Update app.py

app.py

@@ -1,20 +1,20 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-import PyPDF2
 import io
 from docx import Document
 import os
-import pymupdf  # Corrected import for PyMuPDF
-from reportlab.pdfgen import canvas
+import pymupdf
+# For PDF generation
 from reportlab.lib.pagesizes import letter
 from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
 from reportlab.lib.styles import getSampleStyleSheet
-from reportlab.lib import colors
 
+# Initialize Hugging Face Inference Client
 client = InferenceClient(
     model="meta-llama/Meta-Llama-3-8B-Instruct",
     token=os.getenv("HF_TOKEN"))
 
+# Function to extract text from PDF
 def extract_text_from_pdf(pdf_file):
     try:
         pdf_document = pymupdf.open(pdf_file)
@@ -23,6 +23,7 @@ def extract_text_from_pdf(pdf_file):
     except Exception as e:
         return f"Error reading PDF: {e}"
 
+# Function to extract text from DOCX
 def extract_text_from_docx(docx_file):
     try:
         doc = Document(docx_file)
@@ -31,70 +32,71 @@ def extract_text_from_docx(docx_file):
     except Exception as e:
         return f"Error reading DOCX: {e}"
 
+# Function to analyze CV and generate report
 def parse_cv(file, job_description):
     if file is None:
-        return "Please upload a CV file.", ""
+        return "Please upload a CV file.", "", None
     try:
         file_path = file.name
         file_ext = os.path.splitext(file_path)[1].lower()
-        extracted_text = extract_text_from_pdf(file_path) if file_ext == ".pdf" else extract_text_from_docx(file_path)
+        if file_ext == ".pdf":
+            extracted_text = extract_text_from_pdf(file_path)
+        elif file_ext == ".docx":
+            extracted_text = extract_text_from_docx(file_path)
+        else:
+            return "Unsupported file format. Please upload a PDF or DOCX file.", "", None
     except Exception as e:
-        return f"Error reading file: {e}", ""
+        return f"Error reading file: {e}", "", None
     if extracted_text.startswith("Error"):
-        return extracted_text, "Error during text extraction."
-    prompt = f"Analyze this CV for job relevance.\nJob Description:\n{job_description}\n\nCV:\n{extracted_text}\n"
+        return extracted_text, "Error during text extraction. Please check the file.", None
+    prompt = (
+        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}\n"
+    )
     try:
         analysis = client.text_generation(prompt, max_new_tokens=512)
-        return extracted_text, f"**Analysis Report:**\n{analysis}"
+        report_text = f"--- Analysis Report ---\n{analysis}"
+        pdf_path = create_pdf_report(report_text)  # Generate PDF in the backend
+        return extracted_text, report_text, pdf_path
     except Exception as e:
-        return extracted_text, f"Analysis Error: {e}"
+        return extracted_text, f"Analysis Error: {e}", None
 
+# Function to create PDF report
 def create_pdf_report(report_text):
-    pdf_buffer = io.BytesIO()
-    doc = SimpleDocTemplate(pdf_buffer, pagesize=letter)
+    if not report_text.strip():
+        report_text = "No analysis report to convert."
+
+    pdf_path = "analysis_report.pdf"
+    doc = SimpleDocTemplate(pdf_path, pagesize=letter)
     styles = getSampleStyleSheet()
-    Story = [Paragraph("<b>Analysis Report</b>", styles['Title']), Spacer(1, 12)]
-    Story.append(Paragraph(report_text.replace("\n", "<br/>"), styles['BodyText']))
-    doc.build(Story)
-    pdf_buffer.seek(0)
-    return pdf_buffer.getvalue(), "analysis_report.pdf"
+    Story = []
 
-def process_resume(resume_file, job_title):
-    if resume_file is None:
-        return "Please upload a resume file."
-    try:
-        file_path = resume_file.name
-        file_ext = os.path.splitext(file_path)[1].lower()
-        resume_text = extract_text_from_pdf(file_path) if file_ext == ".pdf" else extract_text_from_docx(file_path)
-        if resume_text.startswith("Error"):
-            return resume_text
-        prompt = f"Optimize this resume for {job_title}:\n{resume_text}\n"
-        optimized_resume = client.text_generation(prompt, max_new_tokens=1024)
-        return optimized_resume.replace("\n", "  \n")  # Ensure Markdown formatting
-    except Exception as e:
-        return f"Error processing resume: {e}"
+    title = Paragraph("<b>Analysis Report</b>", styles['Title'])
+    Story.append(title)
+    Story.append(Spacer(1, 12))
 
+    report_paragraph = Paragraph(report_text.replace("\n", "<br/>"), styles['BodyText'])
+    Story.append(report_paragraph)
+
+    doc.build(Story)
+    return pdf_path
+
+# Build the Gradio UI
 demo = gr.Blocks()
 with demo:
     gr.Markdown("## AI-powered CV Analyzer and Optimizer")
-    
     with gr.Tab("CV Analyzer"):
+        gr.Markdown("### Upload your CV and provide the job description")
         file_input = gr.File(label="Upload CV", file_types=[".pdf", ".docx"])
         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.Markdown(label="Analysis Report")
-        download_pdf_button = gr.Button("Download Analysis as PDF", visible=False)
-        pdf_file = gr.File(label="Download PDF", interactive=False)
+        analysis_output = gr.Textbox(label="Analysis Report", lines=10, interactive=False)
+        pdf_file = gr.File(label="Download Analysis Report PDF", interactive=True)
         analyze_button = gr.Button("Analyze CV")
-        analyze_button.click(parse_cv, [file_input, job_desc_input], [extracted_text, analysis_output])
-        download_pdf_button.click(create_pdf_report, [analysis_output], [pdf_file])
-    
-    with gr.Tab("CV Optimizer"):
-        resume_file = gr.File(label="Upload Resume (PDF or Word)", file_types=[".pdf", ".docx"])
-        job_title_input = gr.Textbox(label="Job Title")
-        optimized_resume_output = gr.Markdown(label="Optimized Resume")
-        optimize_button = gr.Button("Optimize Resume")
-        optimize_button.click(process_resume, [resume_file, job_title_input], [optimized_resume_output])
+
+        analyze_button.click(parse_cv, [file_input, job_desc_input], [extracted_text, analysis_output, pdf_file])
 
 if __name__ == "__main__":
-    demo.queue().launch()
+    demo.queue().launch()