Update app.py

app.py

@@ -5,21 +5,19 @@ import io
 from docx import Document
 import os
 import pymupdf  # Corrected import for PyMuPDF
-
 # For PDF generation
 from reportlab.pdfgen import canvas
 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 with Meta-Llama-3.1-8B-Instruct
 client = InferenceClient(
-    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
-    token=os.getenv("HF_TOKEN")
-)
+    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)
@@ -41,11 +39,9 @@ def extract_text_from_docx(docx_file):
 def parse_cv(file, job_description):
     if file is None:
         return "Please upload a CV file.", ""
-
     try:
         file_path = file.name
         file_ext = os.path.splitext(file_path)[1].lower()
-
         if file_ext == ".pdf":
             extracted_text = extract_text_from_pdf(file_path)
         elif file_ext == ".docx":
@@ -54,17 +50,14 @@ def parse_cv(file, job_description):
             return "Unsupported file format. Please upload a PDF or DOCX file.", ""
     except Exception as e:
         return f"Error reading file: {e}", ""
-
     if extracted_text.startswith("Error"):
         return extracted_text, "Error during text extraction. Please check the file."
-
     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}"
@@ -75,11 +68,64 @@ def parse_cv(file, job_description):
 def toggle_download_button(analysis_report):
     return gr.update(interactive=bool(analysis_report.strip()), visible=bool(analysis_report.strip()))
 
+# Function to create PDF report
+def create_pdf_report(report_text):
+    if not report_text.strip():
+        report_text = "No analysis report to convert."
+
+    pdf_buffer = io.BytesIO()
+    doc = SimpleDocTemplate(pdf_buffer, pagesize=letter)
+    styles = getSampleStyleSheet()
+    Story = []
+
+    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)
+    pdf_buffer.seek(0)
+    return (pdf_buffer.getvalue(), "analysis_report.pdf")
+
+def process_resume(resume_file, job_title):
+    """
+    Processes the uploaded resume, optimizes it for the given job title using the LLM,
+    and returns the optimized resume content.
+    """
+    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()
+
+        if file_ext == ".pdf":
+            resume_text = extract_text_from_pdf(file_path)
+        elif file_ext == ".docx":
+            resume_text = extract_text_from_docx(file_path)
+        else:
+            return "Unsupported file format. Please upload a PDF or DOCX file."
+
+        if resume_text.startswith("Error"):
+            return resume_text
+
+        prompt = (
+            f"Optimize the following resume for the job title: {job_title}.\n"
+            f"Include relevant skills, experience, and keywords related to the job title.\n\n"
+            f"Resume:\n{resume_text}\n"
+        )
+
+        optimized_resume = client.text_generation(prompt, max_new_tokens=1024)
+        return optimized_resume
+
+    except Exception as e:
+        return f"Error processing resume: {e}"
 # Build the Gradio UI
 demo = gr.Blocks()
 with demo:
     gr.Markdown("## AI-powered CV Analyzer, Optimizer, and Chatbot")
-
     with gr.Tab("Chatbot"):
         chat_interface = gr.ChatInterface(
             lambda message, history: client.chat_completion(
@@ -89,7 +135,6 @@ with demo:
             chatbot=gr.Chatbot(label="Chatbot", type="messages"),
             textbox=gr.Textbox(placeholder="Enter your message here...", label="Message"),
         )
-
     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"])
@@ -99,19 +144,18 @@ with demo:
         download_pdf_button = gr.Button("Download Analysis as PDF", visible=False, interactive=False)
         pdf_file = gr.File(label="Download PDF", interactive=False)
         analyze_button = gr.Button("Analyze CV")
-        
+
         analyze_button.click(parse_cv, [file_input, job_desc_input], [extracted_text, analysis_output])
         analyze_button.click(toggle_download_button, [analysis_output], [download_pdf_button])
         download_pdf_button.click(create_pdf_report, [analysis_output], [pdf_file])
-
     with gr.Tab("CV Optimizer"):
         gr.Markdown("### Upload your Resume and Enter Job Title")
-        resume_file = gr.File(label="Upload Resume (PDF or Word)")
+        resume_file = gr.File(label="Upload Resume (PDF or Word)", file_types=[".pdf", ".docx"])
         job_title_input = gr.Textbox(label="Job Title", lines=1)
         optimized_resume_output = gr.Textbox(label="Optimized Resume", lines=20)
         optimize_button = gr.Button("Optimize Resume")
-        
+
         optimize_button.click(process_resume, [resume_file, job_title_input], [optimized_resume_output])
 
 if __name__ == "__main__":
-    demo.queue().launch()
+    demo.queue().launch()