是以 ReAct (推論 + 行動) 範例為基礎，可讓大型語言模型使用自然語言推論解決複雜工作。預設步驟上限為五個。

    例如：

    使用者輸入內容 生成答案的兩個步驟
    Google 成立幾年後，營收達到 10 億美元？ 步驟 1：
    [想法]：我需要知道 Google 的成立時間，才能查詢自那時起的收益。
    [Act] Search: Google 何時成立？[Observe Search Results]：「1998 年」

    步驟 2：
    [Thought]：現在我需要搜尋 Google 自 1998 年以來的年營收，並找出首次超過 10 億美元的時間。
    [Act] Search: Google revenue since 1998
    [Observe Search Results] Google revenue in 1998, Google revenue in 1999…..
    [答案]：Google 於 1998 年成立 [2]，並在 2003 年達到超過 10 億美元的營收 [1]，

    多步驟推論需要進階 LLM 功能。

查詢分類

查詢分類選項用於識別惡意查詢和非尋求答案的查詢。根據預設，查詢分類選項會關閉。

如要進一步瞭解惡意和非尋求答案的查詢，請參閱「忽略惡意查詢」和「忽略非尋求摘要的查詢」。

搜尋階段功能

搜尋時，回答方法與搜尋方法有相同的選項。例如：

答案階段功能

在回答階段，系統會根據搜尋結果生成答案，這時您可以啟用與搜尋方法相同的特徵。例如：

搜尋方法不支援的其他答案階段功能包括：

  • 取得每項主張 (生成答案中的句子) 的支援分數。 支援分數是介於 [0,1] 之間的浮點值，表示聲明在資料存放區資料中的根據程度。詳情請參閱「傳回基礎支援分數」。

  • 取得答案的匯總支援分數。支援分數代表答案與資料儲存庫中資料的關聯程度。詳情請參閱「傳回基礎支援分數」。

  • 只傳回有根據的答案。您可以選擇只傳回符合特定支援分數門檻的答案。詳情請參閱「只顯示有根據的答案」。

  • 選擇傳回相關問題。相關問題是建議，使用者可以選擇這些問題，而不必自行輸入問題。

  • 在查詢中加入個人化資訊，讓系統為個別使用者提供量身打造的答案。詳情請參閱「個人化回覆」。

如要取得包含圖表或圖片的多模式答案，請使用下列選項：

  • 取得的答案會包含圖表，繪製答案中包含的資料。詳情請參閱「產生答案圖表」。

  • 從資料儲存庫擷取圖片。如果資料存放區包含圖片，回答方法可以在答案中傳回圖片。如果要求提供引文，也可以在參考資料中傳回資料儲存空間中的圖片。詳情請參閱「從資料儲存區擷取現有圖片」。

事前準備

視應用程式類型而定，請完成下列要求：

  • 如果您有結構化、非結構化或網站搜尋應用程式，請開啟下列選項：

    • Enterprise 版功能：可存取核心生成式回覆功能。這包括所有答案生成功能，但進階生成式答案功能除外，例如相關問題、查詢簡化、多輪查詢，以及傳回圖片和圖表的答案。
    • 進階 LLM 功能：啟用這項功能後，您就能使用進階生成式回答功能，包括多步驟推論、簡化查詢、多輪查詢、相關問題，以及傳回圖片和圖表的多元模式回答。

  • 此外，如果您有網站搜尋資料儲存庫，請啟用「進階網站索引建立功能」。

搜尋並回答 (基本)

下列指令顯示如何呼叫 answer 方法，並傳回生成的答案和搜尋結果清單，以及來源連結。

這項指令只會顯示必要輸入內容。選項會保留預設值。

REST

如要搜尋並取得生成的答案，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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"}
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。例如「比較 BigQuery 和 Spanner 資料庫？」

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

查詢階段指令

本節說明如何為 answer 方法呼叫的查詢階段指定選項。

搜尋並回答 (重新措辭功能已停用)

下列指令顯示如何呼叫 answer 方法，並傳回生成的答案和搜尋結果清單。由於重新措辭選項已停用，因此答案可能與先前的答案不同。

REST

如要搜尋並取得附有生成答案的結果，但不套用查詢重述，請執行下列步驟：

  1. 執行下列 curl 指令：

    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
        }
    }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：Vertex AI Search 應用程式的 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。例如「比較 BigQuery 和 Spanner 資料庫？」

