import gradio as gr
import fitz  # PyMuPDF
from models import evaluate_with_gpt, evaluate_with_gemma, evaluate_with_bloom, evaluate_with_jabir, evaluate_with_llama  ,evaluate_with_qwen

def extract_text_from_pdf(pdf_file):
    document = fitz.open(pdf_file)
    text = ""
    for page_num in range(len(document)):
        page = document.load_page(page_num)
        text += page.get_text()
    return text

def evaluate_all_models(pdf_file, job_description):
    resume_text = extract_text_from_pdf(pdf_file)
    gpt_result = evaluate_with_gpt(resume_text, job_description)
    gemma_result = evaluate_with_gemma(resume_text, job_description)
    bloom_result = evaluate_with_bloom(resume_text, job_description)
    jabir_result = evaluate_with_jabir(resume_text, job_description)
    llama_result = evaluate_with_llama(resume_text, job_description)
    qwen_result=evaluate_with_qwen(resume_text, job_description)

    
    return f"GPT-4o Result:\n{gpt_result}\n\nGemma Result:\n{gemma_result}\n\nBloom Result:\n{bloom_result}\n\nJabir Result:\n{jabir_result}\n\nLlama Result:\n{llama_result}\n\nqwen_result:\n{qwen_result}"
import gradio as gr
from models import evaluate_with_gpt, evaluate_with_gemma, evaluate_with_bloom, evaluate_with_jabir, evaluate_with_llama,evaluate_with_qwen

def evaluate_multiple_resumes(resume_texts, job_description, model):
    results = []
    for resume_text in resume_texts.split("\n\n"):  # Assuming each resume text is separated by two newlines
        if model == "GPT-4o":
            result = evaluate_with_gpt(resume_text, job_description)
        elif model == "Gemma":
            result = evaluate_with_gemma(resume_text, job_description)
        elif model == "Bloom":
            result = evaluate_with_bloom(resume_text, job_description)
        elif model == "jabir":
            result = evaluate_with_jabir(resume_text, job_description)
        elif model == "llama":
            result = evaluate_with_llama(resume_text, job_description)
        elif model=="qwen":
            evaluate_with_qwen(resume_text, job_description)
        else:
            gpt_result = evaluate_with_gpt(resume_text, job_description)
            gemma_result = evaluate_with_gemma(resume_text, job_description)
            bloom_result = evaluate_with_bloom(resume_text, job_description)
            jabir_result = evaluate_with_jabir(resume_text, job_description)
            llama_result = evaluate_with_llama(resume_text, job_description)
            qwen_result=evaluate_with_qwen(resume_text, job_description)
            result = f"GPT-4o Result:\n{gpt_result}\n\nGemma Result:\n{gemma_result}\n\nBloom Result:\n{bloom_result}\n\nJabir Result:\n{jabir_result}\n\nLlama Result:\n{llama_result}\n\nqwen_result:\n{qwen_result}"
        results.append(f"Result for Resume:\n{result}\n\n")
    return "\n".join(results)

iface = gr.Interface(
    fn=evaluate_multiple_resumes,
    inputs=[
        gr.Textbox(lines=20, label="Paste Resumes (separate multiple resumes by two newlines)"),
        gr.Textbox(lines=10, label="Job Description"),
        gr.Radio(choices=["GPT-4o", "Gemma", "Bloom", "jabir", "llama", "qwen","All"], label="Choose Model")
    ],
    outputs="text",
    title="Multiple Resume Evaluator"
)

iface.launch()