import streamlit as st
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity

@st.cache(allow_output_mutation=True)
def load_model():
    model = SentenceTransformer('all-MiniLM-L6-v2')
    return model

def calculate_similarity(model, text1, text2):
    embedding1 = model.encode([text1])
    embedding2 = model.encode([text2])
    return cosine_similarity(embedding1, embedding2)[0][0]

st.title("Resume Matcher")

model = load_model()

jd = st.text_area("Enter the Job Description:", height=200)
resume = st.text_area("Enter the Resume:", height=200)

if st.button("Calculate Match Score"):
    if jd and resume:
        score = calculate_similarity(model, jd, resume)
        st.write(f"The match score is: {score}")
    else:
        st.write("Please enter both the job description and resume.")