取得回覆和後續追蹤 (舊版)

本頁面介紹 Gemini Enterprise 的「搜尋並回答及後續追蹤」功能，並說明如何使用方法呼叫實作。

「搜尋答案」和「後續問題」功能採用回答方法。answer 方法也提供一些重要的額外功能，例如處理複雜查詢。

回答方式的特色

answer 方法的主要功能如下：

  • 生成複雜查詢的答案。舉例來說，answer 方法可以將複合查詢 (例如以下查詢) 拆解成多個較小的查詢，傳回更準確的結果，進而提供更優質的答案：

    • 「Google Cloud 和 Google Ads 在 2024 年的收益分別是多少？」
    • 「Google 成立幾年後，收益達到 10 億美元？」

  • 在多輪對話中，透過在每輪對話呼叫 answer 方法，結合搜尋和答案生成功能。

  • 可與搜尋方法配對，縮短搜尋延遲時間。您可以分別呼叫搜尋方法和解答方法，並在不同時間，於不同 iframe 中算繪搜尋結果和解答。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)。您不必等到系統生成答案，就能顯示搜尋結果。

回答和後續問題的功能可分為查詢、搜尋和回答三個階段：

回答和搜尋功能的適用時機

Gemini Enterprise 有兩種方法可用於查詢應用程式。兩者功能不同，但有部分重疊。

在下列情況下，請使用 answer 方法：

  • 您希望取得 AI 生成的搜尋結果答案 (或摘要)。

  • 您想要多輪搜尋，也就是保留內容的搜尋，可供後續提問。

在下列情況下，請使用 search 方法：

  • 您只需要搜尋結果，不需要生成的答案。

  • 您希望系統傳回超過十個搜尋結果 (「藍色連結」)。

  • 您具備下列任一條件：

    • 自備嵌入
    • 同義詞或重新導向控制項
    • facet
    • 使用者國家/地區代碼

在下列情況下，請同時使用回答和搜尋方法：

  • 您希望傳回超過十筆搜尋結果，「且」希望取得生成的答案。

  • 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

「答案和後續問題」功能支援自然語言查詢處理。

本節將說明並圖解查詢改寫和分類的各種選項。

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改寫查詢，提升搜尋結果品質。這項功能也能處理不需要重新措辭的查詢。

  • 將複雜查詢拆解為多項查詢，並執行同步子查詢。

    例如：將複雜查詢拆解成四個較簡單的查詢。

    使用者輸入內容 從複雜查詢建立的子查詢
    Andie Ram 和 Arnaud Clément 有哪些共同的職業和興趣？
    • Andie Ram 職業
    • Arnaud Clément 職業
    • Andie Ram 嗜好
    • Arnaud Clément 嗜好

  • 彙整多輪查詢，讓後續問題能考量上下文和狀態。

    例如，根據使用者在每個回合輸入的內容合成的查詢可能如下所示：

    使用者輸入內容 已統整查詢
    Turn 1: laptops for school 上學用筆電
    第 2 輪：不是 mac 學校適用的筆記型電腦 (非 Mac)
    Turn 3: bigger screen and i also need wireless keyboard and mouse 學校用大螢幕筆電，非 Mac，附無線鍵盤和滑鼠
    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，還要能裝筆電的背包

  • 簡化冗長的查詢，提升檢索成效。

    例如：將冗長的查詢縮短為簡單的查詢。

    使用者輸入內容 查詢簡化
    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。使用者點選按鈕後，商品似乎不會加入購物車，而且會收到錯誤訊息。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) 範式為基礎，可讓 LLM 使用自然語言推論解決複雜工作。預設最多可有五個步驟。

    例如：

    使用者輸入內容 生成答案的兩個步驟
    Google 創立幾年後，收益達到 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: When was Google founded?[Observe Search Results]: "1998"

    Step 2:
    [Thought]: Now I need to Google's yearly revenue since 1998, and find out when it exceeded 1 billion for the first time.
    [Act] Search: Google revenue since 1998
    [Observe Search Results] Google revenue in 1998, Google revenue in 1999…..
    [Answer]: Google reached more than 1 billion USD revenue in 2003 [1], 5 years after its founding in 1998[2].

