本頁面由 Cloud Translation API 翻譯而成。

篩選自訂搜尋的結構化或非結構化資料

如果您有使用結構化資料的搜尋應用程式，或使用含有中繼資料的非結構化資料，可以運用中繼資料篩選搜尋查詢。本頁說明如何使用中繼資料欄位，將搜尋範圍限制在特定文件集。

事前準備

請確認您已建立應用程式，並擷取結構化資料或含有中繼資料的非結構化資料。詳情請參閱「建立搜尋應用程式」。

中繼資料範例

請參閱以下四個 PDF 檔案 (document_1.pdf、document_2.pdf、document_3.pdf 和 document_4.pdf) 的中繼資料範例。這些中繼資料會與 PDF 檔案一起存放在 Cloud Storage bucket 的 JSON 檔案中。閱讀本頁內容時，您可以隨時返回這個範例。

{"id": "1", "structData": {"title": "Policy on accepting corrected claims", "category": ["persona_A"]}, "content": {"mimeType": "application/pdf", "uri": "gs://bucketname_87654321/data/document_1.pdf"}}
{"id": "2", "structData": {"title": "Claims documentation and reporting guidelines for commercial members", "category": ["persona_A", "persona_B"]}, "content": {"mimeType": "application/pdf", "uri": "gs://bucketname_87654321/data/document_2.pdf"}}
{"id": "3", "structData": {"title": "Claims guidelines for bundled services and supplies for commercial members", "category": ["persona_B", "persona_C"]}, "content": {"mimeType": "application/pdf", "uri": "gs://bucketname_87654321/data/document_3.pdf"}}
{"id": "4", "structData": {"title": "Advantage claims submission guidelines", "category": ["persona_A", "persona_C"]}, "content": {"mimeType": "application/pdf", "uri": "gs://bucketname_87654321/data/document_4.pdf"}}

篩選運算式語法

請務必瞭解用於定義搜尋篩選器的篩選運算式語法。篩選運算式語法可歸納為下列擴充巴科斯諾爾形式：

  # A single expression or multiple expressions that are joined by "AND" or "OR".
  filter = expression, { " AND " | "OR", expression };
  # Expressions can be prefixed with "-" or "NOT" to express a negation.
  expression = [ "-" | "NOT " ],
    # A parenthetical expression.
    | "(", expression, ")"
    # A simple expression applying to a text field.
    # Function "ANY" returns true if the field exactly matches any of the literals.
    ( text_field, ":", "ANY", "(", literal, { ",", literal }, ")"
    # A simple expression applying to a numerical field. Function "IN" returns true
    # if a field value is within the range. By default, lower_bound is inclusive and
    # upper_bound is exclusive.
    | numerical_field, ":", "IN", "(", lower_bound, ",", upper_bound, ")"
    # A simple expression that applies to a numerical field and compares with a double value.
    | numerical_field, comparison, double
    # An expression that applies to a geolocation field with text/street/postal address.
    |  geolocation_field, ":", "GEO_DISTANCE(", literal, ",", distance_in_meters, ")"
    # An expression that applies to a geolocation field with latitude and longitude.
    | geolocation_field, ":", "GEO_DISTANCE(", latitude_double, ",", longitude_double, ",", distance_in_meters, ")"
    # Datetime field
    | datetime_field, comparison, literal_iso_8601_datetime_format);
  # A lower_bound is either a double or "*", which represents negative infinity.
  # Explicitly specify inclusive bound with the character 'i' or exclusive bound
  # with the character 'e'.
  lower_bound = ( double, [ "e" | "i" ] ) | "*";
  # An upper_bound is either a double or "*", which represents infinity.
  # Explicitly specify inclusive bound with the character 'i' or exclusive bound
  # with the character 'e'.
  upper_bound = ( double, [ "e" | "i" ] ) | "*";
  # Supported comparison operators.
  comparison = "<=" | "<" | ">=" | ">" | "=";
  # A literal is any double quoted string. You must escape backslash (\) and
  # quote (") characters.
  literal = double quoted string;
  text_field = text field - for example, category;
  numerical_field = numerical field - for example, score;
  geolocation_field = field of geolocation data type - for example home_address, location;
  datetime_field = field of datetime data type - for example creation_date, expires_on;
  literal_iso_8601_datetime_format = either a double quoted string representing ISO 8601 datetime or a numerical field representing microseconds from unix epoch.

使用中繼資料篩選器搜尋

如要使用中繼資料篩選器搜尋，請按照下列步驟操作：

決定要使用哪個中繼資料欄位來篩選搜尋查詢。舉例來說，針對「開始前」一節中的中繼資料，您可以使用 category 欄位做為搜尋篩選器。使用者可以依persona_A、persona_B 或 persona_C篩選，將搜尋範圍限制在與感興趣的角色相關聯的文件。
將中繼資料欄位設為可建立索引：
1. 前往 Google Cloud 控制台的「AI Applications」頁面，然後在導覽選單中點選「Apps」。
  
  前往「應用程式」頁面
2. 按一下搜尋應用程式。
3. 在導覽選單中，按一下「資料」。
4. 按一下 [Schema] (結構定義) 分頁標籤。這個分頁會顯示目前的欄位設定。
  
  注意： 只有包含結構化資料或含有中繼資料的非結構化資料的資料儲存庫，才會顯示「結構定義」分頁標籤。
5. 按一下 [編輯]。
6. 找出要設為可建立索引的欄位，然後選取「可建立索引」核取方塊。
7. 按一下 [儲存]。詳情請參閱「設定欄位設定」。
找出資料儲存庫 ID。如果已有資料商店 ID，請跳到下一個步驟。
1. 前往 Google Cloud 控制台的「AI Applications」頁面，然後在導覽選單中點選「Data Stores」。
  
