app.py

import pandas as pd
import tempfile
import json
import gradio as gr
from resume_extractor import ResumeExtractor
from job_description_extractor import JobDescriptionExtractor
from model_trainer import ModelTrainer
from comparison_utils import (
    compare_with_chatgpt_job_title,
    compare_with_chatgpt_education,
    compare_with_chatgpt_location,
    compare_age_range_with_description
)
from synthetic_data import create_synthetic_data

def main(resume_text, job_description):
    openai_api_key = 'sk-proj-bC6H6QrP6DUqHkn5vOkYT3BlbkFJsSyvL4Bc9c3UEbHrsPMj'
    ner_model_name_or_path = "NLPclass/Named-entity-recognition"
    skill_model_name_or_path = "GalalEwida/lm-ner-skills-recognition"

    resume_extractor = ResumeExtractor(ner_model_name_or_path, openai_api_key)
    job_description_extractor = JobDescriptionExtractor(openai_api_key)

    full_name, loc, age, skills, education_resume, title_job_resume = resume_extractor.extract_resume_info(resume_text, skill_model_name_or_path)
    job_skills, education_job, title_job, location, age_DS = job_description_extractor.extract_job_info(job_description, skill_model_name_or_path)

    education_match = compare_with_chatgpt_education(education_resume, education_job, openai_api_key)
    title_job_match = compare_with_chatgpt_job_title(title_job_resume, title_job, openai_api_key)
    title_loc_match = compare_with_chatgpt_location(loc, location, openai_api_key)
    title_age_match = compare_age_range_with_description(age, age_DS, openai_api_key)

    synthetic_data = create_synthetic_data(job_skills, education_job, title_job, location, age_DS)
    synthetic_data.to_csv('synthetic_data.csv')
    model_trainer = ModelTrainer(synthetic_data)
    best_model = model_trainer.train_models()

    input_data = {skill: 1 if skill in skills else 0 for skill in job_skills}
    input_data[education_job] = education_match
    input_data[title_job] = title_job_match
    input_data[location] = title_loc_match
    input_data[age_DS] = title_age_match

    input_df = pd.DataFrame([input_data])
    input_df.to_csv('input_df.csv')
    predicted_target = best_model.predict(input_df)

    return {
        "full_name": full_name,
        "location": loc,
        "age": age,
        "age_DS": age_DS,
        "skills": skills,
        "education_resume": education_resume,
        "title_job_resume": title_job_resume,
        "job_skills": job_skills,
        "education_job": education_job,
        "title_job": title_job,
        "location_job": location,
        "predicted_target": predicted_target[0]
    }

def process_text(resume_text, job_description_text):
    try:
        output = main(resume_text, job_description_text)
        
        # ذخیره خروجی JSON در یک فایل موقت
        with tempfile.NamedTemporaryFile(delete=False, suffix=".json", mode='w', encoding='utf-8') as tmp_file:
            json.dump(output, tmp_file, ensure_ascii=False, indent=4)
            return tmp_file.name
    except Exception as e:
        # ایجاد یک فایل متنی موقت برای پیام خطا
        with tempfile.NamedTemporaryFile(delete=False, suffix=".txt", mode='w', encoding='utf-8') as tmp_file:
            tmp_file.write(f"Error: {str(e)}")
            return tmp_file.name

iface = gr.Interface(
    fn=process_text,
    inputs=[gr.Textbox(lines=10, placeholder="لطفاً رزومه خود را وارد کنید..."), 
            gr.Textbox(lines=10, placeholder="لطفاً توضیحات شغلی را وارد کنید...")],
    outputs=gr.File(label="دانلود فایل JSON"),
    title="پردازش رزومه و توضیحات شغلی",
    description="این ابزار رزومه و توضیحات شغلی شما را پردازش کرده و امتیازات مشابهت را محاسبه می‌کند."
)

if __name__ == "__main__":
    iface.launch()