Create app.py

app.py

@@ -0,0 +1,302 @@
+import os
+import time
+import tempfile
+import gradio as gr
+import warnings
+from pathlib import Path
+import PyPDF2
+import markdown
+from datetime import datetime, timedelta
+from collections import defaultdict
+import threading
+
+warnings.filterwarnings('ignore')
+
+# Rate limiting
+class RateLimiter:
+    def __init__(self, max_requests=5, time_window=60):
+        self.max_requests = max_requests
+        self.time_window = time_window
+        self.requests = defaultdict(list)
+        self.lock = threading.Lock()
+    
+    def is_allowed(self, user_id):
+        with self.lock:
+            now = datetime.now()
+            # Clean old requests
+            self.requests[user_id] = [
+                req_time for req_time in self.requests[user_id]
+                if now - req_time < timedelta(seconds=self.time_window)
+            ]
+            
+            if len(self.requests[user_id]) >= self.max_requests:
+                return False
+            
+            self.requests[user_id].append(now)
+            return True
+
+# Global rate limiter
+rate_limiter = RateLimiter(max_requests=3, time_window=300)  # 3 requests per 5 minutes
+
+def extract_text_from_pdf(pdf_file):
+    """Extract text from uploaded PDF file."""
+    try:
+        reader = PyPDF2.PdfReader(pdf_file)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text() + "\n"
+        return text.strip()
+    except Exception as e:
+        return f"Error reading PDF: {str(e)}"
+
+def setup_crewai():
+    """Initialize CrewAI components."""
+    try:
+        from crewai import Agent, Task, Crew
+        from crewai_tools import ScrapeWebsiteTool, SerperDevTool
+        from langchain_openai import ChatOpenAI
+        
+        # Initialize tools
+        search_tool = SerperDevTool()
+        scrape_tool = ScrapeWebsiteTool()
+        
+        # Initialize LLM
+        llm = ChatOpenAI(model="gpt-4o-mini", temperature=0.3)
+        
+        # Create agents
+        researcher = Agent(
+            role="Job Requirements Analyst",
+            goal="Extract and analyze key job requirements efficiently",
+            tools=[scrape_tool, search_tool],
+            verbose=False,
+            backstory="Expert at quickly identifying essential job requirements and qualifications from job postings.",
+            llm=llm,
+        )
+        
+        resume_strategist = Agent(
+            role="Resume Enhancement Specialist",
+            goal="Optimize resumes to match job requirements effectively",
+            tools=[],
+            verbose=False,
+            backstory="Skilled at tailoring resumes to highlight relevant experience and skills for specific job applications.",
+            llm=llm,
+        )
+        
+        return researcher, resume_strategist, llm
+        
+    except ImportError:
+        raise Exception("CrewAI not installed. Please install required packages.")
+
+def create_tasks(researcher, resume_strategist, job_url, resume_text):
+    """Create optimized tasks for the crew."""
+    from crewai import Task
+    
+    # Research task - focused and efficient
+    research_task = Task(
+        description=f"""
+        Analyze the job posting at {job_url} and extract the top 10 most important:
+        1. Required skills and technologies
+        2. Key qualifications and experience levels
+        3. Preferred background and certifications
+        
+        Focus on the most critical requirements only.
+        """,
+        expected_output="A concise list of the top 10 most important job requirements.",
+        agent=researcher,
+    )
+    
+    # Resume optimization task
+    resume_task = Task(
+        description=f"""
+        Using the job requirements from the research task, optimize this resume:
+        
+        {resume_text}
+        
+        Instructions:
+        1. Rewrite the professional summary to align with the job
+        2. Highlight relevant experience and skills
+        3. Adjust technical skills section to match requirements
+        4. Ensure ATS-friendly formatting
+        5. Keep the same factual information but present it strategically
+        
+        Return the complete optimized resume in markdown format.
+        """,
+        expected_output="A complete, optimized resume in markdown format tailored to the job requirements.",
+        agent=resume_strategist,
+        context=[research_task]
+    )
+    
+    return research_task, resume_task
+
+def process_application(pdf_file, job_url, user_session):
+    """Main processing function with rate limiting."""
+    
+    # Rate limiting check
+    if not rate_limiter.is_allowed(user_session):
+        return "⚠️ Rate limit exceeded. Please wait 5 minutes before submitting another request.", ""
+    
+    if not pdf_file or not job_url:
+        return "❌ Please provide both a PDF resume and job URL.", ""
+    
+    try:
+        # Extract text from PDF
+        with gr.Progress() as progress:
+            progress(0.1, desc="Extracting text from PDF...")
+            resume_text = extract_text_from_pdf(pdf_file)
+            
+            if "Error reading PDF" in resume_text:
+                return f"❌ {resume_text}", ""
+            
+            progress(0.3, desc="Setting up AI agents...")
