Update app.py

app.py

@@ -39,25 +39,24 @@ uploaded_files = st.file_uploader(
 all_resumes_text = []  # Store the text content and entities of each PDF
 
 if uploaded_files:
-    model = GLiNER.from_pretrained("urchade/gliner_base")
-    labels = ["person", "country", "organization", "time", "role"]
+    
 
     for uploaded_file in uploaded_files:
         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)
 
-        entities = model(text_data)
+            entity_dict = {}
+            for label in labels:
+                entity_dict[label] = [entity["text"] for entity in entities if entity["label"] == label]
 
-        entity_dict = {}
-        for label in labels:
-            entity_dict[label] = [entity["word"] for entity in entities if entity["entity_group"] == label]
+            data = {"Text": text_data, **entity_dict}
+            all_resumes_text.append(data)
 
-        data = {"Text": text_data, **entity_dict}
-        all_resumes_text.append(data)
-
-    st.write("Processed data:", all_resumes_text) # For demonstration
         
 
     if all_resumes_text:
@@ -96,25 +95,23 @@ uploaded_files = st.file_uploader(
 all_resumes_text = []  # Store the text content and entities of each PDF
 
 if uploaded_files:
-    model = GLiNER.from_pretrained("urchade/gliner_base")
-    labels = ["person", "country", "organization", "time", "role"]
+    
 
     for uploaded_file in uploaded_files:
         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)
 
-        entities = model(text_data)
-
-        entity_dict = {}
-        for label in labels:
-            entity_dict[label] = [entity["word"] for entity in entities if entity["entity_group"] == label]
-
-        data = {"Text": text_data, **entity_dict}
-        all_resumes_text1.append(data)
+            entity_dict = {}
+            for label in labels:
+                entity_dict[label] = [entity["text"] for entity in entities if entity["label"] == label]
 
-    st.write("Processed data:", all_resumes_text) # For demonstration
+            data = {"Text": text_data, **entity_dict}
+            all_resumes_text.append(data)
         
 
     if all_resumes_text: