登录 免费开始

配置多租户

你应该创建多少个集合？ 在大多数情况下，你只需使用一个带有基于载荷的分区的集合。这种方法称为多租户。对于大多数用户来说，它是高效的，但需要额外的配置。本文档将向你展示如何进行设置。

你应该何时创建多个集合？ 当你用户数量有限且需要隔离时。这种方法灵活，但可能更昂贵，因为创建大量集合可能会导致资源开销。此外，你需要确保它们之间互不影响，包括性能方面。

按载荷分区

当一个实例在多个用户之间共享时，你可能需要按用户对向量进行分区。这样做是为了让每个用户只能访问他们自己的向量，而看不到其他用户的向量。

PUT /collections/{collection_name}/points
{
    "points": [
        {
            "id": 1,
            "payload": {"group_id": "user_1"},
            "vector": [0.9, 0.1, 0.1]
        },
        {
            "id": 2,
            "payload": {"group_id": "user_1"},
            "vector": [0.1, 0.9, 0.1]
        },
        {
            "id": 3,
            "payload": {"group_id": "user_2"},
            "vector": [0.1, 0.1, 0.9]
        },
    ]
}

client.upsert(
    collection_name="{collection_name}",
    points=[
        models.PointStruct(
            id=1,
            payload={"group_id": "user_1"},
            vector=[0.9, 0.1, 0.1],
        ),
        models.PointStruct(
            id=2,
            payload={"group_id": "user_1"},
            vector=[0.1, 0.9, 0.1],
        ),
        models.PointStruct(
            id=3,
            payload={"group_id": "user_2"},
            vector=[0.1, 0.1, 0.9],
        ),
    ],
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.upsert("{collection_name}", {
  points: [
    {
      id: 1,
      payload: { group_id: "user_1" },
      vector: [0.9, 0.1, 0.1],
    },
    {
      id: 2,
      payload: { group_id: "user_1" },
      vector: [0.1, 0.9, 0.1],
    },
    {
      id: 3,
      payload: { group_id: "user_2" },
      vector: [0.1, 0.1, 0.9],
    },
  ],
});

use qdrant_client::qdrant::{PointStruct, UpsertPointsBuilder};
use qdrant_client::Qdrant;

let client = Qdrant::from_url("http://localhost:6334").build()?;

client
    .upsert_points(UpsertPointsBuilder::new(
        "{collection_name}",
        vec![
            PointStruct::new(1, vec![0.9, 0.1, 0.1], [("group_id", "user_1".into())]),
            PointStruct::new(2, vec![0.1, 0.9, 0.1], [("group_id", "user_1".into())]),
            PointStruct::new(3, vec![0.1, 0.1, 0.9], [("group_id", "user_2".into())]),
        ],
    ))
    .await?;

import java.util.List;
import java.util.Map;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.PointStruct;

QdrantClient client =
    new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client
    .upsertAsync(
        "{collection_name}",
        List.of(
            PointStruct.newBuilder()
                .setId(id(1))
                .setVectors(vectors(0.9f, 0.1f, 0.1f))
                .putAllPayload(Map.of("group_id", value("user_1")))
                .build(),
            PointStruct.newBuilder()
                .setId(id(2))
                .setVectors(vectors(0.1f, 0.9f, 0.1f))
                .putAllPayload(Map.of("group_id", value("user_1")))
                .build(),
            PointStruct.newBuilder()
                .setId(id(3))
                .setVectors(vectors(0.1f, 0.1f, 0.9f))
                .putAllPayload(Map.of("group_id", value("user_2")))
                .build()))
    .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.UpsertAsync(
	collectionName: "{collection_name}",
	points: new List<PointStruct>
	{
		new()
		{
			Id = 1,
			Vectors = new[] { 0.9f, 0.1f, 0.1f },
			Payload = { ["group_id"] = "user_1" }
		},
		new()
		{
			Id = 2,
			Vectors = new[] { 0.1f, 0.9f, 0.1f },
			Payload = { ["group_id"] = "user_1" }
		},
		new()
		{
			Id = 3,
			Vectors = new[] { 0.1f, 0.1f, 0.9f },
			Payload = { ["group_id"] = "user_2" }
		}
	}
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Upsert(context.Background(), &qdrant.UpsertPoints{
	CollectionName: "{collection_name}",
	Points: []*qdrant.PointStruct{
		{
			Id:      qdrant.NewIDNum(1),
			Vectors: qdrant.NewVectors(0.9, 0.1, 0.1),
			Payload: qdrant.NewValueMap(map[string]any{"group_id": "user_1"}),
		},
		{
			Id:      qdrant.NewIDNum(2),
			Vectors: qdrant.NewVectors(0.1, 0.9, 0.1),
			Payload: qdrant.NewValueMap(map[string]any{"group_id": "user_1"}),
		},
		{
			Id:      qdrant.NewIDNum(3),
			Vectors: qdrant.NewVectors(0.1, 0.1, 0.9),
			Payload: qdrant.NewValueMap(map[string]any{"group_id": "user_2"}),
		},
	},
})
  1. 使用过滤器以及 group_id 来过滤每个用户的向量。
POST /collections/{collection_name}/points/query
{
    "query": [0.1, 0.1, 0.9],
    "filter": {
        "must": [
            {
                "key": "group_id",
                "match": {
                    "value": "user_1"
                }
            }
        ]
    },
    "limit": 10
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.query_points(
    collection_name="{collection_name}",
    query=[0.1, 0.1, 0.9],
    query_filter=models.Filter(
        must=[
            models.FieldCondition(
                key="group_id",
                match=models.MatchValue(
                    value="user_1",
                ),
            )
        ]
    ),
    limit=10,
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.query("{collection_name}", {
    query: [0.1, 0.1, 0.9],
    filter: {
        must: [{ key: "group_id", match: { value: "user_1" } }],
    },
    limit: 10,
});