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

搜尋並回答 (指定最多步驟)

下列指令顯示如何呼叫 answer 方法，並傳回生成的答案和搜尋結果清單。由於重新措辭的步驟增加，因此答案與先前的答案不同。

REST

如要搜尋並取得生成的答案，最多可重新措辭五次，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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
             }
         }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。例如「比較 BigQuery 和 Spanner 資料庫？」
    • MAX_REPHRASE：重新措辭步驟的數量上限。允許的最大值為 5。 如未設定或設為小於 1，則值為預設值 1。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

透過查詢分類搜尋及回答問題

下列指令顯示如何呼叫 answer 方法，查詢查詢是否為對抗性、非尋求答案或兩者皆非。

回覆會包含查詢的分類類型，但答案本身不受分類影響。 如要根據查詢類型變更回答行為，可以在回答階段執行這項操作。請參閱「忽略惡意查詢」和「忽略非摘要查詢」。

REST

如要判斷查詢是否為對抗性或非尋求答案，請執行下列操作：

  1. 執行下列 curl 指令：

    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"]
             }
         }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。例如「hello」。
    • QUERY_CLASSIFICATION_TYPE：您要識別的查詢類型：ADVERSARIAL_QUERY、NON_ANSWER_SEEKING_QUERY 或兩者。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

搜尋階段指令：搜尋並回答，提供搜尋結果選項

本節說明如何為 answer 方法呼叫的搜尋階段指定選項，例如設定傳回的文件數上限、提升和篩選，以及在提供自己的搜尋結果時如何取得答案。

下列指令說明如何呼叫 answer 方法，並指定搜尋結果的回傳方式。(搜尋結果與答案無關)。

REST

如要設定各種選項，決定要傳回哪些搜尋結果及傳回方式，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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
           }
         }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。舉例來說，「比較 BigQuery 和 Spanner 資料庫？」
    • MAX_RETURN_RESULTS：要傳回的搜尋結果數量。預設值為 10。最大值為 25。
    • FILTER：篩選器會指定要查詢的文件。如果文件的中繼資料符合篩選條件規格，系統就會查詢該文件。如要瞭解詳情 (包括篩選器語法)，請參閱「篩選結構化或非結構化資料的自訂搜尋」。
    • BOOST_SPEC：提升規格可讓您在搜尋結果中提升特定文件，這可能會影響答案。如要瞭解詳情 (包括提升規格的語法)，請參閱「提升搜尋結果」。
    • ORDER_BY：傳回文件的順序。文件可依 Document 物件中的欄位排序。orderBy 運算式須區分大小寫。 如果無法辨識這個欄位，系統會傳回 INVALID_ARGUMENT。
    • SEARCH_RESULT_MODE：指定搜尋結果模式：DOCUMENTS 或 CHUNKS。詳情請參閱「剖析及分塊處理文件」和「ContentSearchSpec」。這個欄位僅適用於 API 的 v1alpha 版。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

回答階段指令

本節說明如何自訂 answer 方法呼叫。您可以視需要組合下列選項。

忽略對抗查詢和非尋求答案的查詢

下列指令說明在呼叫 answer 方法時，如何避免回答對手查詢和非尋求答案的查詢。

REST

如要略過對抗性或非尋求答案的查詢，請執行下列操作：

  1. 執行下列 curl 指令：

    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
        }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

只顯示相關答案

Vertex AI Search 可以評估結果與查詢的關聯性。如果系統判定沒有足夠相關的結果，您可以選擇傳回備用答案「We do not have a summary for your query.」，而不是從不相關或相關性極低的結果生成答案。

下列指令說明在呼叫 answer 方法時，如果結果不相關，如何傳回備用答案。

REST

如要傳回備用答案 (如果找不到相關結果)，請執行下列操作：

  1. 執行下列 curl 指令：

    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
        }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

傳回基礎支援分數

以下指令顯示如何傳回答案和聲明的根據支援分數。

如需 Vertex AI 基礎的相關一般資訊，請參閱「使用 RAG 檢查基礎」。groundingConfigs.check 方法是由 answer 方法呼叫。

REST

如要傳回每項主張 (答案中的句子) 的支援分數，以及答案的匯總支援分數，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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,
        }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。

