如何在认知搜索中创建 TEXTSPLIT 技能以及如何在索引器中引用它

问题描述 投票：0回答：1

我不知道如何创建文本拆分技能并在索引器中引用它

导入数据后，我创建了一个索引器，并使用了语言检测和关键阶段提取等内置技能。但是，我找不到将 TEXTSPLIT 技能添加到我创建的索引器中的方法。

索引：

{
  "@odata.context": "https://mssearchser.search.windows.net/$metadata#indexes/$entity",
  "@odata.etag": "\"0x8DC690C7EB356B6\"",
  "name": "azureblob-index",
  "defaultScoringProfile": "",
  "fields": [
    {
      "name": "content",
      "type": "Edm.String",
      "searchable": true,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "standard.lucene",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_storage_content_type",
      "type": "Edm.String",
      "searchable": false,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_storage_size",
      "type": "Edm.Int64",
      "searchable": false,
      "filterable": true,
      "retrievable": true,
      "stored": true,
      "sortable": true,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_storage_last_modified",
      "type": "Edm.DateTimeOffset",
      "searchable": false,
      "filterable": true,
      "retrievable": true,
      "stored": true,
      "sortable": true,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_storage_content_md5",
      "type": "Edm.String",
      "searchable": false,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_storage_name",
      "type": "Edm.String",
      "searchable": false,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_storage_path",
      "type": "Edm.String",
      "searchable": false,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": true,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_storage_file_extension",
      "type": "Edm.String",
      "searchable": false,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_content_type",
      "type": "Edm.String",
      "searchable": false,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_author",
      "type": "Edm.String",
      "searchable": true,
      "filterable": true,
      "retrievable": true,
      "stored": true,
      "sortable": true,
      "facetable": true,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "standard.lucene",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_creation_date",
      "type": "Edm.DateTimeOffset",
      "searchable": false,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "metadata_last_modified",
      "type": "Edm.DateTimeOffset",
      "searchable": false,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "locations",
      "type": "Collection(Edm.String)",
      "searchable": true,
      "filterable": true,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "standard.lucene",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "keyphrases",
      "type": "Collection(Edm.String)",
      "searchable": true,
      "filterable": true,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "standard.lucene",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "language",
      "type": "Edm.String",
      "searchable": false,
      "filterable": true,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": null,
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "merged_content",
      "type": "Edm.String",
      "searchable": true,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "standard.lucene",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "text",
      "type": "Collection(Edm.String)",
      "searchable": true,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "standard.lucene",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    },
    {
      "name": "layoutText",
      "type": "Collection(Edm.String)",
      "searchable": true,
      "filterable": false,
      "retrievable": true,
      "stored": true,
      "sortable": false,
      "facetable": false,
      "key": false,
      "indexAnalyzer": null,
      "searchAnalyzer": null,
      "analyzer": "standard.lucene",
      "normalizer": null,
      "dimensions": null,
      "vectorSearchProfile": null,
      "synonymMaps": []
    }
  ],
  "scoringProfiles": [],
  "corsOptions": null,
  "suggesters": [],
  "analyzers": [],
  "normalizers": [],
  "tokenizers": [],
  "tokenFilters": [],
  "charFilters": [],
  "encryptionKey": null,
  "similarity": {
    "@odata.type": "#Microsoft.Azure.Search.BM25Similarity",
    "k1": null,
    "b": null
  },
  "semantic": null,
  "vectorSearch": null
}

索引器：

{
  "@odata.context": "https://mssearchser.search.windows.net/$metadata#indexers/$entity",
  "@odata.etag": "\"0x8DC690CB8941711\"",
  "name": "terminal-indexer",
  "description": "",
  "dataSourceName": "terminal-data",
  "skillsetName": "terminal-skillset",
  "targetIndexName": "azureblob-index",
  "disabled": null,
  "schedule": null,
  "parameters": {
    "batchSize": null,
    "maxFailedItems": 0,
    "maxFailedItemsPerBatch": 0,
    "base64EncodeKeys": null,
    "configuration": {
      "dataToExtract": "contentAndMetadata",
      "parsingMode": "default",
      "imageAction": "generateNormalizedImages"
    }
  },
  "fieldMappings": [
    {
      "sourceFieldName": "metadata_storage_path",
      "targetFieldName": "metadata_storage_path",
      "mappingFunction": {
        "name": "base64Encode",
        "parameters": null
      }
    }
  ],
  "outputFieldMappings": [
    {
      "sourceFieldName": "/document/merged_content/locations",
      "targetFieldName": "locations"
    },
    {
      "sourceFieldName": "/document/merged_content/keyphrases",
      "targetFieldName": "keyphrases"
    },
    {
      "sourceFieldName": "/document/language",
      "targetFieldName": "language"
    },
    {
      "sourceFieldName": "/document/merged_content",
      "targetFieldName": "merged_content"
    },
    {
      "sourceFieldName": "/document/normalized_images/*/text",
      "targetFieldName": "text"
    },
    {
      "sourceFieldName": "/document/normalized_images/*/layoutText",
      "targetFieldName": "layoutText"
    }
  ],
  "cache": null,
  "encryptionKey": null
}
json azure indexing azure-cognitive-services indexer
1个回答
0
投票
  • 文本分割技能旨在将文本分割成可管理的块，可以按指定长度的句子或页面。
  • 它提供了多个自定义参数，例如确定拆分模式（页面或句子）以及设置每页的最大长度。