查詢分類

查詢分類選項可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。

如要進一步瞭解對抗性查詢和非尋求答案的查詢，請參閱「忽略對抗性查詢」和「忽略非尋求摘要的查詢」。

搜尋階段功能

在搜尋方面，answer 方法的選項與 search 方法相同。例如：

回答階段功能

在回答階段，系統會根據搜尋結果生成答案，您可以啟用與搜尋方法相同的各項功能。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 到 1 之間的浮點值，表示資料儲存庫中的資料對主張的支持程度。詳情請參閱「傳回基準支援分數」。

  • 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「傳回基準支援分數」。

  • 只傳回有充分依據的答案。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「僅顯示有充分依據的答案」。

  • 在查詢中加入個人化資訊，讓系統為個別使用者提供客製化答案。詳情請參閱「個人化回覆」。

如要取得多模態回覆 (除了文字外，還包含圖表或圖片)，可使用下列選項：

  • 取得的回覆包含圖表，可繪製回覆中的資料。詳情請參閱「生成答案圖表」。

  • 從資料儲存庫擷取圖片。如果資料儲存庫包含圖片，答案方法可以在答案中傳回圖片。如果要求提供引文，也可以在參照中傳回資料儲存空間中的圖片。詳情請參閱「從資料儲存空間擷取現有圖片」。

搜尋及回答 (基本)

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

這個指令只會顯示必要輸入內容。其餘選項則保留預設值。

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：專案的 ID。
    • APP_ID：要查詢的應用程式 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

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

    # 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 (已停用重述功能)

下列指令說明如何呼叫 answer 方法，並傳回生成的答案和搜尋結果清單。由於換句話說選項已停用，答案可能與前一個答案不同。

REST

如要搜尋並取得生成式答案，但不套用查詢重述，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": {
              "disable": true
        }
    }
      }'

    更改下列內容：

    • PROJECT_ID：專案的 ID。
    • APP_ID：應用程式 ID。
    • QUERY：包含問題或搜尋查詢的自由文字字串。例如「比較 BigQuery 和 Spanner 資料庫」。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱「Gemini Enterprise Python API 參考文件」。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

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

    # Handle the response
    print(response)

    return response

搜尋並回答 (指定步驟上限)

下列指令說明如何呼叫 answer 方法，並傳回生成的答案和搜尋結果清單。答案與先前的答案不同，因為重新措辭的步驟數量已增加。

REST

如要搜尋並取得生成式答案，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：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：包含問題或搜尋查詢的自由文字字串。例如：「比較 BigQuery 和 Spanner 資料庫」。
    • MAX_REPHRASE：改寫步驟數量上限。允許的最大值為 5。 如未設定或設定的值小於 1，則會採用預設值 1。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱「Gemini Enterprise Python API 參考文件」。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

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

    # Handle the response
    print(response)

    return response

使用查詢分類功能搜尋及回答

下列指令說明如何呼叫 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「忽略對抗性查詢」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": {
            "queryClassificationSpec": {
                "types": ["QUERY_CLASSIFICATION_TYPE"]
             }
         }
      }'

    更改下列內容：

    • PROJECT_ID：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：包含問題或搜尋查詢的自由文字字串。例如「hello」。
    • QUERY_CLASSIFICATION_TYPE：要識別的查詢類型：ADVERSARIAL_QUERY、NON_ANSWER_SEEKING_QUERY 或兩者。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱「Gemini Enterprise Python API 參考文件」。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

    # 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，附帶搜尋結果選項

本節說明如何為 answer 方法呼叫的搜尋階段部分指定選項，例如設定傳回的文件數量上限、提升和篩選，以及如何在提供自己的搜尋結果時取得答案。

下列指令說明如何呼叫 answer 方法，並指定搜尋結果傳回方式的各種選項。(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：專案的 ID。
    • APP_ID：要查詢的應用程式 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_RETURN_RESULTS：要傳回的搜尋結果數量。預設值為 10。
    • FILTER：篩選條件會指定要查詢的文件。如果文件的中繼資料符合篩選器規格，系統就會查詢該文件。如需更多資訊 (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。如要進一步瞭解提升規格的語法等資訊，請參閱「提升搜尋結果」。
    • ORDER_BY：傳回文件的順序。文件可以依 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，可以是 DOCUMENTS 或 CHUNKS。詳情請參閱「剖析及分塊文件」和「ContentSearchSpec」。這個欄位僅適用於 API 的 v1alpha 版本。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱「Gemini Enterprise Python API 參考文件」。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