+            researcher, resume_strategist, llm = setup_crewai()
+            
+            progress(0.5, desc="Creating optimization tasks...")
+            research_task, resume_task = create_tasks(researcher, resume_strategist, job_url, resume_text)
+            
+            progress(0.7, desc="Analyzing job requirements...")
+            # Execute tasks
+            from crewai import Crew
+            crew = Crew(
+                agents=[researcher, resume_strategist],
+                tasks=[research_task, resume_task],
+                verbose=False
+            )
+            
+            progress(0.9, desc="Generating tailored resume...")
+            result = crew.kickoff()
+            
+            progress(1.0, desc="Complete!")
+            
+            # Convert markdown to HTML for better display
+            html_result = markdown.markdown(str(result))
+            
+            return "✅ Resume successfully tailored!", html_result
+            
+    except Exception as e:
+        return f"❌ Error processing your request: {str(e)}", ""
+
+def create_interface():
+    """Create the Gradio interface."""
+    
+    with gr.Blocks(
+        title="CV Tailor - AI Resume Optimizer",
+        theme=gr.themes.Soft(),
+        css="""
+        .gradio-container {
+            max-width: 1200px;
+            margin: auto;
+        }
+        .header {
+            text-align: center;
+            margin-bottom: 30px;
+        }
+        .rate-limit-info {
+            background-color: #f0f8ff;
+            padding: 10px;
+            border-radius: 5px;
+            margin-bottom: 20px;
+        }
+        """
+    ) as app:
+        
+        gr.HTML("""
+        <div class="header">
+            <h1>🎯 CV Tailor - AI Resume Optimizer</h1>
+            <p>Upload your PDF resume and job URL to get an AI-tailored resume that matches the job requirements!</p>
+        </div>
+        """)
+        
+        gr.HTML("""
+        <div class="rate-limit-info">
+            <strong>⚡ Rate Limit:</strong> 3 requests per 5 minutes to manage API costs. 
+            Please be patient and make each request count!
+        </div>
+        """)
+        
+        with gr.Row():
+            with gr.Column(scale=1):
+                pdf_input = gr.File(
+                    label="📄 Upload Your Resume (PDF)",
+                    file_types=[".pdf"],
+                    file_count="single"
+                )
+                
+                job_url_input = gr.Textbox(
+                    label="🔗 Job Posting URL",
+                    placeholder="https://company.com/jobs/position",
+                    lines=1
+                )
+                
+                submit_btn = gr.Button(
+                    "🚀 Generate Tailored Resume",
+                    variant="primary",
+                    size="lg"
+                )
+                
+                # Examples
+                gr.Examples(
+                    examples=[
+                        ["https://jobs.lever.co/example-company/software-engineer"],
+                        ["https://www.linkedin.com/jobs/view/example-job-id"],
+                        ["https://careers.google.com/jobs/results/example-position"]
+                    ],
+                    inputs=job_url_input,
+                    label="📝 Example Job URLs"
+                )
+            
+            with gr.Column(scale=2):
+                status_output = gr.Textbox(
+                    label="📊 Status",
+                    interactive=False,
+                    lines=1
+                )
+                
+                result_output = gr.HTML(
+                    label="📋 Tailored Resume",
+                    value="Your optimized resume will appear here..."
+                )
+        
+        # Event handlers
+        submit_btn.click(
+            fn=process_application,
+            inputs=[pdf_input, job_url_input, gr.State(lambda: str(time.time()))],
+            outputs=[status_output, result_output]
+        )
+        
+        # Footer
+        gr.HTML("""
+        <div style="text-align: center; margin-top: 50px; color: #666;">
+            <p>Powered by CrewAI & OpenAI GPT-4o Mini | 
+            <a href="https://github.com/joaomdmoura/crewAI" target="_blank">CrewAI</a> | 
+            Built with ❤️ using Gradio</p>
+        </div>
+        """)
+    
+    return app
+
+# Requirements for requirements.txt
+requirements_txt = """
+crewai==0.28.8
+crewai-tools==0.1.6
+langchain-openai==0.1.7
+langchain-community==0.0.29
+gradio==4.20.0
+PyPDF2==3.0.1
+markdown==3.5.2
+python-dotenv==1.0.0
+"""
+
+# Create the app
+if __name__ == "__main__":
+    # Set up environment variables
+    # In Hugging Face Spaces, set these in the Settings > Variables section
+    if not os.getenv("OPENAI_API_KEY"):
+        print("��️ Warning: OPENAI_API_KEY not found in environment variables")
+    
+    app = create_interface()
+    app.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        show_api=False,
+        share=False
+    )