feat: Add CV Markdown to PDF converter with MCP integration

- Implement Gradio-based web application for converting markdown to PDF
- Add MCP function registration for AI assistant integration
- Include sample CV and formatting instructions
- Fix lambda registration issue and use API base URL from environment variable
- Update README with detailed project documentation
- Configure proper requirements and gitignore files

.gitignore

@@ -0,0 +1,7 @@
+.env
+*.pyc
+__pycache__/
+.DS_Store
+*.pdf
+*.backup
+Task.md

Instructions.md

@@ -0,0 +1,110 @@
+# 📋 CV Formatting Instructions
+
+## YAML Front Matter (Required)
+Start your CV with YAML metadata enclosed in triple dashes:
+```yaml
+---
+name: Your Full Name
+header:
+  - text: |
+      <span style="font-size: 1.2em; font-weight: bold;">Your Job Title</span>
+  - text: <span class="iconify" data-icon="tabler:phone"></span> (555) 123-4567
+    newLine: true
+  - text: <span class="iconify" data-icon="tabler:mail"></span> your.email@domain.com
+    link: mailto:your.email@domain.com
+  - text: <span class="iconify" data-icon="tabler:brand-linkedin"></span> LinkedIn
+    link: https://linkedin.com/in/yourprofile
+  - text: <span class="iconify" data-icon="tabler:brand-github"></span> GitHub
+    link: https://github.com/yourusername
+---
+```
+
+## Special Formatting Tags
+
+### Level 2 Headers (Company/Institution Names)
+- Use `[L2]Company Name[/L2]` for company names
+- Use `[L2R]Location[/L2R]` for right-aligned location information
+- Example: `[L2]Example Corp[/L2] [L2R]City, State[/L2R]`
+
+### Level 3 Headers (Job Titles/Degrees)
+- Use `[L3]Job Title[/L3]` for job titles or degree names
+- Use `[L3R]Date Range[/L3R]` for right-aligned date information
+- Example: `[L3]Senior Software Engineer[/L3] [L3R]Oct 2020 - Present[/L3R]`
+
+## Section Structure
+
+### Experience Section
+```markdown
+## Experience
+
+[L2]Company Name[/L2] [L2R]City, State[/L2R]
+
+[L3]Job Title[/L3] [L3R]Start Date - End Date[/L3R]
+
+- Bullet point describing achievement or responsibility
+- Another bullet point with specific impact
+- Use action verbs and quantify results when possible
+```
+
+### Education Section
+```markdown
+## Education
+
+[L2]University Name[/L2] GPA X.XX [L2R]City, State[/L2R]
+[L3]Degree Name[/L3] [L3R]Start Year - End Year[/L3R]
+```
+
+### Skills Section
+Use HTML `<br>` tags for line breaks and organize by categories:
+```markdown
+## Skills
+
+**Category 1:** Skill1, Skill2, Skill3, <strong>Highlighted Skill</strong>
+<br>
+**Category 2:** More skills here
+<br>
+**Category 3:** Additional skills
+```
+
+### Certifications Section
+```markdown
+## Certifications
+
+- Certificate Name [<span class="iconify" data-icon="mdi:open-in-new"></span>](certificate-url)
+- Certificate without link
+```
+
+## Icons and Styling
+
+### Contact Icons
+- Phone: `<span class="iconify" data-icon="tabler:phone"></span>`
+- Email: `<span class="iconify" data-icon="tabler:mail"></span>`
+- LinkedIn: `<span class="iconify" data-icon="tabler:brand-linkedin"></span>`
+- GitHub: `<span class="iconify" data-icon="tabler:brand-github"></span>`
+
+### External Link Icon
+- Use: `<span class="iconify" data-icon="mdi:open-in-new"></span>`
+
+### Text Styling
+- **Bold text:** Use `**text**` for category labels
+- *Emphasized text:* Use `<strong>text</strong>` for highlighting specific skills
+- Job titles should be styled with the [L3] tags, not markdown headers
+
+## Best Practices
+
+1. **Consistency:** Always use the same formatting patterns throughout
+2. **Alignment:** Use L2R and L3R tags for right-aligned content (dates, locations)
+3. **Icons:** Include relevant icons for contact information and external links
+4. **Bullet Points:** Use concise, action-oriented bullet points for experience
+5. **Categorization:** Group skills by relevant categories
+6. **Links:** Include clickable links for email, social profiles, and certificates
+7. **Spacing:** Use proper section breaks with `##` headers
+
+## Required Sections
+1. **YAML Front Matter** (name and header contact info)
+2. **Experience** (with L2/L3 formatting)
+3. **Education** (with L2/L3 formatting)  
+4. **Skills** (categorized with HTML breaks)
+5. **Certifications** (optional but recommended)
+
+This formatting ensures your CV will render properly in the PDF conversion system with consistent styling and professional appearance.