只顯示有根據的答案

下列指令說明如何只傳回在語料庫 (資料存放區中的資訊) 中有根據的答案。系統會篩除根據不足的答案。

您可以選擇低或高層級的基礎支援分數門檻。然後，只有在答案達到或超過該層級時，才會傳回答案。您可以實驗這兩個篩選器門檻，以及不設門檻的情況，判斷哪種篩選器等級最有可能為使用者提供最佳結果。

如需 Vertex AI 基礎的相關一般資訊，請參閱「使用 RAG 檢查基礎」。groundingConfigs.check 方法是由 answer 方法呼叫。

REST

如要只在答案達到支援分數門檻時傳回答案，請執行下列操作：

  1. 執行下列 curl 指令：

    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"
        }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。
    • FILTER_LEVEL：列舉，用於根據基礎支援分數篩選答案。選項包括： FILTERING_LEVEL_LOW 和 FILTERING_LEVEL_HIGH。如果未加入 filteringLevel，系統就不會對答案套用任何支援分數篩選條件。

指定答案模型

下列指令顯示如何變更用於生成答案的模型版本。

如要瞭解支援的機型，請參閱「答案生成模型版本和生命週期」。

REST

如要使用預設模型以外的模型生成答案，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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",
           }
         }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。
    • MODEL_VERSION：用於生成答案的模型版本。詳情請參閱「答案生成模型版本和生命週期」。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

指定自訂前序

以下指令顯示如何為生成的答案設定前言。前言包含自然語言指示，可自訂答案。你可以要求自訂長度、詳細程度、輸出樣式 (例如「簡單」)、輸出語言、答案重點和格式 (例如表格、項目符號和 XML)。例如，前言可以是「用十歲小孩能理解的方式說明」。

前言可能會對生成的答案品質造成顯著影響。如要瞭解前言的撰寫內容和範例，請參閱「關於自訂前言」。

REST

如要使用預設模型以外的模型生成答案，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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",
           }
        }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。
    • PREAMBLE：以自然語言指示自訂答案。例如，嘗試 show the answer format in an ordered list 或 give a very detailed answer。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

回答方法可以建議相關問題，使用者可以選擇這些問題，不必自行輸入問題。舉例來說，當你詢問「墨西哥一年中哪個時間最適合度假？」時，除了回答你的問題，回答方式還會建議你可能想問的其他問題，例如「墨西哥哪個月的度假費用最便宜？」和「墨西哥的旅遊旺季是哪幾個月？」。

如要接收相關問題，您必須在每個查詢中指定納入相關問題，系統會在回應中以字串陣列的形式傳回相關問題。

事前準備

確認已為應用程式啟用進階 LLM 功能。

程序

以下指令顯示如何要求在答案中加入相關問題。

REST

如要取得相關問題和生成的答案，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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"},
        "relatedQuestionsSpec": { "enable": true }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。例如「我可以將哪些類型的資料匯入 Vertex AI Search？」

只包含書目/引用資料

以下指令顯示如何要求在答案中附上引文。

REST

如要使用預設模型以外的模型生成答案，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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
        }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。
    • INCLUDE_CITATIONS：指定是否要在答案中加入引文的中繼資料。預設值為 false。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

設定答案語言代碼

以下指令說明如何設定答案的語言代碼。

REST

如要使用預設模型以外的模型生成答案，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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"
           }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。
    • ANSWER_LANGUAGE_CODE：答案的語言代碼。請使用 BCP47：語言辨識標記中定義的語言標記。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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-2.0-flash-001/answer_gen/v1",  # 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

個人化答案

如果有可用的使用者特定資訊 (例如個人資料中的資料)，您可以在 endUserMetadata 物件中指定該資訊，以便為使用者提供個人化的查詢結果。

舉例來說，如果已登入的使用者搜尋升級手機的相關資訊，系統會根據個人資料中的資訊 (例如目前的手機型號和行動方案)，產生個人化的回覆。

如要新增提出查詢的使用者個人資訊，並生成考量個人資訊的答案，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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"},
    "endUserSpec": {
       "endUserMetadata": [
         {
           "chunkInfo": {
              "content": "PERSONALIZED_INFO",
              "documentMetadata":  { "title": "INFO_DESCRIPTION"}
           }
         }
       ]
    }
  }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。
    • PERSONALIZATION_INFO：這個字串包含查詢使用者的專屬資訊。例如： This customer has a Pixel 6 Pro purchased over a period of 24-months starting 2023-01-15. This customer is on the Business Plus International plan. No payment is due at this time. 這個字串的長度上限為 8,000 個字元。
    • INFO_DESCRIPTION：簡要說明個人化資訊的字串，例如「模型會使用這項說明和個人化資訊，針對查詢生成自訂回覆」。Customer profile data, including model, plan, and billing status.