use qdrant_client::qdrant::{Condition, Filter, QueryPointsBuilder};
use qdrant_client::Qdrant;

let client = Qdrant::from_url("http://localhost:6334").build()?;

client
    .query(
        QueryPointsBuilder::new("{collection_name}")
            .query(vec![0.1, 0.1, 0.9])
            .limit(10)
            .filter(Filter::must([Condition::matches(
                "group_id",
                "user_1".to_string(),
            )])),
    )
    .await?;

import java.util.List;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Points.Filter;
import io.qdrant.client.grpc.Points.QueryPoints;

import static io.qdrant.client.QueryFactory.nearest;
import static io.qdrant.client.ConditionFactory.matchKeyword;

QdrantClient client =
    new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client.queryAsync(
        QueryPoints.newBuilder()
                .setCollectionName("{collection_name}")
                .setFilter(
                        Filter.newBuilder().addMust(matchKeyword("group_id", "user_1")).build())
                .setQuery(nearest(0.1f, 0.1f, 0.9f))
                .setLimit(10)
                .build())
        .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;
using static Qdrant.Client.Grpc.Conditions;

var client = new QdrantClient("localhost", 6334);

await client.QueryAsync(
	collectionName: "{collection_name}",
	query: new float[] { 0.1f, 0.1f, 0.9f },
	filter: MatchKeyword("group_id", "user_1"),
	limit: 10
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.Query(context.Background(), &qdrant.QueryPoints{
	CollectionName: "{collection_name}",
	Query:          qdrant.NewQuery(0.1, 0.1, 0.9),
	Filter: &qdrant.Filter{
		Must: []*qdrant.Condition{
			qdrant.NewMatch("group_id", "user_1"),
		},
	},
})

校准性能

在这种情况下，索引速度可能成为瓶颈，因为每个用户的向量都将被索引到同一个集合中。为避免此瓶颈，请考虑绕过整个集合的全局向量索引构建，而是仅为单个组构建索引。

通过采用此策略，Qdrant 将独立地为每个用户索引向量，从而显著加快过程。

要实现此方法，你应该

  1. 将 HNSW 配置中的 payload_m 设置为非零值，例如 16。
  2. 将 hnsw 配置中的 m 设置为 0。这将禁用为整个集合构建全局索引。
PUT /collections/{collection_name}
{
    "vectors": {
      "size": 768,
      "distance": "Cosine"
    },
    "hnsw_config": {
        "payload_m": 16,
        "m": 0
    }
}

from qdrant_client import QdrantClient, models

client = QdrantClient(url="http://localhost:6333")

client.create_collection(
    collection_name="{collection_name}",
    vectors_config=models.VectorParams(size=768, distance=models.Distance.COSINE),
    hnsw_config=models.HnswConfigDiff(
        payload_m=16,
        m=0,
    ),
)

import { QdrantClient } from "@qdrant/js-client-rest";

const client = new QdrantClient({ host: "localhost", port: 6333 });

client.createCollection("{collection_name}", {
  vectors: {
    size: 768,
    distance: "Cosine",
  },
  hnsw_config: {
    payload_m: 16,
    m: 0,
  },
});

use qdrant_client::qdrant::{
    CreateCollectionBuilder, Distance, HnswConfigDiffBuilder, VectorParamsBuilder,
};
use qdrant_client::Qdrant;

let client = Qdrant::from_url("http://localhost:6334").build()?;

client
    .create_collection(
        CreateCollectionBuilder::new("{collection_name}")
            .vectors_config(VectorParamsBuilder::new(768, Distance::Cosine))
            .hnsw_config(HnswConfigDiffBuilder::default().payload_m(16).m(0)),
    )
    .await?;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Collections.CreateCollection;
import io.qdrant.client.grpc.Collections.Distance;
import io.qdrant.client.grpc.Collections.HnswConfigDiff;
import io.qdrant.client.grpc.Collections.VectorParams;
import io.qdrant.client.grpc.Collections.VectorsConfig;