README.md

@@ -9,4 +9,16 @@ app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 📄 CV MCP - Markdown to PDF Converter
+
+A Gradio-based web application that converts markdown text to PDF using an external API service. This app provides a clean, two-panel interface where users can input markdown on the left and receive a professionally formatted PDF on the right.
+
+## 🌟 Features
+
+- **Two-Panel Interface**: Clean split layout with markdown input on the left and PDF output on the right
+- **Real-time Conversion**: Click "Convert to PDF" button to process your markdown
+- **External API Integration**: Uses the Nirav Madhani Resume Server API for HTML conversion
+- **PDF Generation**: Converts API-returned HTML to PDF using xhtml2pdf library
+- **Example Templates**: Pre-built markdown examples for quick testing
+- **Responsive Design**: Modern, user-friendly interface built with Gradio
+

Sample.md

@@ -0,0 +1,58 @@
+---
+name: Jane Smith
+header:
+  - text: |
+      <span style="font-size: 1.2em; font-weight: bold;">Software Engineer</span>
+  - text: <span class="iconify" data-icon="tabler:phone"></span> (555) 123-4567
+    newLine: true
+  - text: <span class="iconify" data-icon="tabler:mail"></span> fname.lastname@email.com
+    link: mailto:jane.smith@email.com
+  - text: <span class="iconify" data-icon="tabler:brand-linkedin"></span> LinkedIn
+    link: https://linkedin.com/in/firstnamelastname
+  - text: <span class="iconify" data-icon="tabler:brand-github"></span> GitHub
+    link: https://github.com/firstnamelastname
+---
+
+## Experience
+
+[L2]Example Corp[/L2] [L2R]City, State[/L2R]
+
+[L3]Senior Software Engineer[/L3] [L3R]Oct 2020 - Present[/L3R]
+
+- Developed and maintained critical systems.
+- Led a team of junior developers.
+
+[L3]Junior Software Engineer[/L3] [L3R]Jan 2018 - Oct 2020[/L3R]
+
+- Developed and maintained critical systems.
+- Led a team of junior developers.
+
+## Education
+
+[L2]State University[/L2] GPA 3.75 [L2R]Anytown, USA[/L2R]
+[L3]B.S. in Computer Science[/L3] [L3R]2012 - 2016[/L3R]
+
+## Skills
+
+**Programming Languages:** Python, Java, JavaScript/TypeScript, C++, Go, SQL, C#
+<br>
+**Frameworks/Libraries:** Spring Boot, React (Hooks), Node.js (Express.js), FastAPI, Django/Flask, Pandas, NumPy, TensorFlow, Keras, MXNet, LangChain, Unity, <strong>SMOL Agents</strong>
+<br>
+**Databases & Caching:** PostgreSQL, MySQL, MongoDB, Redis, Elasticsearch, Pinecone (Vector DBs), Azure SQL
+<br>
+**Cloud & DevOps:** Azure (App Service, AKS, AI Services, Monitor, VNet), AWS, GCP, Docker, Kubernetes, Terraform, CI/CD (GitHub Actions), IaC
+<br>
+**Machine Learning & AI:** LLMs, NLP, RAG, Prompt Engineering, Semantic Search, Generative AI, Deep Learning (CNN, GAN, ResNet, SRGAN), TensorFlow, Keras, MXNet, Spark, MLOps
+<br>
+**APIs & Communication:** RESTful APIs, OAuth2, JWT, gRPC, GraphQL
+<br>
+**Tools & Methodologies:** Git, Agile (Scrum), Jira, TDD, Performance Optimization, Scalability, GitHub Copilot, Playwright, Snyk, bs4, lxml
+
+## Certifications
+
+- Certificate 1 [<span class="iconify" data-icon="mdi:open-in-new"></span>](https://certificates.example.com/certificate-1)
+- Certificate 2  
+- Certificate 3 [<span class="iconify" data-icon="mdi:open-in-new"></span>](https://certificates.example.com/certificate-3)
+- Certificate 4 [<span class="iconify" data-icon="mdi:open-in-new"></span>](https://certificates.example.com/certificate-4)
+- Certificate 5 [<span class="iconify" data-icon="mdi:open-in-new"></span>](https://certificates.example.com/certificate-5)
+- Certificate 6 [<span class="iconify" data-icon="mdi:open-in-new"></span>](https://certificates.example.com/certificate-6)

