milvus-logo
LFAI
首页
  • 用户指南

分组搜索

分组搜索允许 Milvus 根据指定字段的值对搜索结果进行分组,以便在更高层次上汇总数据。例如,您可以使用基本的 ANN 搜索来查找与手头的图书相似的图书,但也可以使用分组搜索来查找可能涉及该图书所讨论主题的图书类别。本主题将介绍如何使用分组搜索以及主要注意事项。

概述

当搜索结果中的实体在标量字段中共享相同值时,这表明它们在特定属性上相似,这可能会对搜索结果产生负面影响。

假设一个 Collections 存储了多个文档(用docId 表示)。在将文档转换成向量时,为了尽可能多地保留语义信息,每份文档都会被分割成较小的、易于管理的段落(或),并作为单独的实体存储。即使文档被分割成较小的段落,用户通常仍有兴趣识别哪些文档与他们的需求最相关。

ANN Search ANN 搜索

在对这样的 Collections 执行近似近邻 (ANN) 搜索时,搜索结果可能会包括同一文档中的多个段落,有可能导致其他文档被忽略,这可能与预期用例不符。

Grouping Search 分组搜索

为了提高搜索结果的多样性,可以在搜索请求中添加group_by_field 参数来启用分组搜索。如图所示,您可以将group_by_field 设置为docId 。收到此请求后,Milvus 将

  • 根据提供的查询向量执行 ANN 搜索,找到与查询最相似的所有实体。

  • 按指定的group_by_field 对搜索结果进行分组,如docId

  • 根据limit 参数的定义,返回每个组的顶部结果,并从每个组中选出最相似的实体。

默认情况下,分组搜索每个组只返回一个实体。如果要增加每个组返回结果的数量,可以使用group_sizestrict_group_size 参数进行控制。

本节提供示例代码,演示如何使用分组搜索。以下示例假定 Collections 包括id,vector,chunkdocId 字段。

[
        {"id": 0, "vector": [0.3580376395471989, -0.6023495712049978, 0.18414012509913835, -0.26286205330961354, 0.9029438446296592], "chunk": "pink_8682", "docId": 1},
        {"id": 1, "vector": [0.19886812562848388, 0.06023560599112088, 0.6976963061752597, 0.2614474506242501, 0.838729485096104], "chunk": "red_7025", "docId": 5},
        {"id": 2, "vector": [0.43742130801983836, -0.5597502546264526, 0.6457887650909682, 0.7894058910881185, 0.20785793220625592], "chunk": "orange_6781", "docId": 2},
        {"id": 3, "vector": [0.3172005263489739, 0.9719044792798428, -0.36981146090600725, -0.4860894583077995, 0.95791889146345], "chunk": "pink_9298", "docId": 3},
        {"id": 4, "vector": [0.4452349528804562, -0.8757026943054742, 0.8220779437047674, 0.46406290649483184, 0.30337481143159106], "chunk": "red_4794", "docId": 3},
        {"id": 5, "vector": [0.985825131989184, -0.8144651566660419, 0.6299267002202009, 0.1206906911183383, -0.1446277761879955], "chunk": "yellow_4222", "docId": 4},
        {"id": 6, "vector": [0.8371977790571115, -0.015764369584852833, -0.31062937026679327, -0.562666951622192, -0.8984947637863987], "chunk": "red_9392", "docId": 1},
        {"id": 7, "vector": [-0.33445148015177995, -0.2567135004164067, 0.8987539745369246, 0.9402995886420709, 0.5378064918413052], "chunk": "grey_8510", "docId": 2},
        {"id": 8, "vector": [0.39524717779832685, 0.4000257286739164, -0.5890507376891594, -0.8650502298996872, -0.6140360785406336], "chunk": "white_9381", "docId": 5},
        {"id": 9, "vector": [0.5718280481994695, 0.24070317428066512, -0.3737913482606834, -0.06726932177492717, -0.6980531615588608], "chunk": "purple_4976", "docId": 3},
]


在搜索请求中,将group_by_fieldoutput_fields 都设置为docId 。Milvus 将根据指定字段对结果进行分组,并从每个分组中返回最相似的实体,包括每个返回实体的docId 值。

from pymilvus import MilvusClient

client = MilvusClient(
    uri="http://localhost:19530",
    token="root:Milvus"
)

query_vectors = [
    [0.14529211512077012, 0.9147257273453546, 0.7965055218724449, 0.7009258593102812, 0.5605206522382088]]

