$scoreFusion (aggregation)（聚合）

Definition定义

$scoreFusion

$scoreFusion first executes all input pipelines independently and then de-duplicates and combines the input pipeline results into a final scored results set.首先独立执行所有输入管道，然后进行重复数据消除，并将输入管道结果组合成最终的评分结果集。

$scoreFusion outputs a ranked set of documents based on the scores of the documents and weights from their input pipelines. You can specify an arithmetic expression to compute the score based on the input scores from the pipeline stage. By default, it uses the average of the scores for the documents from the different input pipeline stages.根据文档的分数和输入管道的权重输出一组排名的文档。您可以指定一个算术表达式，根据流水线阶段的输入分数计算分数。默认情况下，它使用来自不同输入管道阶段的文档的平均分数。

Use $scoreFusion to search for documents in a single collection based on multiple criteria and retrieve a final scored result set that factors in all specified criteria.使用$scoreFusion根据多个条件在单个集合中搜索文档，并检索考虑所有指定条件的最终评分结果集。

Syntax语法

The stage has the following syntax:该阶段具有以下语法：

{ $scoreFusion: {
    input: {
      pipelines: {
            <input-pipeline-name>: <expression>,
            <input-pipeline-name>: <expression>,
            ...
      },
      normalization: "none|sigmoid|minMaxScaler"
    },
    combination: {
      weights: {
            <input-pipeline-name>: <numeric expression>,
            <input-pipeline-name>: <numeric expression>,
            ...
      },
      method: "avg|expression",
      expression: <expression>
    }
} }

Behavior行为

  scoreDetails: {
  value: 7.847857250621068,
  description: 'the value calculated by combining the scores (either normalized or raw) across input pipelines from which this document is output from:',
  normalization: 'sigmoid',
  combination: {
    method: 'custom expression',
    expression: "{ string: { $sum: [ { $multiply: [ '$$searchOne', 10 ] }, '$$searchTwo' ] } }"
  },
  details: [
    {
      inputPipelineName: 'searchOne',
      inputPipelineRawScore: 0.7987099885940552,
      weight: 1,
      value: 0.6896984675751023,
      details: []
    },
    {
      inputPipelineName: 'searchTwo',
      inputPipelineRawScore: 2.9629626274108887,
      weight: 1,
      value: 0.950872574870045,
      details: []
    }
  ]
}

Examples示例

This example uses a collection with embeddings and text fields. Create search and vectorSearch type indexes on the collection.此示例使用具有嵌入和文本字段的集合。在集合上创建search和vectorSearch类型索引。

The following index definition automatically indexes all the dynamically indexable fields in the collection for running $search queries against the indexed fields.以下索引定义自动为集合中的所有动态可索引字段建立索引，以便对索引字段运行$search查询。

search Index搜索索引

db.embedded_movies.createSearchIndex(
   "<INDEX_NAME>",
   {
      mappings: { dynamic: true }
   }
)

The following index definition indexes the field with the embeddings in the collection for running $vectorSearch queries against that field.以下索引定义使用集合中的嵌入对字段进行索引，以便对该字段运行$vectorSearch查询。

vectorSearch Index矢量搜索索引

db.embedded_movies.createSearchIndex(
   "<INDEX_NAME>",
   "vectorSearch",
   {
      "fields": [
         {
            "type": "vector",
            "path": "<FIELD_NAME>",
            "numDimensions": <NUMBER_OF_DIMENSIONS>,
            "similarity": "dotProduct"
         }
      ]
   }
);

The following aggregation pipeline uses $scoreFusion with the following input pipelines:以下聚合管道使用$scoreFusion和以下输入管道：

db.embedded_movies.aggregate( [
   {
      $scoreFusion: {
         input: {
            pipelines: {
               searchOne: [
                  {
                     "$vectorSearch": {
                        "index": "<INDEX_NAME>",
                        "path": "<FIELD_NAME>",
                        "queryVector": <QUERY_EMBEDDINGS>,
                        "numCandidates": <NUMBER_OF_NEAREST_NEIGHBORS_TO_CONSIDER>,
                        "limit": <NUBMER_OF_DOCUMENTS_TO_RETURN>
                     }
                  }
               ],
               searchTwo: [
                  {
                     "$search": {
                        "index": "<INDEX_NAME>",
                        "text": {
                           "query": "<QUERY_TERM>",
                           "path": "<FIELD_NAME>"
                        }
                     }
                  },
               ]
            },
            normalization: "sigmoid"
         },
         combination: {
            method: "expression",
            expression: {
               $sum: [
                 {$multiply: [ "$$searchOne", 10]}, "$$searchTwo"
               ]
            }
         },
         "scoreDetails": true
      }
   },
   {
      "$project": {
         _id: 1,
         title: 1,
         plot: 1,
         scoreDetails: {"$meta": "scoreDetails"}
      }
   },
   { $limit: 20 }
] )

This pipeline performs the following actions:此管道执行以下操作：

• Executes the input pipelines执行input管道
• Combines the returned results合并返回的结果
• Outputs the first 20 documents which are the top 20 ranked results of the $scoreFusion pipeline输出前20个文档，这些文档是$scoreFusion管道排名前20的结果