Update app.py

app.py

@@ -84,56 +84,52 @@ def get_resume_response(prompt: str, api_key: str, model: str = "llama-3.3-70b",
         response_string += chunk.choices[0].delta.content or ""
     return response_string
 
-def process_resume(file, jd_string):
+def process_resume(resume, jd_string):
     """
     Process the uploaded resume and job description, optimize it, and return the result.
     """
     try:
-        # Check if file is a 'NamedString' and read its content correctly
-        file_content = file.name  # Access the file content via the file's path
-
-        # Convert file to Markdown using MarkItDown
-        original_md = md_converter.convert(file_content)
-        original_text = original_md.text_content
-
-        # Save the original resume in Markdown format
-        original_file_path = "resumes/original_resume.md"
-        os.makedirs("resumes", exist_ok=True)  # Ensure the directory exists
-        with open(original_file_path, "w", encoding="utf-8") as f:
-            f.write(original_text)
+        # Read file content from the resume path
+        with open(resume.name, "r", encoding="utf-8") as file:
+            resume_string = file.read()
 
         # Create optimization prompt
-        prompt = create_prompt(original_text, jd_string)
-        response_string = get_resume_response(prompt, api_key)
+        prompt = create_prompt(resume_string, jd_string)
 
-        # Split response into optimized resume and suggestions
+        # Generate response using AI
+        response_string = get_resume_response(prompt, api_key)
         response_list = response_string.split("## Additional Suggestions")
+
+        # Extract new resume and suggestions for improvement
         new_resume = response_list[0].strip()
-        suggestions = "## Additional Suggestions\n\n" + response_list[1].strip() if len(response_list) > 1 else ""
+        suggestions = "## Additional Suggestions \n\n" + response_list[1].strip() if len(response_list) > 1 else ""
 
-        # Save the optimized resume in Markdown format
+        # Save the optimized resume
         optimized_file_path = "resumes/optimized_resume.md"
+        os.makedirs("resumes", exist_ok=True)  # Ensure the directory exists
         with open(optimized_file_path, "w", encoding="utf-8") as f:
             f.write(new_resume)
 
-        return original_text, new_resume, original_file_path, optimized_file_path, suggestions
+        # Return the results
+        return resume_string, new_resume, optimized_file_path, suggestions
     except Exception as e:
-        return f"Error processing file: {str(e)}", "", None, None, ""
+        return f"Error processing file: {str(e)}", "", None, ""
 
-def export_resume(md_file_path):
-    """
-    Export the optimized resume (in Markdown format) as a PDF file.
+def export_resume(new_resume):
     """
-    try:
-        # Step 1: Convert the file to Markdown using MarkItDown
-        md_converter = MarkItDown()
-        result = md_converter.convert(md_file_path)
-        md_content = result.text_content  # This contains the converted Markdown
+    Convert a markdown resume to PDF format and save it.
 
-        # Step 2: Convert Markdown to HTML
-        html_content = markdown.markdown(md_content)  # Using markdown library to convert to HTML
+    Args:
+        new_resume (str): The resume content in markdown format
 
-        # Step 3: Convert HTML to PDF using WeasyPrint
+    Returns:
+        str: A message indicating success or failure of the PDF export
+    """
+    try:
+        # Convert Markdown to HTML
+        html_content = markdown.markdown(new_resume)
+        
+        # Convert HTML to PDF and save
         output_pdf_file = "resumes/optimized_resume.pdf"
         os.makedirs("resumes", exist_ok=True)  # Ensure the directory exists
         HTML(string=html_content).write_pdf(output_pdf_file, stylesheets=['resumes/style.css'])