Update app.py

app.py

@@ -25,39 +25,27 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 import tempfile
 
-txt1 = st.text_area("Job description", key = "text 1")
-job_description_series1 = pd.Series(txt1, name="Text")
-st.dataframe(job_description_series1)
-
-from transformers import pipeline
-
+txt = st.text_area("Job description", key = "text 1")
+job_description_series = pd.Series(txt, name="Text")
+st.dataframe(job_description_series)
 
 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_text = []  # Store the text content and entities of each PDF
 
-if uploaded_files:
-    
+all_resumes_text = []  # Store the text content of each PDF
 
+if uploaded_files:
     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)
-
-            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_resumes_text.append(data)
-
-        
+        try:
+            pdf_reader = PdfReader(uploaded_file)
+            text_data = ""
+            for page in pdf_reader.pages:
+                text_data += page.extract_text()
+            all_resumes_text.append(text_data)
+        except Exception as e:
+            st.error(f"Error processing file {uploaded_file.name}: {e}")
 
     if all_resumes_text:
         all_documents = [job_description_series.iloc[0]] + all_resumes_text
@@ -83,36 +71,27 @@ if uploaded_files:
        
 st.divider()
 
-txt2 = st.text_area("Job description", key = "text 2")
-job_description_series2 = pd.Series(txt2, name="Text")
-st.dataframe(job_description_series2)
-
+txt = st.text_area("Job description", key = "text 2")
+job_description_series = pd.Series(txt, name="Text")
+st.dataframe(job_description_series)
 
 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_text = []  # Store the text content and entities of each PDF
 
-if uploaded_files:
-    
+all_resumes_text = []  # Store the text content of each PDF
 
+if uploaded_files:
     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)
-
-            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_resumes_text.append(data)
-        
+        try:
+            pdf_reader = PdfReader(uploaded_file)
+            text_data = ""
+            for page in pdf_reader.pages:
+                text_data += page.extract_text()
+            all_resumes_text.append(text_data)
+        except Exception as e:
+            st.error(f"Error processing file {uploaded_file.name}: {e}")
 
     if all_resumes_text:
         all_documents = [job_description_series.iloc[0]] + all_resumes_text
@@ -134,4 +113,8 @@ if uploaded_files:
         for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
             st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
 
+    
+
+
+