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")
data1 = pd.Series(txt, index = ["Job Description"])
st.dataframe(data1)



uploaded_files = st.file_uploader(
    "Choose a PDF file(s) and job description as pdf", accept_multiple_files=True, type="pdf"
)

if uploaded_files:
    all_data = []  # Store dictionaries of text and entities for each PDF
    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()

            model = GLiNER.from_pretrained("urchade/gliner_base")
            labels = ["person", "country", "organization", "time", "role"]
            entities = model.predict_entities(text_data, labels)

            entity_dict = {}
            for label in labels:
                entity_dict[label] = [entity["text"] for entity in entities if entity["label"] == label]

            data = {"Text": text_data, **entity_dict}
            all_data.append(data)

        except Exception as e:
            st.error(f"Error processing file {uploaded_file.name}: {e}")

    if all_data:
        df = pd.DataFrame(all_data)
        st.dataframe(df)