Update app.py

app.py

@@ -29,35 +29,38 @@ txt1 = st.text_area("Job description", key = "text 1")
 job_description_series1 = pd.Series(txt1, name="Text")
 st.dataframe(job_description_series1)
 
+
+
+
 uploaded_files = st.file_uploader(
-    "Choose a PDF file(s) for candidate profiles",  type="pdf", key = "candidate 1"
+    "Choose a PDF file(s) for candidate profiles", type="pdf", key="candidate 1"
 )
 
-
-all_resumes_text1 = []  # Store the text content of each PDF
+all_resumes_text = []  # Store the text content and entities of each PDF
 
 if uploaded_files:
+    model = pipeline("ner", model="urchade/gliner_base", aggregation_strategy="simple")
+    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[label] = [entity["word"] for entity in entities if entity["entity_group"] == label]
 
         data = {"Text": text_data, **entity_dict}
-            
-
+        all_resumes_text.append(data)
 
-        all_resumes_text1.append(data)
+    st.write("Processed data:", all_resumes_text) # For demonstration
         
 
-    if all_resumes_text1:
+    if all_resumes_text:
         all_documents = [job_description_series.iloc[0]] + all_resumes_text
 
         vectorizer = TfidfVectorizer()
@@ -85,35 +88,36 @@ txt2 = st.text_area("Job description", key = "text 2")
 job_description_series2 = pd.Series(txt2, name="Text")
 st.dataframe(job_description_series2)
 
+
 uploaded_files = st.file_uploader(
-    "Choose a PDF file(s) for candidate profiles",  type="pdf", key = "candidate 2"
+    "Choose a PDF file(s) for candidate profiles", type="pdf", key="candidate 2"
 )
 
-
-all_resumes_text2 = []  # Store the text content of each PDF
+all_resumes_text = []  # Store the text content and entities of each PDF
 
 if uploaded_files:
+    model = pipeline("ner", model="urchade/gliner_base", aggregation_strategy="simple")
+    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[label] = [entity["word"] for entity in entities if entity["entity_group"] == label]
 
         data = {"Text": text_data, **entity_dict}
-            
-
+        all_resumes_text1.append(data)
 
-        all_resumes_text2.append(data)
+    st.write("Processed data:", all_resumes_text) # For demonstration
         
 
-    if all_resumes_text2:
+    if all_resumes_text:
         all_documents = [job_description_series.iloc[0]] + all_resumes_text
 
         vectorizer = TfidfVectorizer()