doc: Update the description about hybrid search in README.md (#34941)

Signed-off-by: AnthonyTsu1984 <115786031+AnthonyTsu1984@users.noreply.github.com>
This commit is contained in:
AnthonyTsu1984 2024-07-24 10:17:44 +08:00 committed by GitHub
parent 7464ae0f2b
commit c5da4fa094
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 2 deletions

View File

@ -40,7 +40,9 @@ Milvus was released under the [open-source Apache License 2.0](https://github.co
<details>
<summary><b>Hybrid search</b></summary>
In addition to vectors, Milvus supports data types such as Boolean, integers, floating-point numbers, and more. A collection in Milvus can hold multiple fields for accommodating different data features or properties. Milvus pairs scalar filtering with powerful vector similarity search to offer a modern, flexible platform for analyzing unstructured data. Check https://github.com/milvus-io/milvus/wiki/Hybrid-Search for examples and boolean expression rules.
Since Milvus 2.4, we introduced multi-vector support and a hybrid search framework, which means users can bring in several vector fields (up to 10) into a single collection. These vectors in different columns represent diverse facets of data, originating from different embedding models or undergoing distinct processing methods. The results of hybrid searches are integrated using reranking strategies, such as Reciprocal Rank Fusion (RRF) and Weighted Scoring.
This feature is particularly useful in comprehensive search scenarios, such as identifying the most similar person in a vector library based on various attributes like pictures, voice, fingerprints, etc. For details, refer to [Hybrid Search](https://milvus.io/docs/multi-vector-search.md) for more.
</details>
<details>

View File

@ -42,7 +42,9 @@ Milvus 基于 [Apache 2.0 License](https://github.com/milvus-io/milvus/blob/mast
<details>
<summary><b>混合查询</b></summary>
除了向量以外Milvus还支持布尔值、整型、浮点等数据类型。在 Milvus 中,一个 collection 可以包含多个字段来代表数据特征或属性。Milvus 还支持在向量相似度检索过程中进行标量字段过滤。
Milvus 2.4 引入了多向量支持和混合查询框架,用户可以将多个向量字段(最多 10 个)导入到单个 Collection 中。这些来自不同的嵌入模型或经过不同的处理方法处理的向量分别代表了不同的数据特征。混合搜索的结果使用 reranking 策略对各向量列的结果进行融合,如 Reciprocal Rank Fusion (RRF) 和 Weighted Scoring。
该特性尤其适用于综合搜索场景,如基于多种属性(如照片、声音、指纹等)识别向量库中最相似的人。有关更多信息,请参阅 [混合搜索](https://milvus.io/cn/docs/multi-vector-search.md)。
</details>
<details>