Update app.py

app.py

@@ -6,20 +6,32 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 
 uploaded_files = st.file_uploader(
-    "Choose a CSV file", accept_multiple_files=True
+    "Choose a PDF file(s)", accept_multiple_files=True, type=["pdf"]  # Corrected label and added type
 )
+
+all_series = []  # Initialize an empty list to store Pandas Series
+
 for uploaded_file in uploaded_files:
-    pdf_reader = PdfReader(uploaded_file) # read your PDF file
-    # extract the text data from your PDF file after looping through its pages with the .extract_text() method
-    text_data= ""
-    for page in pdf_reader.pages: # for loop method
-        text_data+= page.extract_text()
-
-    
-    
-    data = pd.Series(text_data, index = ["Resume"])
-    st.dataframe(data) # view the text data
-        
+    try:
+        pdf_reader = PdfReader(uploaded_file)
+        text_data = ""
+        for page in pdf_reader.pages:
+            text_data += page.extract_text()
+
+        # Create a Pandas Series for each PDF
+        data = pd.Series({"Resume": text_data})  # Use a dictionary to name the Series
+        all_series.append(data)
+        st.subheader(f"Content of {uploaded_file.name}")
+        st.dataframe(data) # Display the Series for the current PDF
+
+    except Exception as e:
+        st.error(f"Error processing {uploaded_file.name}: {e}")
+
+if all_series:
+    # Concatenate all the Series into a DataFrame
+    all_data_df = pd.DataFrame(all_series)
+    st.subheader("Combined Resume Texts")
+    st.dataframe(all_data_df)