為答案生成圖表

answer 方法可以生成圖表，並將其做為查詢回覆的一部分傳回。

您可以明確要求回覆內容包含圖表，例如「根據現有資料，繪製小型企業付款的年增率圖表」。如果系統判定資料充足，就會傳回圖表。通常會傳回一些答案文字和圖表。

此外，如果資料量充足，可建立圖表，即使查詢未明確要求圖表，答案方法仍可傳回圖表。例如：「在 2010 年至 2020 年這十年期間，更多人取得乾淨飲用水與人類發展指數 (HDI) 分數提升之間有何關聯？」

每個答案只會產生一張圖表。不過，圖表可能包含其他較小的圖表，複合圖表範例如下：

複合圖表包含四個較小的圖表

限制

查詢內容必須以英文輸入。

常見的失敗情況

系統不一定會隨回覆提供圖片。如果資料不足，系統就無法產生數據。

其他失敗情況包括程式碼執行失敗和逾時。如果發生上述任一情況，請改用其他字詞，然後再搜尋一次。

事前準備

執行要求生成圖表的查詢前，請先完成下列事項：

  • 確認已為應用程式啟用進階 LLM 功能。

  • 請確認您使用的是 Gemini 2.0 以上版本。如要瞭解模型，請參閱「答案生成模型版本和生命週期」。

  • 如果非結構化資料儲存庫包含大量表格和圖片的文件，請開啟「版面配置剖析器」。雖然這並非必要，但可獲得品質較佳的結果。

程序

REST

請按照下列方式呼叫 answer 方法，傳回的答案可以包含根據資料儲存庫資料生成的圖表：

  1. 執行下列 curl 指令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1beta/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "answerGenerationSpec": {
          "model_spec": {
             "model_version": "MODEL_VERSION"
         },
          "multimodalSpec": {
             "imageSource": "IMAGE_SOURCE"
             }
        }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：以英文輸入的任意文字字串，內含問題或搜尋查詢。
    • MODEL_VERSION：模型版本 gemini-2.0-flash-001/answer_gen/v1 以上。詳情請參閱「答案生成模型版本和生命週期」。
    • IMAGE_SOURCE：列舉要求答案包含產生的圖表、FIGURE_GENERATION_ONLY，或答案可包含產生的圖表或資料儲存區中的現有圖片、ALL_AVAILABLE_SOURCES。

從資料儲存庫擷取現有圖片

您可以選擇讓系統在回覆中傳回資料儲存庫中的圖片，並在引文參考資料中顯示。資料儲存庫必須是非結構化資料儲存庫，且已開啟版面配置剖析器。

如要在回覆中取得圖表，請務必開啟進階 LLM 功能。

當 imageSource 為 CORPUS_IMAGE_ONLY 或 ALL_AVAILABLE_SOURCES 時，answer 方法可以視需要從資料儲存庫擷取圖片。不過，開啟這項功能並不代表系統一律會傳回圖片。

