DashVector quick start guide - DashVector: Central de Documentação do Alibaba Cloud

Saiba como criar uma coleção, inserir vetores e executar buscas por similaridade com o DashVector.

Pré-requisitos

Cluster criado. Criar um cluster
Chave de API obtida. Gerenciamento de chaves de API
Versão mais recente do SDK do DashVector instalada. Para mais informações, consulte Instale o SDK do DashVector.

Nota

Substitua YOUR_API_KEY e YOUR_CLUSTER_ENDPOINT pelos valores reais.
Localize o endpoint do cluster na página Cluster Detail no console do DashVector.

Etapa 1. Crie um cliente

Ignore esta etapa ao usar a API HTTP.

import dashvector

client = dashvector.Client(
    api_key='YOUR_API_KEY',
    endpoint='YOUR_CLUSTER_ENDPOINT'
)
assert client

import com.aliyun.dashvector.DashVectorClient;
import com.aliyun.dashvector.common.DashVectorException;

DashVectorClient client = new DashVectorClient("YOUR_API_KEY", "YOUR_CLUSTER_ENDPOINT");

Etapa 2. Crie uma coleção

Crie uma coleção chamada quickstart com quatro dimensões de vetor.

client.create(name='quickstart', dimension=4)

collection = client.get('quickstart')
assert collection

import com.aliyun.dashvector.models.responses.Response;
import com.aliyun.dashvector.DashVectorCollection;

Response<Void> response = client.create("quickstart", 4);
System.out.println(response);
DashVectorCollection collection = client.get("quickstart");

assert collection.isSuccess();

curl -XPOST \
  -H 'dashvector-auth-token: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "name": "quickstart", 
    "dimension": 4
  }' https://YOUR_CLUSTER_ENDPOINT/v1/collections

Nota

A métrica de distância padrão é Cosseno.
O tipo de dados vetoriais padrão é Float.

Etapa 3. Inserir Docs

from dashvector import Doc

# Use the dashvector.Doc object to insert a single Doc.
collection.insert(Doc(id='1', vector=[0.1, 0.2, 0.3, 0.4]))

# Use the dashvector.Doc object to insert two Docs at a time.
collection.insert(
    [
        Doc(id='2', vector=[0.2, 0.3, 0.4, 0.5], fields={'age': 20, 'name': 'zhangsan'}),
        Doc(id='3', vector=[0.3, 0.4, 0.5, 0.6], fields={'anykey': 'anyvalue'})    
    ]
)

import com.aliyun.dashvector.models.Vector;
import com.aliyun.dashvector.models.Doc;
import com.aliyun.dashvector.models.requests.InsertDocRequest;
import com.aliyun.dashvector.models.responses.Response;

import java.util.Arrays;
import java.util.HashMap;

Doc doc1 = Doc.builder()
    .id("1")
    .vector(
        Vector.builder()
            .value(Arrays.asList(0.1f, 0.2f, 0.3f, 0.4f))
            .build()
    ).build();

Doc doc2 = Doc.builder()
    .id("2")
    .vector(
        Vector.builder()
            .value(Arrays.asList(0.2f, 0.3f, 0.4f, 0.5f))
            .build()
    ).fields(new HashMap<String, Object>(){{
        put("age", 20);
        put("name", "zhangsan");
    }}).build();

Doc doc3 = Doc.builder()
    .id("3")
    .field("anykey", "anyvalue")
    .vector(
        Vector.builder()
            .value(Arrays.asList(0.3f, 0.4f, 0.5f, 0.6f))
            .build()
    ).build();

InsertDocRequest request = InsertDocRequest.builder()
    .docs(Arrays.asList(doc1, doc2, doc3))
    .build();

Response<Void> response = collection.insert(request);

# Insert three Docs.

curl -XPOST \
  -H 'dashvector-auth-token: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "docs": [
      {"id": "1", "vector": [0.1, 0.2, 0.3, 0.4]},
      {"id": "2", "vector": [0.2, 0.3, 0.4, 0.5], "fields": {"age": 20, "name": "zhangsan"}},
      {"id": "3", "vector": [0.3, 0.4, 0.5, 0.6], "fields": {"anykey": "anyvalue"}}
    ]
  }' https://YOUR_CLUSTER_ENDPOINT/v1/collections/quickstart/docs

Etapa 4. Executar uma busca por similaridade

rets = collection.query([0.1, 0.2, 0.3, 0.4], topk=2)

print(rets)

import com.aliyun.dashvector.models.Vector;
import com.aliyun.dashvector.models.Doc;
import com.aliyun.dashvector.models.requests.QueryDocRequest;
import com.aliyun.dashvector.models.responses.Response;

import java.util.Arrays;
import java.util.List;

Vector vector = Vector.builder().value(Arrays.asList(0.1f, 0.2f, 0.3f, 0.4f)).build();
      	
QueryDocRequest request = QueryDocRequest.builder()
    .vector(vector)
    .topk(2)
    .build();

Response<List<Doc>> response = collection.query(request);

curl -XPOST \
  -H 'dashvector-auth-token: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "vector": [0.1, 0.2, 0.3, 0.4],
    "topk": 2
  }' https://YOUR_CLUSTER_ENDPOINT/v1/collections/quickstart/query

Etapa 5. Exclua um Doc

# Delete a Doc.
collection.delete(ids=['1'])

import com.aliyun.dashvector.models.Doc;
import com.aliyun.dashvector.models.requests.DeleteDocRequest;
import com.aliyun.dashvector.models.responses.Response;

DeleteDocRequest request = DeleteDocRequest.builder()
    .id("1")
    .build();
      
Response<List<Doc>> response = collection.delete(request);

curl -XDELETE \
  -H 'dashvector-auth-token: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"ids": ["1"]}' \
  https://YOUR_CLUSTER_ENDPOINT/v1/collections/quickstart/docs

Etapa 6. Visualize estatísticas da coleção

stats = collection.stats()

print(stats)

import com.aliyun.dashvector.models.CollectionStats;
import com.aliyun.dashvector.models.responses.Response;

Response<CollectionStats> response = collection.stats();

curl -H 'dashvector-auth-token: YOUR_API_KEY' \
  https://YOUR_CLUSTER_ENDPOINT/v1/collections/quickstart/stats

Etapa 7. Exclua uma coleção

client.delete('quickstart')

import com.aliyun.dashvector.models.responses.Response;

Response<Void> response = client.delete("quickstart");

curl -XDELETE -H 'dashvector-auth-token: YOUR_API_KEY' \
  https://YOUR_CLUSTER_ENDPOINT/v1/collections/quickstart