# Group search results
res = client.search(
    collection_name="group_search_collection",
    data=query_vectors,
    limit=3,
    group_by_field="docId",
    output_fields=["docId"]
)

# Retrieve the values in the `docId` column
doc_ids = [result['entity']['docId'] for result in res[0]]

import io.milvus.v2.client.ConnectConfig;
import io.milvus.v2.client.MilvusClientV2;
import io.milvus.v2.service.vector.request.SearchReq
import io.milvus.v2.service.vector.request.data.FloatVec;
import io.milvus.v2.service.vector.response.SearchResp

MilvusClientV2 client = new MilvusClientV2(ConnectConfig.builder()
        .uri("http://localhost:19530")
        .token("root:Milvus")
        .build());

FloatVec queryVector = new FloatVec(new float[]{0.14529211512077012f, 0.9147257273453546f, 0.7965055218724449f, 0.7009258593102812f, 0.5605206522382088f});
SearchReq searchReq = SearchReq.builder()
        .collectionName("group_search_collection")
        .data(Collections.singletonList(queryVector))
        .topK(3)
        .groupByFieldName("docId")
        .outputFields(Collections.singletonList("docId"))
        .build();

SearchResp searchResp = client.search(searchReq);

List<List<SearchResp.SearchResult>> searchResults = searchResp.getSearchResults();
for (List<SearchResp.SearchResult> results : searchResults) {
    System.out.println("TopK results:");
    for (SearchResp.SearchResult result : results) {
        System.out.println(result);
    }
}

// Output
// TopK results:
// SearchResp.SearchResult(entity={docId=5}, score=0.74767184, id=1)
// SearchResp.SearchResult(entity={docId=2}, score=0.6254269, id=7)
// SearchResp.SearchResult(entity={docId=3}, score=0.3611898, id=3)

// nolint
func ExampleClient_Search_grouping() {
    ctx, cancel := context.WithCancel(context.Background())
    defer cancel()

    milvusAddr := "127.0.0.1:19530"
    token := "root:Milvus"

    cli, err := client.New(ctx, &client.ClientConfig{
        Address: milvusAddr,
        APIKey:  token,
    })
    if err != nil {
        log.Fatal("failed to connect to milvus server: ", err.Error())
    }

    defer cli.Close(ctx)

    queryVector := []float32{0.3580376395471989, -0.6023495712049978, 0.18414012509913835, -0.26286205330961354, 0.9029438446296592}

    resultSets, err := cli.Search(ctx, client.NewSearchOption(
        "my_collection", // collectionName
        3,               // limit
        []entity.Vector{entity.FloatVector(queryVector)},
    ).WithGroupByField("docId"))
    if err != nil {
        log.Fatal("failed to perform basic ANN search collection: ", err.Error())
    }

    for _, resultSet := range resultSets {
        log.Println("IDs: ", resultSet.IDs)
        log.Println("Scores: ", resultSet.Scores)
    }
    // Output:
    // IDs:
    // Scores:
}

import { MilvusClient, DataType } from "@zilliz/milvus2-sdk-node";

const address = "http://localhost:19530";
const token = "root:Milvus";
const client = new MilvusClient({address, token});

var query_vector = [0.3580376395471989, -0.6023495712049978, 0.18414012509913835, -0.26286205330961354, 0.9029438446296592]

res = await client.search({
    collection_name: "my_collection",
    data: [query_vector],
    limit: 3,
    // highlight-start
    group_by_field: "docId"
    // highlight-end
})

// Retrieve the values in the `docId` column
var docIds = res.results.map(result => result.entity.docId)

export CLUSTER_ENDPOINT="http://localhost:19530"
export TOKEN="root:Milvus"

curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/search" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
    "collectionName": "group_search_collection",
    "data": [
        [0.3580376395471989, -0.6023495712049978, 0.18414012509913835, -0.26286205330961354, 0.9029438446296592]
    ],
    "annsField": "vector",
    "limit": 3,
    "groupingField": "docId",
    "outputFields": ["docId"]
}'

在上面的请求中,limit=3 表示系统将从三个组中返回搜索结果,每个组都包含与查询向量最相似的单个实体。

配置组大小

默认情况下,分组搜索每个组只返回一个实体。如果希望每组有多个结果,请调整group_sizestrict_group_size 参数。

# Group search results

res = client.search(
    collection_name="group_search_collection", 
    data=query_vectors, # Query vector
    limit=5, # Top K results to return
    group_by_field="docId", # Group by docId
    group_size=2, # Return 2 entities per group
    strict_group_size=True, # Ensure each group has 2 entities
    output_fields=["docId"]
)