  前往「資料儲存庫」頁面
2. 點按資料儲存庫的名稱。
3. 在資料儲存庫的「資料」頁面中，取得資料儲存庫 ID。

取得搜尋結果。

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/dataStores/DATA_STORE_ID/servingConfigs/default_search:search" \
-d '{
"query": "QUERY",
"filter": "FILTER"
}'

更改下列內容：

PROJECT_ID：您的專案 ID。
DATA_STORE_ID：資料儲存庫的 ID。
QUERY：要搜尋的查詢文字。
FILTER：選用。文字欄位，可讓您使用篩選運算式語法，針對一組特定欄位進行篩選。預設值為空字串，表示未套用任何篩選器。

舉例來說，假設您從「事前準備」一節匯入了四個 PDF 檔案和中繼資料。您想搜尋含有「claims」一詞的文件，且只查詢 category 值為 persona_A 的文件。如要這麼做，請在呼叫中加入下列陳述式：

"query": "claims",
"filter": "category: ANY(\"persona_A\")"

詳情請參閱「Get search results for an app with structured or unstructured data」的 REST 分頁。

按一下即可查看範例回覆。

如果您執行類似上述程序的搜尋，預期會收到類似以下的回覆。請注意，回應包含 category 值為 persona_A 的三份文件。

{
"results": [
{
  "id": "2",
  "document": {
    "name": "projects/abcdefg/locations/global/collections/default_collection/dataStores/search_store_id/branches/0/documents/2",
    "id": "2",
    "structData": {
      "title": "Claims documentation and reporting guidelines for commercial members",
      "category": [
        "persona_A",
        "persona_B"
      ]
    },
    "derivedStructData": {
      "link": "gs://bucketname_87654321/data/document_2.pdf",
      "extractive_answers": [
        {
          "pageNumber": "1",
          "content": "lorem ipsum"
        }
      ]
    }
  }
},
{
  "id": "1",
  "document": {
    "name": "projects/abcdefg/locations/global/collections/default_collection/dataStores/search_store_id/branches/0/documents/1",
    "id": "1",
    "structData": {
      "title": "Policy on accepting corrected claims",
      "category": [
        "persona_A"
      ]
    },
    "derivedStructData": {
      "extractive_answers": [
        {
          "pageNumber": "2",
          "content": "lorem ipsum"
        }
      ],
      "link": "gs://bucketname_87654321/data/document_1.pdf"
    }
  }
},
{
  "id": "4",
  "document": {
    "name": "projects/abcdefg/locations/global/collections/default_collection/dataStores/search_store_id/branches/0/documents/4",
    "id": "4",
    "structData": {
      "title": "Advantage claims submission guidelines",
      "category": [
        "persona_A",
        "persona_C"
      ]
    },
    "derivedStructData": {
      "extractive_answers": [
        {
          "pageNumber": "47",
          "content": "lorem ipsum"
        }
      ],
      "link": "gs://bucketname_87654321/data/document_4.pdf"
    }
  }
}
],
"totalSize": 330,
"attributionToken": "UvBRCgsI26PxpQYQs7vQZRIkNjRiYWY1MTItMDAwMC0yZWIwLTg3MTAtMTQyMjNiYzYzMWEyIgdHRU5FUklDKhSOvp0VpovvF8XL8xfC8J4V1LKdFQ",
"guidedSearchResult": {},
"summary": {}
}

篩選運算式範例

下表提供篩選器運算式範例。

篩選器	只會傳回符合下列條件的文件結果：
`category: ANY("persona_A")`	文字欄位 `category` 為 `persona_A`
`score: IN(*, 100.0e)`	數值欄位 `score` 大於負無限大，且小於 100.0
`non-smoking = "true"`	布林值 `non-smoking` 為 true
`pet-friendly = "false"`	布林值 `pet-friendly` 為 false
`manufactured_date = "2023"`	`manufactured date`為 2023 年的任何時間
`manufactured_date >= "2024-04-16"`	`manufactured_date`在 2024 年 4 月 16 日當天或之後
`manufactured_date < "2024-04-16T12:00:00-07:00"`	`manufactured_date` 是 2024 年 4 月 16 日太平洋夏令時間中午 12 點前
`office.location:GEO_DISTANCE("1600 Amphitheater Pkwy, Mountain View, CA, 94043", 500)`	地理位置欄位 `office.location` 位於 1600 Amphitheater Pkwy 的 500 公尺範圍內
`NOT office.location:GEO_DISTANCE("Palo Alto, CA", 1000)`	地理位置欄位 `office.location` 不在加州帕羅奧圖方圓 1 公里內。
`office.location:GEO_DISTANCE(34.1829, -121.293, 500)`	地理位置欄位 `office.location` 位於緯度 34.1829 和經度 -121.293 的 500 公尺半徑內
`category: ANY("persona_A") AND score: IN(*, 100.0e)`	`category`為 `persona_A`，且 `score` 小於 100
`office.location:GEO_DISTANCE("Mountain View, CA", 500) OR office.location:GEO_DISTANCE("Palo Alto, CA", 500)`	`office.location` 位於山景城或帕羅奧圖 500 公尺內。
`(price<175 AND pet-friendly = "true") OR (price<125 AND pet-friendly = "false")`	`price` 小於 175，我可以攜帶寵物；或 `price` 小於 125，我無法攜帶寵物

後續步驟

如要瞭解篩選器對搜尋品質的影響，請評估搜尋品質。詳情請參閱評估搜尋品質。