パート 2: クライアントサイドの AI 有害コンテンツ検出を構築する

export const TOXICITY_THRESHOLD = 0.9 

import { env, pipeline } from '@xenova/transformers'; // Model name: 'Xenova/toxic-bert' // Our threshold is set to 0.9 import { TOXICITY_THRESHOLD, MODEL_NAME } from './config.js'; 

let classifier = null; (async function () {   // Signal to the main thread that model preparation has started   self.postMessage({ code: MESSAGE_CODE.PREPARING_MODEL, payload: null });   try {     // Prepare the model     classifier = await pipeline('text-classification', MODEL_NAME);     // Signal to the main thread that the model is ready     self.postMessage({ code: MESSAGE_CODE.MODEL_READY, payload: null });   } catch (error) {     console.error('[Worker] Error preparing model:', error);     self.postMessage({ code: MESSAGE_CODE.MODEL_ERROR, payload: null });   } })(); 

// Asynchronous function to classify user input // output: [{ label: 'toxic', score: 0.9243140482902527 }, // ... { label: 'insult', score: 0.96187334060668945 } // { label: 'obscene', score: 0.03452680632472038 }, ...etc] async function classify(text) {   if (!classifier) {     throw new Error("Can't run inference, the model is not ready yet");   }   let results = await classifier(text, { topk: null });   return results; } 

self.onmessage = async function (message) {   // User input   const textToClassify = message.data;   if (!classifier) {     throw new Error("Can't run inference, the model is not ready yet");   }   self.postMessage({ code: MESSAGE_CODE.GENERATING_RESPONSE, payload: null });    // Inference: run the classifier   let classificationResults = null;   try {     classificationResults = await classify(textToClassify);   } catch (error) {     console.error('[Worker] Error: ', error);     self.postMessage({       code: MESSAGE_CODE.INFERENCE_ERROR,     });     return;   }   const toxicityTypes = getToxicityTypes(classificationResults);   const toxicityAssessement = {     isToxic: toxicityTypes.length > 0,     toxicityTypeList: toxicityTypes.length > 0 ? toxicityTypes.join(', ') : '',   };   console.info('[Worker] Toxicity assessed: ', toxicityAssessement);   self.postMessage({     code: MESSAGE_CODE.RESPONSE_READY,     payload: toxicityAssessement,   }); }; 

// input: [{ label: 'toxic', score: 0.9243140482902527 }, ... // { label: 'insult', score: 0.96187334060668945 }, // { label: 'obscene', score: 0.03452680632472038 }, ...etc] // output: ['toxic', 'insult'] function getToxicityTypes(results) {   const toxicityAssessment = [];   for (let element of results) {     // If a label's score > our threshold, save the label     if (element.score > TOXICITY_THRESHOLD) {       toxicityAssessment.push(element.label);     }   }   return toxicityAssessment; }  self.onmessage = async function (message) {   // User input   const textToClassify = message.data;   if (!classifier) {     throw new Error("Can't run inference, the model is not ready yet");   }   self.postMessage({ code: MESSAGE_CODE.GENERATING_RESPONSE, payload: null });    // Inference: run the classifier   let classificationResults = null;   try {     classificationResults = await classify(textToClassify);   } catch (error) {     self.postMessage({       code: MESSAGE_CODE.INFERENCE_ERROR,     });     return;   }   const toxicityTypes = getToxicityTypes(classificationResults);   const toxicityAssessement = {     // If any toxicity label is listed, the comment is flagged as     // potentially toxic (isToxic true)     isToxic: toxicityTypes.length > 0,     toxicityTypeList: toxicityTypes.length > 0 ? toxicityTypes.join(', ') : '',   };   self.postMessage({     code: MESSAGE_CODE.RESPONSE_READY,     payload: toxicityAssessement,   }); };