QdrantClient client =
    new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client
    .createCollectionAsync(
        CreateCollection.newBuilder()
            .setCollectionName("{collection_name}")
            .setVectorsConfig(
                VectorsConfig.newBuilder()
                    .setParams(
                        VectorParams.newBuilder()
                            .setSize(768)
                            .setDistance(Distance.Cosine)
                            .build())
                    .build())
            .setHnswConfig(HnswConfigDiff.newBuilder().setPayloadM(16).setM(0).build())
            .build())
    .get();

using Qdrant.Client;
using Qdrant.Client.Grpc;

var client = new QdrantClient("localhost", 6334);

await client.CreateCollectionAsync(
	collectionName: "{collection_name}",
	vectorsConfig: new VectorParams { Size = 768, Distance = Distance.Cosine },
	hnswConfig: new HnswConfigDiff { PayloadM = 16, M = 0 }
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.CreateCollection(context.Background(), &qdrant.CreateCollection{
	CollectionName: "{collection_name}",
	VectorsConfig: qdrant.NewVectorsConfig(&qdrant.VectorParams{
		Size:     768,
		Distance: qdrant.Distance_Cosine,
	}),
	HnswConfig: &qdrant.HnswConfigDiff{
		PayloadM: qdrant.PtrOf(uint64(16)),
		M:        qdrant.PtrOf(uint64(0)),
	},
})
  1. 为 group_id 字段创建关键字载荷索引。
PUT /collections/{collection_name}/index
{
    "field_name": "group_id",
    "field_schema": {
        "type": "keyword",
        "is_tenant": true
    }
}

client.create_payload_index(
    collection_name="{collection_name}",
    field_name="group_id",
    field_schema=models.KeywordIndexParams(
        type="keyword",
        is_tenant=True,
    ),
)

client.createPayloadIndex("{collection_name}", {
  field_name: "group_id",
  field_schema: {
    type: "keyword",
    is_tenant: true,
  },
});

use qdrant_client::qdrant::{
    CreateFieldIndexCollectionBuilder,
    KeywordIndexParamsBuilder,
    FieldType
};
use qdrant_client::{Qdrant, QdrantError};

let client = Qdrant::from_url("http://localhost:6334").build()?;

client.create_field_index(
        CreateFieldIndexCollectionBuilder::new(
            "{collection_name}",
            "group_id",
            FieldType::Keyword,
        ).field_index_params(
            KeywordIndexParamsBuilder::default()
                .is_tenant(true)
        )
    ).await?;

import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.grpc.Collections.PayloadIndexParams;
import io.qdrant.client.grpc.Collections.PayloadSchemaType;
import io.qdrant.client.grpc.Collections.KeywordIndexParams;

QdrantClient client =
    new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());

client
    .createPayloadIndexAsync(
        "{collection_name}",
        "group_id",
        PayloadSchemaType.Keyword,
        PayloadIndexParams.newBuilder()
            .setKeywordIndexParams(
                KeywordIndexParams.newBuilder()
                    .setIsTenant(true)
                    .build())
            .build(),
        null,
        null,
        null)
    .get();

using Qdrant.Client;

var client = new QdrantClient("localhost", 6334);

await client.CreatePayloadIndexAsync(
	collectionName: "{collection_name}",
	fieldName: "group_id",
	schemaType: PayloadSchemaType.Keyword,
	indexParams: new PayloadIndexParams
	{
		KeywordIndexParams = new KeywordIndexParams
		{
			IsTenant = true
		}
	}
);

import (
	"context"

	"github.com/qdrant/go-client/qdrant"
)

client, err := qdrant.NewClient(&qdrant.Config{
	Host: "localhost",
	Port: 6334,
})

client.CreateFieldIndex(context.Background(), &qdrant.CreateFieldIndexCollection{
	CollectionName: "{collection_name}",
	FieldName:      "group_id",
	FieldType:      qdrant.FieldType_FieldTypeKeyword.Enum(),
	FieldIndexParams: qdrant.NewPayloadIndexParams(
		&qdrant.KeywordIndexParams{
			IsTenant: qdrant.PtrOf(true),
		}),
})

is_tenant=true 参数是可选的，但指定它可以为存储提供关于集合将要使用的使用模式的附加信息。指定后，存储结构将以一种将同一租户的向量共置在一起的方式组织，这在某些情况下可以显著提高性能。

限制

这种方法的一个缺点是全局请求（不带 group_id 过滤器）会变慢，因为需要扫描所有组来找到最近邻居。

此页面有用吗？

感谢你的反馈！🙏

很抱歉得知此消息。😔 你可以在 GitHub 上编辑此页面，或创建一个 GitHub 问题。

本页内容