    # 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。您可以視需要結合下列選項。

忽略對抗查詢和非尋求答案的查詢

下列指令說明如何在呼叫 answer 方法時，避免回答對抗性查詢和非尋求答案的查詢。

REST

如要略過回答對抗性或非尋求答案的查詢，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": {
           "ignoreAdversarialQuery": true,
           "ignoreNonAnswerSeekingQuery": true
        }
      }'

    更改下列內容：

    • PROJECT_ID：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：包含問題或搜尋查詢的自由文字字串。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

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

    # Handle the response
    print(response)

    return response

只顯示相關答案

Gemini Enterprise 可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。

下列指令說明如何在呼叫 answer 方法時，傳回不相關結果的備用答案。

REST

如要傳回備用答案 (找不到相關結果時)，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：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：包含問題或搜尋查詢的自由文字字串。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

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

    # Handle the response
    print(response)

    return response

傳回基準支援分數

下列指令說明如何傳回答案和論述的基準支援分數。

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：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：包含問題或搜尋查詢的自由文字字串。

僅顯示有充分依據的答案

下列指令說明如何只傳回在語料庫 (資料儲存庫中的資訊) 中有充分根據的答案。系統會篩除依據不足的答案。

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等級時，才會傳回。您可以實驗這兩種篩選器門檻，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。

REST

如要只傳回符合支援分數門檻的答案，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"},
        "groundingSpec": {
           "filteringLevel": "FILTER_LEVEL"
        }
      }'

    更改下列內容：

    • PROJECT_ID：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：包含問題或搜尋查詢的任意文字字串。
    • FILTER_LEVEL：根據基準支援分數篩選答案的列舉。選項包括： FILTERING_LEVEL_LOW 和 FILTERING_LEVEL_HIGH。如果未納入 filteringLevel，系統就不會對答案套用支援分數篩選器。

指定答案模型

下列指令說明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：專案的 ID。
    • APP_ID：要查詢的應用程式 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

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

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

    # Handle the response
    print(response)

    return response

指定自訂前序

下列指令說明如何為生成的答案設定前導提示。前導提示包含自然語言指令，可用來自訂答案。你可以要求自訂長度、詳細程度、輸出風格 (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)。舉例來說，前導提示可以是「用十歲小孩的口吻解釋」。

前導提示可能會對生成的答案品質造成重大影響。如要瞭解前言的撰寫方式和前言範例，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回覆，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：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：包含問題或搜尋查詢的自由文字字串。
    • PREAMBLE：以自然語言提供指示，自訂回覆內容。例如，嘗試 show the answer format in an ordered list 或 give a very detailed answer。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

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

    # Handle the response
    print(response)

    return response

加入引用內容

下列指令說明如何要求在回覆中加入引用來源。

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：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：包含問題或搜尋查詢的自由文字字串。
    • INCLUDE_CITATIONS：指定是否要在答案中加入引用中繼資料。預設值為 false。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

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

    # Handle the response
    print(response)

    return response

設定答案語言代碼

下列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：專案的 ID。
    • APP_ID：要查詢的應用程式 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

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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(
        # Use the 2026 stable production model for answer generation
        model_version="gemini-2.5-flash/answer_gen/stable",
        ),
        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,
        user_pseudo_id="user-pseudo-id",  # Optional: Add user pseudo-identifier for queries.
    )

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

    # Handle the response
    print(response)

    return response

個人化答案

如果有使用者的特定資訊 (例如設定檔中的資料)，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網路方案)，提供個人化的生成回覆。