每個答案最多可附上一張圖片。引文可以包含多張圖片。

限制

  • 您使用的應用程式必須連線至非結構化資料儲存庫。圖片無法從網站或結構化資料儲存庫傳回。

  • 查詢內容必須以英文輸入。

  • 透過版面配置剖析器進行的圖片註解必須套用至資料儲存庫。如要瞭解版面配置剖析器，請參閱「剖析及分塊處理文件」。

程序

REST

如要傳回答案，並在答案中加入資料存放區的圖片，請按照下列方式呼叫 answer 方法：

  1. 執行下列 curl 指令：

    curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://discoveryengine.googleapis.com/v1beta/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:answer" \
  -d '{
        "query": { "text": "QUERY"},
        "answerGenerationSpec": {
          "model_spec": {
             "model_version": "MODEL_VERSION"
          },
          includeCitations: true,
          "multimodalSpec": {
             "imageSource": "IMAGE_SOURCE"
             }
        }
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：要查詢的 Vertex AI Search 應用程式 ID。
    • QUERY：以英文輸入的任意文字字串，內含問題或搜尋查詢。
    • MODEL_VERSION：模型版本 gemini-2.0-flash-001/answer_gen/v1 以上。詳情請參閱「答案生成模型版本和生命週期」。
    • IMAGE_SOURCE：列舉，用於要求答案包含資料存放區中的圖片 (CORPUS_IMAGE_ONLY)，或答案可包含資料存放區中的圖片或產生的圖表 (ALL_AVAILABLE_SOURCES)。

後續問題的指令

後續問題是多輪查詢，在後續工作階段中，第一次查詢後，後續的「回合」會將先前的互動納入考量。透過後續問題，回答方法也能建議相關問題，使用者可以選擇這些問題，而不必自行輸入後續問題。如要取得相關問題的建議，請務必啟用進階 LLM 功能。

您可以使用前幾節所述的所有回答和後續追問功能，例如引用來源、篩選器、安全搜尋、忽略特定類型的查詢，以及使用前言自訂回答。

後續追蹤工作階段範例

以下是包含後續追蹤的會話範例。假設你想瞭解在墨西哥度假的相關資訊：

  • 第 1 回合：

    • 你：一年中什麼時候最適合到墨西哥度假？

    • 回答並提供後續資訊：墨西哥的最佳旅遊時間是乾季，也就是 11 月到 4 月。

  • 第 2 回合：

    • 你：匯率是多少？

    • 回答並追問：1 美元約等於 17.65 墨西哥披索。

  • 第 3 輪：

    • 你：12 月的平均溫度是多少？

    • 回答並追問：平均溫度為 21 到 26 攝氏度。 坎昆的平均溫度約為 25°C。

如果沒有後續問題，系統就無法回答「匯率是多少？」這個問題，因為一般搜尋不知道您想查詢墨西哥的匯率。同樣地，如果沒有後續對話，系統就無法取得提供墨西哥氣溫資訊所需的背景資訊。

關於工作階段

如要瞭解 Vertex AI Search 中的後續問題功能，您必須先瞭解工作階段。

工作階段包含使用者提供的文字查詢，以及 Vertex AI Search 提供的回覆。

這些查詢和回應組合有時也稱為「回合」。在上述範例中，第二輪對話包含「匯率是多少？」和「1 美元約等於 17.65 墨西哥披索」。

工作階段會與應用程式一併儲存。 在應用程式中，工作階段會以工作階段資源表示。

除了查詢和回應訊息外，工作階段資源還包含：

  • 專屬名稱 (工作階段 ID)。

  • 狀態 (進行中或已完成)。

  • 使用者虛擬 ID，也就是追蹤使用者的訪客 ID。可透過程式輔助方式指派。如果將模型對應至應用程式使用者事件中的使用者虛擬 ID，模型就能協助您為使用者提供個人化結果。

  • 開始時間和結束時間。

  • 一輪對話，也就是查詢和答案的配對。

事前準備

執行要求後續問題的查詢前，請務必為應用程式啟用進階 LLM 功能。

儲存工作階段資訊並取得回覆

您可以使用指令列產生搜尋回應和答案，並將這些內容連同工作階段中的每項查詢儲存起來。

REST

如要使用指令列建立工作階段，並根據使用者的輸入內容生成回覆，請按照下列步驟操作：

  1. 指定要儲存工作階段的應用程式：

    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"
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。

    • APP_ID：Vertex AI Search 應用程式的 ID。

    • USER_PSEUDO_ID：以 UTF-8 編碼的字串，可做為追蹤使用者的專屬匿名 ID。長度上限為 128 個半形字元。 Google 強烈建議使用這個欄位，因為這有助於提升模型效能和個人化品質。您可以使用 HTTP Cookie 做為這個欄位的值，明確識別單一裝置上的訪客。以下是幾個重要考量：