FloatVec queryVector = new FloatVec(new float[]{0.14529211512077012f, 0.9147257273453546f, 0.7965055218724449f, 0.7009258593102812f, 0.5605206522382088f});
SearchReq searchReq = SearchReq.builder()
        .collectionName("group_search_collection")
        .data(Collections.singletonList(queryVector))
        .topK(5)
        .groupByFieldName("docId")
        .groupSize(2)
        .strictGroupSize(true)
        .outputFields(Collections.singletonList("docId"))
        .build();

SearchResp searchResp = client.search(searchReq);

List<List<SearchResp.SearchResult>> searchResults = searchResp.getSearchResults();
for (List<SearchResp.SearchResult> results : searchResults) {
    System.out.println("TopK results:");
    for (SearchResp.SearchResult result : results) {
        System.out.println(result);
    }
}

// Output
// TopK results:
// SearchResp.SearchResult(entity={docId=5}, score=0.74767184, id=1)
// SearchResp.SearchResult(entity={docId=5}, score=-0.49148706, id=8)
// SearchResp.SearchResult(entity={docId=2}, score=0.6254269, id=7)
// SearchResp.SearchResult(entity={docId=2}, score=0.38515577, id=2)
// SearchResp.SearchResult(entity={docId=3}, score=0.3611898, id=3)
// SearchResp.SearchResult(entity={docId=3}, score=0.19556211, id=4)

import { MilvusClient, DataType } from "@zilliz/milvus2-sdk-node";

const address = "http://localhost:19530";
const token = "root:Milvus";
const client = new MilvusClient({address, token});

var query_vector = [0.3580376395471989, -0.6023495712049978, 0.18414012509913835, -0.26286205330961354, 0.9029438446296592]

res = await client.search({
    collection_name: "my_collection",
    data: [query_vector],
    limit: 3,
    group_by_field: "docId",
    // highlight-start
    group_size: 2,
    strict_group_size: true
    // highlight-end
})

// Retrieve the values in the `docId` column
var docIds = res.results.map(result => result.entity.docId)

curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/search" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
    "collectionName": "group_search_collection",
    "data": [
        [0.3580376395471989, -0.6023495712049978, 0.18414012509913835, -0.26286205330961354, 0.9029438446296592]
    ],
    "annsField": "vector",
    "limit": 5,
    "groupingField": "docId",
    "groupSize":2,
    "strictGroupSize":true,
    "outputFields": ["docId"]
}'

在上面的示例中

  • group_size:指定每个组要返回的实体数量。例如,设置group_size=2 意味着每个组(或每个docId )最好返回两个最相似的段落(或)。如果未设置group_size ,系统将默认为每组返回一个结果。

  • strict_group_size:这个布尔参数控制着系统是否应严格执行group_size 设置的计数。当strict_group_size=True 时,系统将尝试在每个组中包含group_size 所指定的实体的确切数量(例如两个段落),除非该组中没有足够的数据。默认情况下(strict_group_size=False ),系统会优先满足limit 参数指定的组数,而不是确保每个组都包含group_size 实体。在数据分布不均衡的情况下,这种方法通常更有效。

有关其他参数的详细信息,请参阅search()

注意事项

  • 组的数量limit 参数控制返回搜索结果的组的数量,而不是每个组中实体的具体数量。设置适当的limit 有助于控制搜索多样性和查询性能。如果数据分布密集或需要考虑性能问题,减少limit 可以降低计算成本。

  • 每组实体group_size 参数控制每个组返回的实体数量。根据使用情况调整group_size 可以增加搜索结果的丰富性。但是,如果数据分布不均,某些组返回的实体数量可能少于group_size 的指定数量,尤其是在数据有限的情况下。

  • 严格的组大小:当strict_group_size=True 时,系统将尝试为每个组返回指定数量的实体 (group_size),除非该组中没有足够的数据。此设置可确保每个组的实体数一致,但在数据分布不均或资源有限的情况下,可能会导致性能下降。如果不需要严格的实体数,设置strict_group_size=False 可以提高查询速度。

翻译自DeepL

想要更快、更简单、更好用的 Milvus SaaS服务 ?

Zilliz Cloud是基于Milvus的全托管向量数据库,拥有更高性能,更易扩展,以及卓越性价比

免费试用 Zilliz Cloud
反馈

此页对您是否有帮助?