app.py

@@ -0,0 +1,260 @@
+import gradio as gr
+import requests
+import os
+from dotenv import load_dotenv
+import tempfile
+
+# Load environment variables
+load_dotenv()
+
+def get_sample_cv():
+    """
+    Return the sample CV markdown content for reference
+    """
+    try:
+        with open('Sample.md', 'r', encoding='utf-8') as f:
+            return f.read()
+    except FileNotFoundError:
+        return "Sample.md file not found in the current directory."
+    except Exception as e:
+        return f"Error reading Sample.md: {str(e)}"
+
+def get_cv_formatting_instructions():
+    """
+    Return detailed CV formatting instructions from external markdown file
+    """
+    try:
+        with open('Instructions.md', 'r', encoding='utf-8') as f:
+            return f.read()
+    except FileNotFoundError:
+        return "Instructions.md file not found in the current directory."
+    except Exception as e:
+        return f"Error reading Instructions.md: {str(e)}"
+
+def convert_markdown_to_pdf(markdown_text):
+    """
+    Convert markdown text to PDF and HTML using the external API endpoints
+    
+    Args:
+        markdown_text (str): The markdown text to convert
+        
+    Returns:
+        tuple: (pdf_path, html_content, status_message)
+    """
+    if not markdown_text.strip():
+        return None, "", "Please enter some markdown text."
+    
+    # Get bearer token from environment
+    bearer_token = os.getenv('BEARER_TOKEN')
+    if not bearer_token or bearer_token == 'your_bearer_token_here':
+        return None, "", "❌ Bearer token not configured. Please set BEARER_TOKEN in .env file."
+    
+    try:
+        headers = {
+            'Authorization': f'Bearer {bearer_token}',
+            'Content-Type': 'text/markdown'
+        }
+        
+        # Get base URL from environment
+        base_url = os.getenv('API_BASE_URL', 'https://nirav-madhani-resume-server.hf.space')
+        
+        # Get PDF directly from API
+        pdf_url = f"{base_url}/convert/pdf"
+        print(f"📡 Making request to {pdf_url}")
+        pdf_response = requests.post(pdf_url, data=markdown_text, headers=headers, timeout=30)
+        
+        if pdf_response.status_code != 200:
+            return None, "", f"❌ PDF API request failed with status {pdf_response.status_code}: {pdf_response.text}"
+        
+        # Save PDF to temporary file
+        with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf', mode='w+b') as temp_pdf:
+            temp_pdf.write(pdf_response.content)
+            pdf_path = temp_pdf.name
+        
+        # Get HTML for preview
+        html_url = f"{base_url}/convert/html"
+        print(f"📡 Making request to {html_url}")
+        html_response = requests.post(html_url, data=markdown_text, headers=headers, timeout=30)
+        
+        if html_response.status_code != 200:
+            # PDF worked but HTML failed - still return PDF
+            return pdf_path, "", f"✅ PDF generated successfully! (HTML preview failed: {html_response.status_code})"
+        
+        html_content = html_response.text
+        return pdf_path, html_content, "✅ PDF and HTML generated successfully via API!"
+            
+    except requests.exceptions.RequestException as e:
+        return None, "", f"❌ Network error: {str(e)}"
+    except Exception as e:
+        return None, "", f"❌ Error generating PDF: {str(e)}"
+
+def process_conversion(markdown_text):
+    """
+    Process the markdown conversion and return results for Gradio interface
+    
+    Args:
+        markdown_text (str): The markdown text to convert
+        
+    Returns:
+        tuple: (pdf_file_path, html_content, status_message)
+    """
+    pdf_path, html_content, message = convert_markdown_to_pdf(markdown_text)
+    return pdf_path, html_content, message
+
+# MCP Tool Functions (callable by AI assistants)
+def mcp_get_sample_cv():
+    """MCP tool: Get sample CV markdown
+    
+    Returns:
+        str: The sample CV markdown content
+    """
+    return get_sample_cv()
+
+def mcp_get_cv_instructions():
+    """MCP tool: Get CV formatting instructions
+    
+    Returns:
+        str: The CV formatting instructions
+    """
+    return get_cv_formatting_instructions()
+
+def mcp_convert_cv(markdown_text: str):
+    """MCP tool: Convert CV markdown to PDF
+    
+    Args:
+        markdown_text (str): The markdown text to convert to PDF
+        
+    Returns:
+        str: The conversion result message
+    """
+    pdf_path, html_content, message = process_conversion(markdown_text)
+    return f"Conversion result: {message}"
+
+# Create Gradio interface
