如何执行混合搜索

什么是倒数排名融合？

倒数排名融合是一种技术，通过执行以下操作，将不同搜索方法的结果合并为一个结果集：

1. 计算结果中各个文档的倒数排名。

   对于每个搜索结果中每个排名的文档，首先将该文档的排名 (r) 与一个常数 60 相加，以平滑分数 (rank_constant)，然后将 1 除以 r 与 rank_constant 之和，得出该文档在搜索结果中的倒数排名。您无法设置 rank_constant 的值，默认值为 60。

   reciprocal_rank = 1 / ( r + rank_constant )

   对于每种搜索方法，应用不同的权重 （w） 以使该搜索方法占更大重要性。对于每个文档，加权倒数排名的计算方法是将权重乘以文档的倒数排名。

   weighted_reciprocal_rank = w x reciprocal_rank

2. 将结果中文档的派生排名分数和加权分数相结合。

   对于所有搜索结果中的每个文档，将计算出的倒数排名相加，获得文档的单个分数。

3. 按结果中文档的综合得分对结果进行排序。

   根据结果中的综合得分对结果中的文档进行排序，以获得结果中文档的单一综合排名列表。

关于不同的混合搜索应用场景

You can leverage MongoDB Vector Search to perform several types of hybrid search. Specifically, MongoDB Vector Search supports the following use cases:

• Full-text and vector search in a single query: You can combine results from different search methods, such as a semantic and a full-text search. You can use the $vectorSearch for the semantic search and the $search for the full-text search results and combine the results by using the reciprocal rank fusion technique. To learn more, see the Perform Hybrid Search with MongoDB Vector Search and MongoDB Search tutorial, which demonstrates how to perform a semantic search and full-text search against the sample_mflix.embedded_movies namespace and retrieve combined ranked results by using reciprocal rank fusion.

  Alternatively, for a more granular hybrid search where the score matters in addition to the relative ordering of results, you can use the $scoreFusion pipeline stage. To learn more, see the Perform Hybrid Search with MongoDB Vector Search and MongoDB Search tutorial, which demonstrates how to perform a semantic search and full-text search against the sample_mflix.embedded_movies namespace and retrieve input pipeline results into a final scored results set.

  While $rankFusion ranks documents based on their positions (relative ranks) in input pipelines using the Reciprocal Rank Fusion algorithm, $scoreFusion ranks documents based on scores assigned by the input pipelines, using mathematical expressions for combining the results.

  In $rankFusion, rankings are influenced by pipeline weights. In $scoreFusion, weights control the contribution of each pipeline's scores to the final result.

• 在单个 MongoDB $rankFusion 管道中进行多个向量搜索查询：MongoDB 管道支持多个子管道，这些子管道包含针对同一集合执行的向量搜索查询，并使用倒数排名融合技术合并结果。如何组合多个 $vectorSearch 查询教程演示了以下类型的向量搜索：

  • 对您的数据集进行全面搜索，以在同一查询中查找语义相似的术语。

  • 在数据集中搜索多个字段，以确定哪些字段为查询返回最佳结果。

  • 使用不同嵌入模型生成的嵌入向量进行搜索，以确定不同模型在语义解释上的差异。

Considerations

When using the $rankFusion or $scoreFusion pipeline stage for hybrid search, consider the following.

限制

The following limitations apply to hybrid search using $rankFusion and $scoreFusion:

• $rankFusion is only supported on MongoDB 8.0.14 (including latest Rapid Release).

• $rankFusion and $scoreFusion sub-pipelines can contain only the following stages:

  • $search

  • $vectorSearch

  • $match

  • $sort

  • $geoNear

• $rankFusion and $scoreFusion preserve a traceable link back to the original input document for each sub-pipeline. Therefore, it doesn't support the following:

  • $project 阶段

  • storedSource 字段

• $rankFusion and $scoreFusion sub-pipelines run serially, not in parallel.

• $rankFusion and $scoreFusion don't support pagination.

• rankFusion can be run on Views only on clusters running MongoDB 8.0 or higher. You can't run rankFusion within a view definition or on a time series collection.

先决条件

要试用这些教程，必须具备以下条件:

• An Atlas cluster with MongoDB version v8.0 or later.

• sample_mflix 数据库已加载到 Atlas 集群。

• mongosh 在您的 Atlas 集群上尝试这些查询。

  注意

  您还可以通过使用 Atlas CLI 创建的本地 Atlas 部署来尝试这些混合搜索用例。要了解详情，请参阅创建本地 Atlas 部署。