$rankFusion (aggregation)（聚合）

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(
   "search_index",
   {
      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(
   "vector_index",
   "vectorSearch",
   {
      "fields": [
         {
            "type": "vector",
            "path": "<FIELD_NAME>",
            "numDimensions": <NUMBER_OF_DIMENSIONS>,
            "similarity": "dotProduct"
         }
      ]
   }
);

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

db.embedded_movies.aggregate( [
   {
      $rankFusion: {
         input: {
            pipelines: {
               searchOne: [
                  {
                     "$vectorSearch": {
                        "index": "<INDEX_NAME>",
                        "path": "<FIELD_NAME>",
                        "queryVector": <QUERY_EMBEDDINGS>,
                        "numCandidates": 500,
                        "limit": 20
                     }
                  }
               ],
               searchTwo: [
                  {
                     "$search": {
                        "index": "<INDEX_NAME>",
                        "text": {
                           "query": "<QUERY_TERM>",
                           "path": "<FIELD_NAME>"
                        }
                     }
                  },
                  { "$limit": 20 }
               ],
            }
         }
      }
   },
   { $limit: 20 }
] )

This operation performs the following actions:此操作执行以下操作：

• 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 $rankFusion pipeline输出前20个文档，这些文档是$rankFusion管道排名前20的结果

The Node.js examples on this page use the sample_mflix database from the Atlas sample datasets. 本页上的Node.js示例使用Atlas示例数据集中的sample_mflix数据库。To learn how to create a free MongoDB Atlas cluster and load the sample datasets, see Get Started in the MongoDB Node.js driver documentation.要了解如何创建免费的MongoDB Atlas集群并加载示例数据集，请参阅MongoDB Node.js驱动程序文档中的入门。

To use the MongoDB Node.js driver to add a $rankFusion stage to an aggregation pipeline, use the $rankFusion operator in a pipeline object.要使用MongoDB Node.js驱动程序将$rankFusion阶段添加到聚合管道中，请在管道对象中使用$rankFusion运算符。

Before running the following example, you must create an Atlas Search index named default. Include the following code in your application to create a search index on the movies collection:在运行以下示例之前，您必须创建一个名为default的Atlas搜索索引。在应用程序中包含以下代码，以创建电影集合的搜索索引：

const index = {
  name: "default",
  definition: {
    mappings: { dynamic: true }
  }
}

const result = collection.createSearchIndex(index);

The following example creates a pipeline stage that executes two pipelines, searchPlot and searchGenre, that perform $search operations by using the default search index. 以下示例创建了一个管道阶段，该阶段执行两个管道searchPlot和searchGenre，这两个管道使用默认搜索索引执行$search操作。The $rankFusion stage then ranks the search results based on each $search pipeline's assigned weight and returns the ordered results. $rankFusion阶段然后根据每个$search管道的分配权重对搜索结果进行排名，并返回排序结果。The $addFields stage includes the scoreDetails field in the return documents. The example then runs the aggregation pipeline:$addFields阶段包括退货文档中的scoreDetails字段。然后，该示例运行聚合管道：

const pipeline = [
  {
    $rankFusion: { 
      input: {
        pipelines: {
          searchPlot: [
            {
              $search: {
                index: "default",
                text: { query: "space", path: "plot"}
              }
            }
          ],
          searchGenre: [
            {
              $search: {
                index: "default",
                text: { query: "adventure", path: "genres" }
              }
            }
          ] 
        }
      },
      combination: { weights: {searchPlot: 0.6, searchGenre: 0.4} },
      scoreDetails: true                  
    }
  },
  { $addFields: { scoreDetails: { $meta: "searchScoreDetails" } } }
];
          
const cursor = collection.aggregate(pipeline);  
return cursor;