      • 訪客登入或登出網站時，這個 ID 不會變更。
      • 這個欄位不得為多位使用者設定相同的 ID。 否則，相同的 User-ID 可能會合併不同使用者的事件記錄，導致模型品質下降。
      • 這個欄位不得包含個人識別資訊 (PII)。
      • 針對特定搜尋或瀏覽要求，這個欄位必須對應至使用者事件中的相應 userPseudoId 欄位。

      詳情請參閱 userPseudoId。

    指令和結果範例

    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. 記下工作階段 ID，也就是 JSON 回應中 name: 欄位結尾的數字。在範例結果中，ID 為 5386462384953257772。下一個步驟會用到這個 ID。

  3. 生成答案並新增至應用程式中的工作階段：

    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"} }
}'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：Vertex AI Search 應用程式的 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。
    • SESSION_ID：您在步驟 1 建立的工作階段 ID。這些數字位於步驟 2 中記下的 name: 欄位結尾。在一個工作階段中，每次輪流對話時都使用相同的工作階段 ID。
    • FILTER：文字欄位，可使用篩選器運算式篩選搜尋結果。預設值為空字串。建構篩選條件的方式會因資料類型而異，包括含有中繼資料的非結構化資料、結構化資料或網站資料。詳情請參閱「篩選結構化或非結構化資料的自訂搜尋結果」和「篩選網站搜尋結果」。

    指令和結果範例

    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. 針對工作階段中的每項新查詢重複步驟 3。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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

從資料儲存庫取得工作階段

以下指令說明如何呼叫 get 方法，並從資料存放區取得工作階段。

REST

如要從資料存放區取得工作階段，請執行下列操作：

  1. 執行下列 curl 指令：

    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"

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：Vertex AI Search 應用程式的 ID。
    • SESSION_ID：要取得的工作階段 ID。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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

從應用程式中刪除課程

以下指令示範如何呼叫 delete 方法，並從資料存放區刪除工作階段。

根據預設，系統會自動刪除超過 60 天的會話。 不過，如要刪除特定工作階段 (例如含有私密內容)，請使用這個 API 呼叫。

REST

如要從應用程式中刪除工作階段，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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"

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：Vertex AI Search 應用程式的 ID。
    • SESSION_ID：要刪除的工作階段 ID。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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.")

更新工作階段

您可能會因為各種原因而想更新工作階段。舉例來說，您可以執行下列任一操作：

  • 將目標時段標示為完成
  • 將一個工作階段的訊息合併到另一個工作階段
  • 變更使用者的虛擬 ID

以下指令顯示如何呼叫 patch 方法，並更新資料存放區中的工作階段。

REST

如要從應用程式更新工作階段，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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"
      }'

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：Vertex AI Search 應用程式的 ID。
    • SESSION_ID：要更新的會話 ID。
    • NEW_STATE：狀態的新值，例如 IN_PROGRESS。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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

列出所有工作階段

下列指令顯示如何呼叫 list 方法，並列出資料儲存區中的工作階段。

REST

如要列出應用程式的會期，請按照下列步驟操作：

  1. 執行下列 curl 指令：

    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"

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：Vertex AI Search 應用程式的 ID。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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

列出使用者的工作階段

下列指令說明如何呼叫 list 方法，列出與使用者或訪客相關聯的工作階段。

REST

如要列出與使用者或訪客相關聯的工作階段，請執行下列操作：

  1. 執行下列 curl 指令：

    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"

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：Vertex AI Search 應用程式的 ID。
    • USER_PSEUDO_ID：您要列出工作階段的使用者虛擬 ID。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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

列出使用者和狀態的工作階段

以下指令說明如何呼叫 list 方法，列出特定使用者處於指定狀態的工作階段。

REST

如要列出與特定使用者或訪客相關聯的開啟或關閉工作階段，請執行下列操作：

  1. 執行下列 curl 指令：

    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"

    更改下列內容：

    • PROJECT_ID：您的 Google Cloud 專案 ID。
    • APP_ID：Vertex AI Search 應用程式的 ID。
    • USER_PSEUDO_ID：您要列出工作階段的使用者虛擬 ID。
    • STATE：工作階段狀態： STATE_UNSPECIFIED (已關閉或不明) 或 IN_PROGRESS (已開啟)。

Python

詳情請參閱 AI Applications Python API 參考說明文件。

如要向 AI Applications 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

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