运行向量搜索近似最近邻 (ANN) 和精确最近邻 (ENN) 查询

预过滤搜索数据

您可以使用过滤器预先筛选数据，以缩小语义搜索的范围，并确保只考虑相关向量进行比较。当使用 filter 选项对数据进行预过滤时，MongoDB 向量搜索仅对数据的子集合执行语义搜索，这可提高搜索结果的准确性。

预过滤可能过于限制，因为预过滤可能会排除与预过滤不完全匹配的数据，但在向量搜索过程中，该数据与您要考虑的查询在语义上相似。为了缓解这一问题，我们建议设置广泛的过滤器条件，以确保您的查询包含以下内容：

• 包含尽可能多的相关结果。

• 从结果中排除不相关数据。

• 返回结果中请求的文档数量。

帖子-过滤器搜索结果

If your index size isn't optimal for pre-filtering or if you set broad pre-filtering criteria, you can post-filter your vector search results to return only relevant data. To filter the results of your vector search, you can use any supported aggregation pipeline stage, such as the $match stage, after the $vectorSearch stage. To learn more, see Additional Performance Recommendations.

To select the fields to return in the results, use the $project stage unless you need all the fields in the results. We recommend excluding the vector field in the $project stage to improve query performance.

For example, you can use the $project stage to include the vectorSearchScore and then use the $match stage to return only documents above a certain score threshold.

过滤器注意事项

• MongoDB Vector Search supports the short form of $eq. In the short form, you don't need to specify $eq in the query.

  例如，考虑以下带有 $eq 的过滤器：

  "filter": { "_id": { "$eq": ObjectId("5a9427648b0beebeb69537a5") }

  这相当于以下过滤器，它使用 $eq 的简写形式：

  "filter": { "_id": ObjectId("5a9427648b0beebeb69537a5") }

• You can use the $and MQL operator to specify an array of filters in a single query.

  例如，考虑以下预过滤器，用于 genres 字段等于 Action 和 year 字段值为 1999、2000 或 2001 的文档：

  "filter": {
    "$and": [
      { "genres": "Action" },
      { "year": { "$in": [ 1999, 2000, 2001 ] } }
    ]
  }

• For advanced filtering capabilities such as fuzzy search, phrase matching, location filtering, and other analyzed text, use the vectorSearch operator in a $search stage.