Azure中用SplitSkill拆分大文档：认知搜索+OpenAI集成遇阻

我正尝试优化Azure认知搜索与OpenAI集成的性能，从SharePoint索引大体积文档时遇到问题：需要拆分文档，让认知搜索仅返回OpenAI所需的片段而非完整文档。使用#Microsoft.Skills.Text.SplitSkill技能集时，无法将content拆分为名为pages的数组，最终目标是将内容拆分为多个保留原文件路径的文档。

当前索引结构 #

{    
    "name" : "{{index-name}}",    
    "fields": [        
        { "name": "id", "type": "Edm.String", "key": true, "searchable": false },        
        { "name": "metadata_spo_item_name", "type": "Edm.String", "key": false, "searchable": true, "filterable": false, "sortable": false, "facetable": false },        
        { "name": "metadata_spo_item_path", "type": "Edm.String", "key": false, "searchable": false, "filterable": false, "sortable": false, "facetable": false },        
        { "name": "metadata_spo_item_content_type", "type": "Edm.String", "key": false, "searchable": false, "filterable": true, "sortable": false, "facetable": true },        
        { "name": "metadata_spo_item_last_modified", "type": "Edm.DateTimeOffset", "key": false, "searchable": false, "filterable": false, "sortable": true, "facetable": false },        
        { "name": "metadata_spo_item_size", "type": "Edm.Int64", "key": false, "searchable": false, "filterable": false, "sortable": false, "facetable": false },        
        { "name": "content", "type": "Edm.String", "searchable": true, "filterable": false, "sortable": false, "facetable": false },        
        { "name": "pages", "type": "Collection(Edm.String)", "searchable": true, "filterable": false, "sortable": false, "facetable": false }    
    ]
}

当前技能集配置 #

{    
    "name": "{{skillset-name}}",    
    "description": "SharePoint skillset",    
    "skills": [        
        {            
            "@odata.type": "#Microsoft.Skills.Text.SplitSkill",            
            "name": "#1",            
            "description": null,            
            "context": "/document/id",            
            "defaultLanguageCode": "en",            
            "textSplitMode": "pages",            
            "maximumPageLength": 5000,            
            "inputs": [                
                {                    
                    "name": "text",                    
                    "source": "/document/content"                
                }            
            ],            
            "outputs": [                
                {                    
                    "name": "textItems",                    
                    "targetName": "pages"                
                }            
            ]        
        }    
    ]
}

问题排查与解决要点 #

• 修正上下文配置：当前SplitSkill的context设为/document/id，会导致拆分片段关联到文档ID而非整个文档对象，需改为/document，确保pages数组直接附加到文档根对象。
• 补充字段映射：检查索引器的字段映射规则，添加pages字段的映射，确保技能集输出正确同步到索引：

  {
      "sourceFieldName": "/document/pages",
      "targetFieldName": "pages",
      "mappingFunction": null
  }
  

• 验证拆分逻辑：若使用pages模式拆分，需确认文档包含标准分页符；若无分页符，可切换为sentences模式并调整maximumPageLength参数，确保拆分生效。
• 实现多文档拆分：若要将单个文档拆分为多个独立索引文档（共享同一文件路径），需结合ShaperSkill生成新文档对象，并配置索引器保留metadata_spo_item_path等元数据字段。

内容的提问来源于stack exchange，提问作者KevJo