定义示例：

{
    "@odata.type": "#Microsoft.Skills.Text.SplitSkill",
    "textSplitMode" : "pages", 
    "maximumPageLength": 1000,
    "pageOverlapLength": 100,
    "maximumPagesToTake": 1,
    "defaultLanguageCode": "en",
    "inputs": [
        {
            "name": "text",
            "source": "/document/content"
        },
        {
            "name": "languageCode",
            "source": "/document/language"
        }
    ],
    "outputs": [
        {
            "name": "textItems",
            "targetName": "mypages"
        }
    ]
}
  • 此外，页面重叠长度和最大页面数等参数可以更好地控制拆分过程，这对于数据分块和矢量化等场景特别有用。

示例输入：

{
    "values": [
        {
            "recordId": "1",
            "data": {
                "text": "This is the loan application for Joe Romero...",
                "languageCode": "en"
            }
        },
        {
            "recordId": "2",
            "data": {
                "text": "This is the second document...",
                "languageCode": "en"
            }
        }
    ]
}
  • 通过defaultLanguageCode参数提供语言支持，确保拆分准确，尤其是对于不同句子结构的语言。
  • 该技能接受文本输入以及可选的语言代码并输出一系列子字符串，以促进下游处理。

示例输出：

{
    "values": [
        {
            "recordId": "1",
            "data": {
                "textItems": [
                    "This is the loan...Here is the overlap part",
                    "Here is the overlap part...In the next section, we continue..."
                ]
            }
        },
        {
            "recordId": "2",
            "data": {
                "textItems": [
                    "This is the second document...Here is the overlap part...",
                    "Here is the overlap part...In the next section of the second doc..."
                ]
            }
        }
    ]
}
  • 文本拆分技能通过将冗长的文本分解为更易于管理的单元来增强文本处理工作流程，从而提高分析或翻译等后续任务的效率和准确性。

对于技能组您的数据：

注意：根据您发送的数据更改来源

{
  "@odata.context": "https://[your-search-service].search.windows.net/$metadata#skillsets/$entity",
  "@odata.etag": "\"0x8DC690CB8941711\"",
  "name": "terminal-skillset1",
  "description": "",
  "skills": [
    {
      "@odata.type": "#Microsoft.Skills.Text.SplitSkill",
      "textSplitMode": "pages",
      "maximumPageLength": 1000,
      "pageOverlapLength": 100,
      "maximumPagesToTake": 1,
      "defaultLanguageCode": "en",
      "inputs": [
        {
          "name": "text",
          "source": "/document/merged_content"
        },
        {
          "name": "languageCode",
          "source": "/document/language"
        }
      ],
      "outputs": [
        {
          "name": "textItems",
          "targetName": "mypages"
        }
      ]
    }
  ]
}

enter image description here

更改索引器中的技能组：

根据字段更改

sourceFieldName
和`targetFieldName


{
  "@odata.context": "https://mssearchser.search.windows.net/$metadata#indexers/$entity",
  "@odata.etag": "\"0x8DC690CB8941711\"",
  "name": "terminal-indexer1",
  "description": "",
  "dataSourceName": "terminal-data",
  "skillsetName": "terminal-skillset", // Reference your skillset here
  "targetIndexName": "azureblob-index",
  "disabled": null,
  "schedule": null,
  "parameters": {
    "batchSize": null,
    "maxFailedItems": 0,
    "maxFailedItemsPerBatch": 0,
    "base64EncodeKeys": null,
    "configuration": {
      "dataToExtract": "contentAndMetadata",
      "parsingMode": "default",
      "imageAction": "generateNormalizedImages"
    }
  },
  "fieldMappings": [
    {
      "sourceFieldName": "metadata_storage_path",
      "targetFieldName": "metadata_storage_path",
      "mappingFunction": {
        "name": "base64Encode",
        "parameters": null
      }
    }
  ],
  "outputFieldMappings": [
    {
      "sourceFieldName": "/document/merged_content/locations",
      "targetFieldName": "locations"
    },
    {
      "sourceFieldName": "/document/merged_content/keyphrases",
      "targetFieldName": "keyphrases"
    },
    {
      "sourceFieldName": "/document/language",
      "targetFieldName": "language"
    },
    {
      "sourceFieldName": "/document/merged_content",
      "targetFieldName": "merged_content"
    },
    {
      "sourceFieldName": "/document/normalized_images/*/text",
      "targetFieldName": "text"
    },
    {
      "sourceFieldName": "/document/normalized_images/*/layoutText",
      "targetFieldName": "layoutText"
    },
    {
      "sourceFieldName": "/document/mypages/*", // Reference the output field from the skillset
      "targetFieldName": "textItems" // Map to your desired field
    }
  ],
  "cache": null,
  "encryptionKey": null
}
最新问题
© www.soinside.com 2019 - 2024. All rights reserved.