utils.py

import fitz
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

def extract_text_from_pdf(file):
    text = ""
    pdf = fitz.open(stream=file.read(), filetype="pdf")
    for page in pdf:
        text += page.get_text()
    return text


def calculate_similarity(resume_text, job_desc):
    vectorizer = TfidfVectorizer(stop_words="english")
    vectors = vectorizer.fit_transform([resume_text, job_desc])
    similarity = cosine_similarity(vectors[0:1], vectors[1:2])[0][0]
    return round(similarity * 100, 2)