Quick start - Vector Retrieval Service - Alibaba Cloud Documentation Center

This topic helps you quickly get started with DashVector.

Prerequisites

You have created a cluster. For more information, see Create a cluster.
You have created an API key. For more information, see API key management.
You have installed the DashVector SDK of the latest version. For more information, see Install a DashVector SDK.

Note

You must replace YOUR_API_KEY with your API key, and YOUR_CLUSTER_ENDPOINT with the endpoint of your cluster in the following examples.
You can view the endpoint of your cluster on the Cluster Detail page in the DashVector console.

Step 1. Create a client

You can skip this step if you use an HTTP API.

Python

import dashvector

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

Java

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


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

Step 2. Create a collection

Create a collection named quickstart with four vector dimensions.

Python

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

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

Java

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();

HTTP

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

Note

If you do not specify the distance measurement method, the default value Cosine is used.
If you do not specify the vector data type, the default value Float is used.

Step 3. Insert Docs

Python

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'})    
    ]
)

Java

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);

HTTP

# 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

Step 4. Perform a similarity search

Python

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

print(rets)

Java

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);

HTTP

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

Step 5. Delete a Doc

Python

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

Java

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);

HTTP

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

Step 6. View statistics of a collection

Python

stats = collection.stats()

print(stats)

Java

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


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

HTTP

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

Step7. Delete a collection

Python

client.delete('quickstart')

Java

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


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

HTTP

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