Update app.py

app.py

@@ -4,6 +4,10 @@ import PyPDF2
 import io
 from docx import Document
 
+# For PDF generation
+from reportlab.pdfgen import canvas
+from reportlab.lib.pagesizes import letter
+
 # Initialize the inference client from Hugging Face.
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
@@ -30,10 +34,10 @@ def extract_text_from_docx(docx_file_bytes):
         return f"Error reading DOCX: {e}"
 
 def parse_cv(file, job_description):
-    """Analyze the CV and return both extracted text and analysis report."""
+    """Analyze the CV, show the prompt (debug) and return LLM analysis."""
     if file is None:
         return "Please upload a CV file.", ""
-    
+
     try:
         file_bytes = file
         file_ext = "pdf"
@@ -52,21 +56,28 @@ def parse_cv(file, job_description):
         extracted_text = extract_text_from_pdf(file_bytes)
     elif file_ext == "docx":
         extracted_text = extract_text_from_docx(file_bytes)
-    
+
     # Check for extraction errors
     if extracted_text.startswith("Error"):
         return extracted_text, "Error during text extraction. Please check the file."
 
-    # Prepare and send to LLM
+    # Prepare debug prompt
     prompt = (
-        f"Analyze the CV against the job description. Provide a summary, assessment, and score 0-10.\n\n"
+        f"Analyze the CV against the job description. Provide a summary, assessment, "
+        f"and a score 0-10.\n\n"
         f"Job Description:\n{job_description}\n\n"
-        f"Candidate CV:\n{extracted_text}"
+        f"Candidate CV:\n{extracted_text}\n"
     )
 
+    # Call LLM
     try:
         analysis = client.text_generation(prompt, max_new_tokens=512)
-        return extracted_text, analysis
+        # Show both the debug prompt and analysis in the "Analysis Report"
+        analysis_report = (
+            f"--- DEBUG PROMPT ---\n{prompt}\n"
+            f"--- LLM ANALYSIS ---\n{analysis}"
+        )
+        return extracted_text, analysis_report
     except Exception as e:
         return extracted_text, f"Analysis Error: {e}"
 
@@ -95,7 +106,38 @@ def respond(message, history: list[tuple[str, str]], system_message, max_tokens,
     except Exception as e:
         yield f"Error during chat generation: {e}"
 
-# Gradio Interface
+
+def create_pdf_report(report_text):
+    """
+    Creates a PDF from the given report text and returns (filename, PDF_bytes).
+    """
+    if not report_text.strip():
+        # If there's no report, just return a basic PDF stating so
+        report_text = "No analysis report to convert."
+
+    # Use ReportLab to generate PDF in-memory
+    pdf_buffer = io.BytesIO()
+    c = canvas.Canvas(pdf_buffer, pagesize=letter)
+    
+    # Title
+    c.setFont("Helvetica-Bold", 14)
+    c.drawString(72, 750, "Analysis Report")
+    
+    # Body
+    text_obj = c.beginText(72, 730)
+    text_obj.setFont("Helvetica", 11)
+    for line in report_text.split("\n"):
+        text_obj.textLine(line)
+    c.drawText(text_obj)
+    
+    c.showPage()
+    c.save()
+    pdf_buffer.seek(0)
+
+    return ("analysis_report.pdf", pdf_buffer.getvalue())
+
+
+# Build the Gradio UI
 demo = gr.Blocks()
 with demo:
     gr.Markdown("## AI-powered CV Analyzer and Chatbot")
@@ -119,13 +161,23 @@ with demo:
         job_desc_input = gr.Textbox(label="Job Description", lines=5)
         extracted_text = gr.Textbox(label="Extracted CV Content", lines=10, interactive=False)
         analysis_output = gr.Textbox(label="Analysis Report", lines=10)
-        analyze_button = gr.Button("Analyze CV")
 
+        analyze_button = gr.Button("Analyze CV")
         analyze_button.click(
             parse_cv,
             inputs=[file_input, job_desc_input],
             outputs=[extracted_text, analysis_output]
         )
 
+        # Button to generate/download PDF
+        download_pdf_button = gr.Button("Download Analysis as PDF")
+        pdf_file = gr.File(label="Download PDF", file_count="single", interactive=False)
+
+        download_pdf_button.click(
+            create_pdf_report,
+            inputs=[analysis_output],  # pass the analysis text
+            outputs=[pdf_file]         # this will allow downloading the PDF
+        )
+
 if __name__ == "__main__":
-    demo.queue().launch(debug=True)
+    demo.queue().launch()