Update functions.py

functions.py

@@ -385,79 +385,80 @@ class QdrantInterface:
 
 
 
-def resume_pdf():
 
 
-    # File uploader widget
-    uploaded_file = st.file_uploader("Upload Resumes", type=["pdf"])
 
-    if uploaded_file is not None:
-        # Read PDF file
-        pdf_reader = PyPDF2.PdfReader(uploaded_file)
+def extract_text_from_pdf(file):
+    """
+    Extract text from a PDF file using PyPDF2 library.
+    """
+    text = ""
+    try:
+        pdf_reader = PyPDF2.PdfReader(file)
         num_pages = len(pdf_reader.pages) 
-
-        # Extract text from each page
-        text = ""
         for page_num in range(num_pages):
             page = pdf_reader.pages[page_num] 
             text += page.extract_text()
+    except Exception as e:
+        st.error(f"Error extracting text from PDF: {e}")
+    return text
 
-        # Convert text to CSV
-        csv_data = convert_to_csv(text)
+def resume_pdf():
+    st.title(UPLOAD RESUMES")
 
-        # Display or download CSV
-        st.subheader("Converted CSV Data")
-        st.write(csv_data)
+    # Allow user to upload multiple PDF files
+    uploaded_files = st.file_uploader("Upload PDF files", type="pdf")
 
-        # Download link for CSV file
-        st.download_button(
-            label="Download CSV",
-            data=csv_data,
-            file_name="converted_data.csv",
-            mime="text/csv"
-        )
+    if uploaded_files:
+        st.write("## Extracted Text from PDFs")
+        df_rows = []
 
-def job_desc_pdf():
+        # Iterate over uploaded PDF files
+        for uploaded_file in uploaded_files:
+            text = extract_text_from_pdf(uploaded_file)
 
+            # Add text to DataFrame
+            df_rows.append({"File Name": uploaded_file.name, "Text": text})
 
-    # File uploader widget
-    uploaded_file = st.file_uploader("Upload Job Description", type=["pdf"])
+            # Display extracted text
+            st.write(f"### {uploaded_file.name}")
+            st.write(text)
 
-    if uploaded_file is not None:
-        # Read PDF file
-        pdf_reader = PyPDF2.PdfReader(uploaded_file)
-        num_pages = len(pdf_reader.pages) 
+        # Create DataFrame
+        df = pd.DataFrame(df_rows)
 
-        # Extract text from each page
-        text = ""
-        for page_num in range(num_pages):
-            page = pdf_reader.pages[page_num] 
-            text += page.extract_text()
+        # Display DataFrame
+        st.write("## Combined Data in DataFrame")
+        st.write(df)
 
-        # Convert text to CSV
-        csv_data = convert_to_csv(text)
+def job_desc_pdf():
+    st.title(UPLOAD JOB DESCRIPTION")
 
-        # Display or download CSV
-        st.subheader("Converted CSV Data")
-        st.write(csv_data)
+    # Allow user to upload multiple PDF files
+    uploaded_files = st.file_uploader("Upload PDF files", accept_multiple_files=True, type="pdf")
 
-        # Download link for CSV file
-        st.download_button(
-            label="Download CSV",
-            data=csv_data,
-            file_name="converted_data.csv",
-            mime="text/csv"
-        )
-    
-def convert_to_csv(text):
-    # Split text into lines and create a DataFrame
-    lines = text.split("\n")
-    df = pd.DataFrame(lines, columns=["Text"])
+    if uploaded_files:
+        st.write("## Extracted Text from PDFs")
+        df_rows = []
+
+        # # Iterate over uploaded PDF files
+        # for uploaded_file in uploaded_files:
+        #     text = extract_text_from_pdf(uploaded_file)
+
+        #     # Add text to DataFrame
+        #     df_rows.append({"File Name": uploaded_file.name, "Text": text})
+
+        #     # Display extracted text
+        #     st.write(f"### {uploaded_file.name}")
+        #     st.write(text)
+
+        # Create DataFrame
+        df = pd.DataFrame(df_rows)
 
-    # Convert DataFrame to CSV format
-    csv_data = df.to_csv(index=False, escapechar='\\')
+        # Display DataFrame
+        st.write("## Combined Data in DataFrame")
+        st.write(df)
 
-    return csv_data