翻译技能不写字段输出

Question

我一直无法将翻译后的内容字段输出到我的结果中。

这是查询的示例结果。我希望我的技能集能够根据定义的两项技能输出 6 个额外的字段。

{
    "@odata.context": "https://text-skill-test.search.windows.net/indexes('translate-english1')/$metadata#docs(*)",
    "value": [
        {
            "@search.score": 1,
            "index_id": "1",
            "metadata_content_type": null,
            "language": null,
            "title": "3 Things to Know About Release Notes",
            "content": "\r\n<p>Hey there Office Insiders!</p>\r\n"
        }
    ]
}

我的索引器：


{
  "@odata.context": "https://text-skill-test.search.windows.net/$metadata#indexers/$entity",
  "name": "indexer1613347856608",
  "description": null,
  "dataSourceName": "englishfolder",
  "skillsetName": "azureblob-skillset",
  "targetIndexName": "translate-english1",
  "disabled": null,
  "schedule": null,
  "parameters": {
    "batchSize": null,
    "maxFailedItems": 0,
    "maxFailedItemsPerBatch": 0,
    "base64EncodeKeys": null,
    "configuration": {
      "dataToExtract": "contentAndMetadata",
      "parsingMode": "json"
    }
  },
  "fieldMappings": [
    {
      "sourceFieldName": "metadata_storage_path",
      "targetFieldName": "index_id",
      "mappingFunction": {
        "name": "base64Encode",
        "parameters": null
      }
    }
  ],
  "outputFieldMappings": [
    {
      "sourceFieldName": "/document/title",
      "targetFieldName": "title"
    },
    {
      "sourceFieldName": "/document/content",
      "targetFieldName": "content"
    }
  ]
}

我的技能定义是这样的。我也试过使用下面的源字段并省略 /document 但它没有用。

{
  "@odata.context": "https://text-skill-test.search.windows.net/$metadata#skillsets/$entity",
  "@odata.etag": "\"0x8D8D1466CF19C8E\"",
  "name": "azureblob-skillset",
  "description": "Skillset created from the portal. skillsetName: azureblob-skillset; contentField: metadata_storage_content_type; enrichmentGranularity: document; knowledgeStoreStorageAccount: ;",
  "skills": [
    {
      "@odata.type": "#Microsoft.Skills.Text.TranslationSkill",
      "name": "#1",
      "description": null,
      "context": "/document",
      "defaultFromLanguageCode": null,
      "defaultToLanguageCode": "fr",
      "suggestedFrom": "en",
      "inputs": [
        {
          "name": "text",
          "source": "/document/content"
        }
      ],
      "outputs": [
        {
          "name": "translatedText",
          "targetName": "translatedContentText_fr"
        },
        {
          "name": "translatedFromLanguageCode",
          "targetName": "translatedContentFromLanguageCode_fr"
        },
        {
          "name": "translatedToLanguageCode",
          "targetName": "translatedContentToLanguageCode_fr"
        }
      ]
    },
    {
      "@odata.type": "#Microsoft.Skills.Text.TranslationSkill",
      "name": "#2",
      "description": null,
      "context": "/document",
      "defaultFromLanguageCode": null,
      "defaultToLanguageCode": "fr",
      "suggestedFrom": "en",
      "inputs": [
        {
          "name": "text",
          "source": "/document/title"
        }
      ],
      "outputs": [
        {
          "name": "translatedText",
          "targetName": "translatedTitle_fr"
        },
        {
          "name": "translatedFromLanguageCode",
          "targetName": "translatedTitleFromLanguageCode_fr"
        },
        {
          "name": "translatedToLanguageCode",
          "targetName": "translatedTitleToLanguageCode_fr"
        }
      ]
    }
  ],
  "cognitiveServices": null,
  "knowledgeStore": null,
  "encryptionKey": null
}

20 个成功的文档，没有错误或警告：

Answer 1

我还需要查看您的索引定义以查明修复方法。您的索引器有一个问题：

不正确的索引器输出字段映射。在输出字段映射中添加以下对象。 { "sourceFieldName": "/document/translatedContentText_fr", "targetFieldName": "你的法语文本索引字段名称", “映射功能”：空 }
您可能会遇到第二个问题，即索引定义中缺少该字段。要解决此问题，请将一个字段添加到 EDM.String 类型的索引，并在上述输出字段映射中使用该名称。确保该字段至少是可检索的。

翻译技能不写字段输出

Translation Skill not writing fields to output

azure-cognitive-search

azure-cognitive-services