Update app.py

app.py

@@ -13,32 +13,42 @@ 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
+
 uploaded_files = st.file_uploader(
-    "Choose a PDF file(s) and job description as pdf", accept_multiple_files=True, type = "pdf"
+    "Choose a PDF file(s) and job description as pdf", accept_multiple_files=True, type="pdf"
 )
 
-all_resumes = []  # Store the text content of each PDF
-
 if uploaded_files:
+    all_data = []  # Store dictionaries of text and entities for each PDF
     for i, uploaded_file in enumerate(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("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: entities})
-            st.dataframe(resumes)
+            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)
 
-            
+            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)
+