@thecodingwhale/cv-processor/dist/extractors/AITextExtractor.js

CV Processor to extract structured data from PDF resumes using TypeScript

"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    var desc = Object.getOwnPropertyDescriptor(m, k);
    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
      desc = { enumerable: true, get: function() { return m[k]; } };
    }
    Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
    Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
    o["default"] = v;
});
var __importStar = (this && this.__importStar) || (function () {
    var ownKeys = function(o) {
        ownKeys = Object.getOwnPropertyNames || function (o) {
            var ar = [];
            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
            return ar;
        };
        return ownKeys(o);
    };
    return function (mod) {
        if (mod && mod.__esModule) return mod;
        var result = {};
        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
        __setModuleDefault(result, mod);
        return result;
    };
})();
var __importDefault = (this && this.__importDefault) || function (mod) {
    return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.AITextExtractor = void 0;
const fs = __importStar(require("fs"));
const pdf_parse_1 = __importDefault(require("pdf-parse"));
const uuid_1 = require("uuid");
function replaceUUIDv4Placeholders(obj) {
    if (typeof obj === 'object' && obj !== null) {
        for (const key in obj) {
            if (typeof obj[key] === 'string' && obj[key] === 'UUIDv4') {
                obj[key] = (0, uuid_1.v4)();
            }
            else if (typeof obj[key] === 'object') {
                replaceUUIDv4Placeholders(obj[key]);
            }
        }
    }
    return obj;
}
/**
 * Class for extracting text from PDFs using AI models
 */
class AITextExtractor {
    /**
     * Initialize the AI Text Extractor
     */
    constructor(aiProvider) {
        this.tokenUsage = {
            promptTokens: 0,
            completionTokens: 0,
            totalTokens: 0,
            estimatedCost: 0,
        };
        this.aiProvider = aiProvider;
    }
    /**
     * Extract text from PDF file using AI
     */
    async extractTextFromPDF(pdfPath) {
        try {
            // Check if file exists
            if (!fs.existsSync(pdfPath)) {
                throw new Error(`PDF file does not exist: ${pdfPath}`);
            }
            const buffer = fs.readFileSync(pdfPath);
            const parsed = await (0, pdf_parse_1.default)(buffer);
            const text = this.cleanText(parsed.text);
            return text;
        }
        catch (error) {
            console.error(`Error in extractTextFromPDF: ${error}`);
            throw error;
        }
    }
    cleanText(text) {
        return text
            .replace(/PROFILE[\s\S]*?(?=\n\d{4})/i, '')
            .replace(/NOTES[\s\S]*$/i, '')
            .trim();
    }
    buildPrompt(text) {
        return `
      You are an AI data extractor for an actor's resume system. Only use these official categories:
      ["Commercial","Film","Television","Theatre","Print / Fashion","Training","Voice","Stunt","Corporate","MC/Presenting","Extras","Other"]
      Map synonyms logically. Use "Other" if uncertain.

      Schema:
      { "resume": [{ "category": "<Category>", "category_id": "<UUIDv4>", "credits": [{ "id": "<UUIDv4>", "year": "YYYY", "title": "<Title>", "role": "<Role>", "director": "<Director>", "attached_media": [] }] }], "resume_show_years": true }

      Ignore profile, skills, notes.

      Resume text:
      ${text}`;
    }
    /**
     * Add token usage from a response to the running total
     */
    addTokenUsage(usage) {
        this.tokenUsage.promptTokens += usage.promptTokens || 0;
        this.tokenUsage.completionTokens += usage.completionTokens || 0;
        this.tokenUsage.totalTokens += usage.totalTokens || 0;
        this.tokenUsage.estimatedCost =
            (this.tokenUsage.estimatedCost || 0) + (usage.estimatedCost || 0);
    }
    /**
     * Get token usage statistics
     */
    getTokenUsage() {
        return { ...this.tokenUsage };
    }
    /**
     * Reset token usage statistics
     */
    resetTokenUsage() {
        this.tokenUsage = {
            promptTokens: 0,
            completionTokens: 0,
            totalTokens: 0,
            estimatedCost: 0,
        };
    }
}
exports.AITextExtractor = AITextExtractor;