[Milvus] Docker로 실행하여 Nodejs SDK Client 연결

Milvus를 선택한 이유

• 오픈소스
• Git star수가 가장 높음
• Docs가 깔끔함 (https://milvus.io/docs/index.md)
• vector index 종류가 많음
• 지원하는 언어가 많음

 

Requirement

Node.js v12+

Docker

 

Quick Start

이 가이드에서는 Node.js와 Milvus를 사용하여 간단한 애플리케이션을 설정하는 방법을 보여줍니다. 그 범위는 node.js 클라이언트를 설정하고 간단한 CRUD 작업을 수행하는 방법뿐입니다. 더 자세한 내용은 Milvus 공식 웹사이트를 참조하세요

 

Create the package.json file

directory 생성

mkdir myProject
cd myProject

 

새 프로젝트 초기화 하기

npm init -y

 

클라이언트를 종속성으로 설치

npm install @zilliz/milvus2-sdk-node

 

Start a milvus server

# Download the milvus standalone yaml file
wget https://github.com/milvus-io/milvus/releases/download/v2.2.8/milvus-standalone-docker-compose.yml -O docker-compose.yml

# start the milvus server
sudo docker-compose up -d

 

Connect to Milvus

app.js 파일을 만들고 다음 코드를 추가하여 Milvus node.js 클라이언트 사용

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

/**
 * Connect to Milvus 
*/
const address = 'localhost:19530';
const token = "root:Milvus"
const ssl = false;
const client = new MilvusClient({address, ssl, token});

 

 

예제 코드 작성하여 실행결과 확인

import { MilvusClient, DataType } from '@zilliz/milvus2-sdk-node';
/**
 * Connect to Milvus
 */
const address = 'localhost:19530';
const token = "root:Milvus"
const ssl = false;
const client = new MilvusClient({address, ssl, token});

/**
 * Create a collection
 */
// define schema
const collection_name = `hello_milvus`;
const dim = 128;
const schema = [
   {
      name: 'age',
      description: 'ID field',
      data_type: DataType.Int64,
      is_primary_key: true,
      autoID: true,
   },
   {
      name: 'vector',
      description: 'Vector field',
      data_type: DataType.FloatVector,
      dim: 8,
   },
   { name: 'height', description: 'int64 field', data_type: DataType.Int64 },
   {
      name: 'name',
      description: 'VarChar field',
      data_type: DataType.VarChar,
      max_length: 128,
   },
];

// Create the collection
await client.createCollection({
   collection_name,
   fields: schema,
});

/**
 * Prepare data
 */
const fields_data = [
   {
   vector: [
      0.11878310581111173, 0.9694947902934701, 0.16443679307243175,
      0.5484226189097237, 0.9839246709011924, 0.5178387104937776,
      0.8716926129208069, 0.5616972243831446,
   ],
   height: 20405,
   name: 'zlnmh',
   },
   {
   vector: [
      0.9992090731236536, 0.8248790611809487, 0.8660083940881405,
      0.09946359318481224, 0.6790698063908669, 0.5013786801063624,
      0.795311915725105, 0.9183033261617566,
   ],
   height: 93773,
   name: '5lr9y',
   },
   {
   vector: [
      0.8761291569818763, 0.07127366044153227, 0.775648976160332,
      0.5619757601304878, 0.6076543120476996, 0.8373907516027586,
      0.8556140171597648, 0.4043893119391049,
   ],
   height: 85122,
   name: 'nes0j',
   },
];

/**
 * Insert data into collection
 */
await client.insert({
   collection_name,
   fields_data,
});

/**
 * Create index
 */

// create index
await client.createIndex({
   // required
   collection_name,
   field_name: 'vector', // optional if you are using milvus v2.2.9+
   index_name: 'myindex', // optional
   index_type: 'HNSW', // optional if you are using milvus v2.2.9+
   params: { efConstruction: 10, M: 4 }, // optional if you are using milvus v2.2.9+
   metric_type: 'L2', // optional if you are using milvus v2.2.9+
});

/**
 * Load collection
 */
// load collection
await client.loadCollectionSync({
   collection_name,
});

/**
 * vector search
 */
// get the search vector
const searchVector = fields_data[0].vector;
// Perform a vector search on the collection
const res = await client.search({
   // required
   collection_name, // required, the collection name
   vector: searchVector, // required, vector used to compare other vectors in milvus
   // optionals
   filter: 'height > 0', // optional, filter
   params: { nprobe: 64 }, // optional, specify the search parameters
   limit: 10, // optional, specify the number of nearest neighbors to return
   metric_type: 'L2', // optional, metric to calculate similarity of two vectors
   output_fields: ['height', 'name'], // optional, specify the fields to return in the search results
});

 

실행 결과 res 확인

{ "status": { "error_code": "Success", "reason": "", "code": 0, "retriable": false, "detail": "" }, "results": [ { "score": 0, "id": "448230196146166133", "height": "20405", "name": "zlnmh" }, { "score": 1.7160398960113525, "id": "448230196146166134", "height": "93773", "name": "5lr9y" }, { "score": 2.0228352546691895, "id": "448230196146166135", "height": "85122", "name": "nes0j" } ] }

 

• searchVector 확인

0.11878310581111173,0.9694947902934701,0.16443679307243175,0.5484226189097237,0.9839246709011924,0.5178387104937776,0.8716926129208069,0.5616972243831446