Serverless Inference로 Weave 배우기

import * as weave from 'weave';
import OpenAI from 'openai';

// Weave를 초기화합니다. "[]"로 묶인 값을 실제 값으로 바꾸세요.
await weave.init("[YOUR-TEAM]/inference-quickstart")

// Serverless Inference를 가리키는 OpenAI 호환 클라이언트를 생성합니다
const client = new OpenAI({
    baseURL: 'https://api.inference.wandb.ai/v1',  // Serverless Inference 엔드포인트
    apiKey: process.env.WANDB_API_KEY || 'YOUR_WANDB_API_KEY', // API 키로 바꾸거나 WANDB_API_KEY 환경 변수를 설정하세요
});

// 트레이싱을 활성화하려면 함수를 weave.op로 래핑하세요
const askLlama = weave.op(async function askLlama(question: string): Promise<string> {
const response = await client.chat.completions.create({
    model: 'meta-llama/Llama-3.1-70B-Instruct',
    messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: question }
    ],
});
return response.choices[0].message.content || '';
});

// 함수를 호출합니다. Weave가 모든 과정을 자동으로 트레이스합니다
const result = await askLlama('What are the benefits of using W&B Weave for LLM development?');
console.log(result);

import * as weave from 'weave';
import OpenAI from 'openai';

// Weave를 초기화합니다. your-team/your-project를 실제 값으로 바꾸세요
await weave.init('[YOUR-TEAM]/inference-quickstart');

const client = new OpenAI({
baseURL: 'https://api.inference.wandb.ai/v1',
apiKey: process.env.WANDB_API_KEY || 'YOUR_WANDB_API_KEY',  // 실제 API 키로 바꾸거나 WANDB_API_KEY 환경 변수를 설정하세요
});

const extractKeyPoints = weave.op(async function extractKeyPoints(text: string): Promise<string[]> {
const response = await client.chat.completions.create({
    model: 'meta-llama/Llama-3.1-8B-Instruct',
    messages: [
    { role: 'system', content: 'Extract 3-5 key points from the text. Return each point on a new line.' },
    { role: 'user', content: text }
    ],
});
// 빈 줄을 제외한 응답을 반환합니다
const content = response.choices[0].message.content || '';
return content.split('\n').map(line => line.trim()).filter(line => line.length > 0);
});

const createSummary = weave.op(async function createSummary(keyPoints: string[]): Promise<string> {
const pointsText = keyPoints.map(point => `- ${point}`).join('\n');
const response = await client.chat.completions.create({
    model: 'meta-llama/Llama-3.1-8B-Instruct',
    messages: [
    { role: 'system', content: 'Create a one-sentence summary based on these key points.' },
    { role: 'user', content: `Key points:\n${pointsText}` }
    ],
});
return response.choices[0].message.content || '';
});

const summarizeText = weave.op(async function summarizeText(text: string): Promise<{key_points: string[], summary: string}> {
const keyPoints = await extractKeyPoints(text);
const summary = await createSummary(keyPoints);
return {
    key_points: keyPoints,
    summary: summary
};
});

// 샘플 텍스트로 사용해 보세요
const sampleText = `
The Apollo 11 mission was a historic spaceflight that landed the first humans on the Moon 
on July 20, 1969. Commander Neil Armstrong and lunar module pilot Buzz Aldrin descended 
to the lunar surface while Michael Collins remained in orbit. Armstrong became the first 
person to step onto the Moon, followed by Aldrin 19 minutes later. They spent about 
two and a quarter hours together outside the spacecraft, collecting samples and taking photographs.
`;

const result = await summarizeText(sampleText);
console.log('Key Points:', result.key_points);
console.log('\nSummary:', result.summary);

import * as weave from 'weave';
import OpenAI from 'openai';

// Weave를 초기화합니다. your-team/your-project로 바꾸세요
await weave.init("[YOUR-TEAM]/inference-quickstart")

const client = new OpenAI({
  baseURL: 'https://api.inference.wandb.ai/v1',
  apiKey: process.env.WANDB_API_KEY || 'YOUR_WANDB_API_KEY', // API 키로 바꾸거나 WANDB_API_KEY 환경 변수를 설정하세요
});

