Source-Web-23070-DataAnalysis/v2/scrapper/agent.js

import { readFileSync } from "fs";

export async function jsonToAgent(filePath) {

    let system_prompt;

    const res = readFileSync('./assets/agent.txt');
    if (res) {
        system_prompt = res.toString();
    } else {
        console.error("Failed to load system prompt");
        return;
    }

    console.log('processing file:', filePath);

    let content;
    const fileRes = readFileSync(filePath);
    if (fileRes) {
        content = fileRes.toString();
    } else {
        console.error("Failed to load JSON file");
        return;
    }

    // 使用 OpenAI Chat Completions API 搭配 Structured Outputs (json_schema)
    const response = await fetch('https://api.openai.com/v1/chat/completions', {
        method: 'POST',
        headers: {
            'Content-Type': 'application/json',
            'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`
        },
        body: JSON.stringify({
            model: "gpt-4o",
            messages: [
                { role: "system", content: system_prompt },
                { role: "user", content: content }
            ],
            store: false,
            response_format: {
                type: "json_schema",
                json_schema: {
                    name: "conversation_analysis",
                    strict: true,
                    schema: {
                        type: "object",
                        properties: {
                            output: {
                                type: "array",
                                description: "包含對話中所有留言的分析陣列",
                                items: {
                                    type: "object",
                                    properties: {
                                        summry: { 
                                            type: "string", 
                                            description: "簡短精煉的全域對話主題（20字以內）。注意：此欄位在所有 array items 中必須完全一致。" 
                                        },
                                        keywords: { 
                                            type: "array", 
                                            items: { type: "string" },
                                            description: "從留言中提取的關鍵字（事件、概念、情緒等）"
                                        },
                                        number: { 
                                            type: "integer", 
                                            description: "目前留言的序號" 
                                        },
                                        total: { 
                                            type: "integer", 
                                            description: "留言總數 M" 
                                        },
                                        content: { 
                                            type: "string", 
                                            description: "原始留言內容" 
                                        },
                                        metadata: { 
                                            type: "object", 
                                            description: "原始留言的後設資料",
                                            properties:{
                                                text: { type:'string'},
                                                published_on: { type:'integer'},
                                                like_count: { type:'integer'},
                                                reply_count: { type:'integer'},
                                                username: { type:'string'},
                                                id: { type:'string'},
                                                code: { type:'string'},
                                                parent_post_id: { type:'string'}
                                            },
                                             required: ["text", "published_on", "like_count", "reply_count", "username", "id", "code", "parent_post_id"],
                                            // 在 strict: true 模式下，這必須為 false
                                            additionalProperties: false,
                                        }
                                    },
                                    required: ["summry", "keywords", "number", "total", "content", "metadata"],
                                    additionalProperties: false
                                }
                            }
                        },
                        required: ["output"],
                        additionalProperties: false
                    }
                }
            },
            temperature: 0.1
        })
    });

    const data = await response.json();
    
    if (data.error) {
        console.error("API Error:", data.error);
        return null;
    }

    try {
        // 從 choices[0].message.content 中解析 AI 回傳的 JSON 字串
        const output = JSON.parse(data.choices[0].message.content);
        return output;
    } catch (err) {
        console.error("Failed to parse agent response as JSON:", data);
        return null;
    }
}