import streamlit as st
from PyPDF2 import PdfReader
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer

from sklearn.metrics.pairwise import cosine_similarity

import streamlit as st
from PyPDF2 import PdfReader
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
from gliner import GLiNER


import streamlit as st
import pandas as pd
from PyPDF2 import PdfReader
from gliner import GLiNER


txt = st.text_area("Job description")
job_description_series = pd.Series([txt], name="Text")
st.dataframe(job_description_series)

uploaded_files = st.file_uploader(
    "Choose a PDF file(s) for candidate profiles", accept_multiple_files=True, type="pdf"
)

all_resumes_text = []  # Store the text content of each PDF

if uploaded_files:
    for uploaded_file in uploaded_files:
        try:
            pdf_reader = PdfReader(uploaded_file)
            text_data = ""
            for page in pdf_reader.pages:
                text_data += page.extract_text()
            all_resumes_text.append(text_data)
        except Exception as e:
            st.error(f"Error processing file {uploaded_file.name}: {e}")

    if all_resumes_text:
        all_documents = [job_description_series.iloc[0]] + all_resumes_text

        vectorizer = TfidfVectorizer()
        tfidf_matrix = vectorizer.fit_transform(all_documents)

        tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
        st.subheader("TF-IDF Values:")
        st.dataframe(tfidf_df)

        cosine_sim_matrix = cosine_similarity(tfidf_matrix)
        cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
        st.subheader("Cosine Similarity Matrix:")
        st.dataframe(cosine_sim_df)

        # Display similarity scores between the job description and each resume
        st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
        for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
            st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")