app.py

import gradio as gr
import pdfplumber
import spacy
from sentence_transformers import SentenceTransformer, util

# Load spaCy model and Sentence Transformer model
nlp = spacy.load('en_core_web_md')
model = SentenceTransformer('all-MiniLM-L6-v2')

def extract_text_from_pdf(pdf_path):
    text = ''
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            text += page.extract_text()
    return text

def extract_text_from_txt(txt_path):
    with open(txt_path, 'r') as file:
        return file.read()

def analyze_resume(resume_file, job_description_file):
    # Extract text from the PDF resume
    resume_text = extract_text_from_pdf(resume_file.name)
    
    # Extract text from the job description text file
    job_description = extract_text_from_txt(job_description_file.name)

    # Process the text with spaCy
    doc = nlp(resume_text)

    # Extract named entities from the resume
    entities = [(ent.text, ent.label_) for ent in doc.ents]
    
    # Get embeddings and compute similarity
    resume_embedding = model.encode(resume_text)
    job_description_embedding = model.encode(job_description)
    similarity = util.pytorch_cos_sim(resume_embedding, job_description_embedding).item()

    return entities, similarity, job_description

# Create a Gradio interface
iface = gr.Interface(
    fn=analyze_resume,
    inputs=[
        gr.File(label="Upload Resume (PDF)"),
        gr.File(label="Upload Job Description (TXT)")
    ],
    outputs=[
        gr.JSON(label="Extracted Entities"),
        gr.Textbox(label="Resume and Job Description Similarity"),
        gr.Textbox(label="Job Description Text", interactive=False)
    ],
    title="Resume and Job Description Analyzer",
    description="Upload your PDF resume and a TXT job description to extract entities and calculate similarity."
)

# Launch the interface
iface.launch()