+with gr.Blocks(title="CV Markdown to PDF Converter", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 📄 CV Markdown to PDF Converter")
+    gr.Markdown("Convert your CV markdown to professional PDF format. Use the Instructions & Sample tab to learn the proper formatting.")
+    
+    with gr.Tabs():
+        with gr.TabItem("🚀 Convert CV"):
+            with gr.Row():
+                with gr.Column(scale=1):
+                    gr.Markdown("## Input")
+                    markdown_input = gr.Textbox(
+                        label="CV Markdown Text",
+                        placeholder="Enter your CV markdown here... (see Instructions & Sample tab for formatting guide)",
+                        lines=20,
+                        max_lines=30
+                    )
+                
+                with gr.Column(scale=1):
+                    gr.Markdown("## Output")
+                    
+                    with gr.Tabs():
+                        with gr.TabItem("📄 PDF Download"):
+                            pdf_output = gr.File(
+                                label="Generated PDF",
+                                file_types=[".pdf"]
+                            )
+                        
+                        with gr.TabItem("🌐 HTML Preview"):
+                            html_output = gr.HTML(
+                                label="HTML Preview",
+                                value="HTML preview will appear here after conversion..."
+                            )
+                    
+                    status_message = gr.Textbox(
+                        label="Status",
+                        interactive=False,
+                        lines=2
+                    )
+            
+            with gr.Row():
+                convert_btn = gr.Button("🚀 Convert to PDF", variant="primary", size="lg")
+            
+            # Event handler
+            convert_btn.click(
+                fn=process_conversion,
+                inputs=[markdown_input],
+                outputs=[pdf_output, html_output, status_message]
+            )
+        
+        with gr.TabItem("📋 Instructions & Sample"):
+            with gr.Tabs():
+                with gr.TabItem("📖 Formatting Instructions"):
+                    gr.Markdown(get_cv_formatting_instructions())
+                
+                with gr.TabItem("📄 Sample CV"):
+                    gr.Markdown("## Sample CV Markdown")
+                    gr.Markdown("Below is a complete sample CV showing all the formatting patterns:")
+                    
+                    sample_cv_display = gr.Code(
+                        value=get_sample_cv(),
+                        language="markdown",
+                        label="Sample CV Markdown Code",
+                        lines=30,
+                        max_lines=50
+                    )
+                    
+                    copy_sample_btn = gr.Button("📋 Copy Sample to Converter", variant="secondary")
+                    
+                    # Copy sample to main input
+                    copy_sample_btn.click(
+                        fn=get_sample_cv,
+                        outputs=[markdown_input]
+                    )
+    
+    # Example CV templates
+    with gr.Row():
+        gr.Examples(
+            examples=[
+                [get_sample_cv()],
+                ["""---
+name: John Doe
+header:
+  - text: |
+      <span style="font-size: 1.2em; font-weight: bold;">Full Stack Developer</span>
+  - text: <span class="iconify" data-icon="tabler:phone"></span> (555) 987-6543
+    newLine: true
+  - text: <span class="iconify" data-icon="tabler:mail"></span> john.doe@email.com
+    link: mailto:john.doe@email.com
+---
+
+## Experience
+
+[L2]Tech Startup Inc.[/L2] [L2R]San Francisco, CA[/L2R]
+
+[L3]Full Stack Developer[/L3] [L3R]Jan 2022 - Present[/L3R]
+
+- Designed and implemented scalable web applications serving 10K+ users
+- Reduced page load times by 40% through optimization techniques
+- Led migration from monolith to microservices architecture
+
+## Education
+
+[L2]University of California[/L2] GPA 3.8 [L2R]Berkeley, CA[/L2R]
+[L3]B.S. in Computer Science[/L3] [L3R]2018 - 2022[/L3R]
+
+## Skills
+
+**Programming:** Python, JavaScript, TypeScript, Java
+<br>
+**Frameworks:** React, Node.js, Django, Spring Boot
+<br>
+**Databases:** PostgreSQL, MongoDB, Redis
+"""],
+            ],
+            inputs=[markdown_input],
+            label="📝 CV Templates"
+        )
+    
+    # Register MCP tools
+    gr.api(mcp_get_sample_cv)
+    gr.api(mcp_get_cv_instructions)
+    gr.api(mcp_convert_cv)
+
+# Launch the app with MCP enabled
+if __name__ == "__main__":
+    demo.launch(
+        mcp_server=True
+    )