// weave.op를 사용해 모델 함수를 생성합니다(TypeScript에서는 weave.Model을 지원하지 않습니다)
function createModel(modelName: string) {
  return weave.op(async function predict(question: string): Promise<string> {
    const response = await client.chat.completions.create({
      model: modelName,
      messages: [
        { role: 'user', content: question }
      ],
    });
    return response.choices[0].message.content || '';
  });
}

// 각 모델의 인스턴스를 생성합니다
const llamaModel = createModel('meta-llama/Llama-3.1-8B-Instruct');
const deepseekModel = createModel('deepseek-ai/DeepSeek-V3.1');

// 응답을 비교합니다
const testQuestion = 'Explain quantum computing in one paragraph for a high school student.';

console.log('Llama 3.1 8B response:');
console.log(await llamaModel(testQuestion));
console.log('\n' + '='.repeat(50) + '\n');
console.log('DeepSeek V3 response:');
console.log(await deepseekModel(testQuestion));

import { EvaluationLogger } from 'weave';

// 간단한 데이터셋 생성
interface DatasetExample {
  question: string;
  expected?: string;
  expected_one_of?: string[];
}

const dataset: DatasetExample[] = [
  { question: 'What is 2 + 2?', expected: '4' },
  { question: 'What is the capital of France?', expected: 'Paris' },
  { question: 'Name a primary color', expected_one_of: ['red', 'blue', 'yellow'] },
];

// Scorer 정의
const accuracyScorer = weave.op(function accuracyScorer(args: {
  expected: string;
  output: string;
  expected_one_of?: string[];
}): { correct: boolean; score: number } {
  const outputClean = args.output.trim().toLowerCase();
  
  let isCorrect: boolean;
  if (args.expected_one_of) {
    isCorrect = args.expected_one_of.some(option => 
      outputClean.includes(option.toLowerCase())
    );
  } else {
    isCorrect = outputClean.includes(args.expected.toLowerCase());
  }
  
  return { correct: isCorrect, score: isCorrect ? 1.0 : 0.0 };
});

// Weave의 EvaluationLogger로 모델 평가
async function evaluateModel(
  model: (question: string) => Promise<string>,
  modelName: string,
  dataset: DatasetExample[]
): Promise<void> {
  // 토큰 사용량을 캡처하려면 반드시 모델을 호출하기 *전에* EvaluationLogger를 초기화하세요
  // Serverless Inference에서 비용을 추적하려면 이 순서가 특히 중요합니다
  // 모델 이름을 유효한 형식으로 변환 (영숫자가 아닌 문자는 밑줄로 대체)
  const safeModelName = modelName.replace(/\//g, '_').replace(/-/g, '_').replace(/\./g, '_');
  const evalLogger = new EvaluationLogger({
    name: 'inference_evaluation',
    model: { name: safeModelName },
    dataset: 'qa_dataset'
  });
  
  for (const example of dataset) {
    // 모델 예측 조회
    const output = await model(example.question);
    
    // 예측 로깅
    const predLogger = evalLogger.logPrediction(
      { question: example.question },
      output
    );
    
    // 출력 채점
    const score = await accuracyScorer({
      expected: example.expected || '',
      output: output,
      expected_one_of: example.expected_one_of
    });
    
    // 점수 로깅
    predLogger.logScore('accuracy', score.score);
    
    // 이 예측의 로깅 종료
    predLogger.finish();
  }
  
  // 요약 로깅 - Weave가 정확도 점수를 자동으로 집계합니다
  await evalLogger.logSummary();
  console.log(`Evaluation complete for ${modelName} (logged as: ${safeModelName}). View results in the weights and Biases UI.`);
}

// 여러 모델 비교 - Weave 평가 프레임워크의 핵심 기능
const modelsToCompare = [
  { model: llamaModel, name: 'meta-llama/Llama-3.1-8B-Instruct' },
  { model: deepseekModel, name: 'deepseek-ai/DeepSeek-V3.1' },
];

for (const { model, name } of modelsToCompare) {
  await evaluateModel(model, name, dataset);
}

// Weights and Biases UI의 Evals 탭으로 이동하여 모델별 결과를 비교하세요