如要新增查詢者的個人資訊，並生成考量個人資訊的回覆，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：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：包含問題或搜尋查詢的自由文字字串。
    • 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：簡短說明個人化資訊的字串，例如 Customer profile data, including model, plan, and billing status.。模型會同時使用這項說明和個人化資訊，生成查詢的自訂答案。

為答案生成圖表

answer 方法可以生成圖表，並在查詢回覆中傳回。

您可以特別要求答案包含圖表，例如「根據可用資料，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，如果資料量足以建立圖表，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 年到 2020 年這十年間，乾淨飲用水取得管道增加，與人類發展指數分數提升有何關聯？」

每個答案只會生成一個圖表。不過，圖表可能是複合圖表，包含其他較小的圖表。複合圖表示例：

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。

常見失敗情境

系統不一定會隨答案傳回圖片。如果資料不足，就無法產生圖表。

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，然後再試一次。

事前準備

執行查詢要求生成圖表前，請先完成下列事項：

  • 請確認您使用的是 Gemini 2.0 以上版本模型。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中的文件包含大量表格和圖片，請開啟「Layout parser」(版面配置剖析器)。雖然這並非絕對必要，但可以提供更優質的結果。

程序

REST

呼叫 answer 方法，如下所示，傳回的答案可包含根據資料儲存庫中的資料生成的圖表：

  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：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：以英文撰寫的自由格式字串，內含問題或搜尋查詢。
    • MODEL_VERSION：模型版本 stable或其他支援的模型，請參閱「答案生成模型版本和生命週期」。
    • IMAGE_SOURCE：列舉，要求答案包含生成的圖表 FIGURE_GENERATION_ONLY，或答案可包含生成的圖表或資料儲存庫中的現有圖片 ALL_AVAILABLE_SOURCES。

從資料儲存庫擷取現有圖片

您可以選擇讓回覆和引用參考資料傳回資料儲存庫中的圖片。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。

如果 imageSource 為 CORPUS_IMAGE_ONLY 或 ALL_AVAILABLE_SOURCES，answer 方法會視情況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。

每個答案最多可附一張圖片。引文可包含多張圖片。

限制

  • 您使用的應用程式必須連結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「剖析及分塊文件」。

程序

REST

呼叫 answer 方法，傳回可包含資料儲存庫圖片的答案：

  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：專案的 ID。
    • APP_ID：要查詢的應用程式 ID。
    • QUERY：以英文撰寫的自由格式字串，內含問題或搜尋查詢。
    • MODEL_VERSION：模型版本 stable 或其他支援的模型，請參閱「答案生成模型版本和生命週期」。
    • IMAGE_SOURCE：列舉，要求答案包含資料儲存庫中的圖片 (CORPUS_IMAGE_ONLY)，或答案可包含資料儲存庫中的圖片或生成式圖表 (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，系統會根據第一個查詢，以及先前的互動，此外，回答方法還會根據後續問題建議相關問題，使用者可以選擇這些問題，不必自行輸入後續問題。

上述各節提到的所有答案和後續問題功能，例如引用、篩選器、安全搜尋、忽略特定類型的查詢，以及使用前導提示自訂答案，都可以與後續問題搭配使用。

後續追蹤工作階段範例

以下是後續追蹤的對話範例。假設你想瞭解在墨西哥度假的相關資訊：

  • 第 1 輪：

    • 你：一年中什麼時候最適合去墨西哥度假？

    • 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 輪：

    • 你：匯率是多少？

    • 回答並提供後續資訊：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？

    • 回答並提供後續資訊：平均溫度介於 70 至 78°F 之間。 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，因為一般搜尋不會知道您想查詢墨西哥的匯率。同樣地，如果沒有後續追問，我們就無法取得提供墨西哥專屬溫度資訊所需的背景資訊。

當你詢問「一年中什麼時候最適合到墨西哥度假？」時，除了回答你的問題，回答和後續問題還會建議你可能想問的其他問題，例如「到墨西哥度假最便宜的月份是哪幾個月？」和「墨西哥的旅遊旺季是哪幾個月？」。

啟用相關問題功能後，問題會以字串形式傳回。

關於工作階段

如要瞭解 Gemini Enterprise 中的後續追問功能，必須先瞭解工作階段。

工作階段是由使用者提供的文字查詢和 Gemini Enterprise 的回覆組成。

這類查詢和回覆組合有時稱為對話。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起儲存。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。可以透過程式輔助方式指派。

