Update app.py

app.py

@@ -2,7 +2,7 @@ import streamlit as st
 from PyPDF2 import PdfReader
 import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.feature_extraction.text import TfidfVectorizer
+
 from sklearn.metrics.pairwise import cosine_similarity
 
 import streamlit as st
@@ -10,6 +10,8 @@ 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
+
 
 uploaded_files = st.file_uploader(
     "Choose a PDF file(s) and job description as pdf", accept_multiple_files=True, type = "pdf"
@@ -24,6 +26,9 @@ if uploaded_files:
             text_data = ""
             for page in pdf_reader.pages:
                 text_data += page.extract_text()
+                model = GLiNER.from_pretrained("xomad/gliner-model-merge-large-v1.0")
+                labels = ["person", "country", "city", "organization", "date", "money", "percent value", "position"]
+                entities = model.predict_entities(text_data, labels)
 
             column_name = f"Candidate profile {i + 1}"
             resumes = pd.Series({column_name: text_data})
@@ -35,19 +40,7 @@ if uploaded_files:
             st.error(f"Error processing file {uploaded_file.name}: {e}")
 
 
-if all_resumes:
-    # Initialize the TF-IDF vectorizer
-    vectorizer = TfidfVectorizer()
 
-    # Fit and transform the text data
-    tfidf_matrix = vectorizer.fit_transform(all_resumes)
-
-    # Calculate the cosine similarity matrix
-    cosine_sim = cosine_similarity(tfidf_matrix)
-
-    st.subheader("Cosine Similarity Matrix")
-    st.dataframe(cosine_sim)
-elif uploaded_files:
-    st.info("Please upload at least two PDF files to calculate cosine similarity.")
+