  • 開始時間和結束時間。

  • 一輪對話，也就是查詢和答案的配對。

儲存工作階段資訊並取得回覆

您可以使用命令列產生搜尋回覆和答案，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：專案的 ID。

    • APP_ID：應用程式 ID。

    • USER_PSEUDO_ID：用來追蹤搜尋訪客的專屬 ID。舉例來說，您可以使用 HTTP Cookie 實作這項功能，在單一裝置上明確識別訪客。

    指令與結果範例

    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：專案的 ID。
    • APP_ID：應用程式 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。這些是 name: 欄位結尾的數字，如步驟 2 所示。在一個工作階段中，每次輪流對話都使用相同的工作階段 ID。
    • FILTER：文字欄位，用於透過篩選運算式篩選搜尋結果。預設值為空白字串。建構篩選條件的方式取決於您擁有的是含中繼資料的非結構化資料、結構化資料，還是網站資料。詳情請參閱「篩選結構化或非結構化資料的自訂搜尋」。

    指令與結果範例

    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，重複執行步驟 3。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱「Gemini Enterprise Python API 參考文件」。

如要向 Gemini Enterprise 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機制」。

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.SessionServiceClient()

    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

下列指令說明如何呼叫 get 方法，並從資料儲存庫取得工作階段。

REST

如要從資料儲存庫取得工作階段，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/SESSION_ID"

    更改下列內容：

    • PROJECT_ID：專案的 ID。
    • APP_ID：應用程式 ID。
    • SESSION_ID：要取得的工作階段 ID。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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.SessionServiceClient()

    # 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

從應用程式中刪除工作階段

下列指令說明如何呼叫 delete 方法，並從資料儲存庫中刪除工作階段。

根據預設，系統會自動刪除超過 60 天的記錄。 不過，如要刪除特定工作階段 (例如含有敏感內容)，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：專案的 ID。
    • APP_ID：應用程式 ID。
    • SESSION_ID：要刪除的工作階段 ID。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱「Gemini Enterprise Python API 參考文件」。

如要向 Gemini Enterprise 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機制」。

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.SessionServiceClient()

    # 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

您可能基於各種原因需要更新工作階段。例如，執行下列任一操作：

  • 將工作階段標示為完成
  • 將一個工作階段的訊息併入另一個工作階段
  • 變更使用者的虛擬 ID

下列指令說明如何呼叫 patch 方法，並更新資料儲存庫中的工作階段。

REST

如要透過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：專案的 ID。
    • APP_ID：應用程式 ID。
    • SESSION_ID：要更新的會期 ID。
    • NEW_STATE：狀態的新值，例如 IN_PROGRESS。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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.SessionServiceClient()

    # 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

下列指令說明如何呼叫 list 方法，並列出資料儲存庫中的工作階段。

REST

如要列出應用程式的工作階段，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：專案的 ID。
    • APP_ID：應用程式 ID。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱「Gemini Enterprise Python API 參考文件」。

如要向 Gemini Enterprise 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機制」。

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.SessionServiceClient()

    # 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?filter=userPseudoId=USER_PSEUDO_ID"

    更改下列內容：

    • PROJECT_ID：專案的 ID。
    • APP_ID：應用程式 ID。
    • USER_PSEUDO_ID：要列出工作階段的使用者虛擬 ID。

Python

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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.SessionServiceClient()

    # 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

下列指令說明如何呼叫 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?filter=userPseudoId=USER_PSEUDO_ID%20AND%20state=STATE"

    更改下列內容：

    • PROJECT_ID：專案的 ID。
    • APP_ID：應用程式 ID。
    • USER_PSEUDO_ID：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

在試用這個範例之前，請先按照「使用用戶端程式庫的 Gemini Enterprise 快速入門導覽課程」中的 Python 設定說明操作。詳情請參閱 Gemini Enterprise Python API 參考文件。

如要向 Gemini Enterprise 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機制」。

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.SessionServiceClient()

    # 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