Create app.py

app.py

@@ -0,0 +1,280 @@
+import gradio as gr
+import os
+from semantic_search import CVSemanticSearch
+import logging
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Initialize the semantic search system
+cv_search = CVSemanticSearch()
+
+def upload_cvs(files):
+    """
+    Handle CV uploads from Gradio
+    
+    Args:
+        files: List of uploaded files from Gradio
+        
+    Returns:
+        Status message
+    """
+    if not files:
+        return "No files uploaded."
+    
+    successful = 0
+    total = len(files)
+    
+    for file in files:
+        try:
+            # Read file content
+            with open(file.name, 'rb') as f:
+                file_content = f.read()
+            
+            # Get filename from path
+            filename = os.path.basename(file.name)
+            
+            # Add to database
+            if cv_search.add_cv_to_database(file_content, filename):
+                successful += 1
+                logger.info(f"Successfully uploaded: {filename}")
+            else:
+                logger.error(f"Failed to upload: {filename}")
+                
+        except Exception as e:
+            logger.error(f"Error processing file {file.name}: {str(e)}")
+    
+    db_info = cv_search.get_database_info()
+    
+    return f"""
+    Upload Complete!
+    ✅ Successfully processed: {successful}/{total} files
+    📊 Database now contains: {db_info['unique_cvs']} CVs ({db_info['total_chunks']} chunks)
+    
+    CVs in database: {', '.join(db_info['cv_filenames'])}
+    """
+
+def search_matching_cvs(job_description, num_results):
+    """
+    Search for CVs matching the job description
+    
+    Args:
+        job_description: Job description text
+        num_results: Number of results to return
+        
+    Returns:
+        Formatted search results
+    """
+    if not job_description.strip():
+        return "Please enter a job description."
+    
+    # Get database info
+    db_info = cv_search.get_database_info()
+    
+    if db_info['unique_cvs'] == 0:
+        return "No CVs in database. Please upload some CV PDFs first."
+    
+    # Perform search
+    results = cv_search.search_cvs(job_description, top_k=num_results)
+    
+    if not results:
+        return "No matching CVs found."
+    
+    # Format results
+    output = f"🎯 **Top {len(results)} Matching CVs:**\n\n"
+    
+    for i, cv in enumerate(results, 1):
+        similarity_percentage = cv['weighted_score'] * 100
+        
+        output += f"""
+**{i}. {cv['filename']}**
+- **Match Score**: {similarity_percentage:.1f}%
+- **Max Similarity**: {cv['max_similarity']*100:.1f}%
+- **Avg Similarity**: {cv['avg_similarity']*100:.1f}%
+- **Chunks Analyzed**: {cv['chunk_count']}
+- **Best Match Preview**: {cv['best_match_text']}
+
+---
+        """
+    
+    return output
+
+def get_database_status():
+    """
+    Get current database status
+    
+    Returns:
+        Database information as formatted string
+    """
+    db_info = cv_search.get_database_info()
+    
+    if db_info['unique_cvs'] == 0:
+        return "📁 Database is empty. Upload some CV PDFs to get started!"
+    
+    return f"""
+    📊 **Database Status:**
+    - **Total CVs**: {db_info['unique_cvs']}
+    - **Total Chunks**: {db_info['total_chunks']}
+    - **CVs in Database**: {', '.join(db_info['cv_filenames'])}
+    """
+
+def clear_database():
+    """
+    Clear the entire database
+    
+    Returns:
+        Status message
+    """
+    if cv_search.clear_database():
+        return "🗑️ Database cleared successfully!"
+    else:
+        return "❌ Error clearing database."
+
+# Create Gradio interface
+def create_interface():
+    """Create and return the Gradio interface"""
+    
+    with gr.Blocks(
+        title="CV Semantic Search",
+        theme=gr.themes.Soft(),
+        css="""
+        .container { max-width: 1200px; margin: auto; }
+        .upload-section { background: #f8f9fa; padding: 20px; border-radius: 10px; margin: 10px 0; }
+        .search-section { background: #e8f5e8; padding: 20px; border-radius: 10px; margin: 10px 0; }
+        .status-section { background: #fff3cd; padding: 15px; border-radius: 8px; margin: 10px 0; }
+        """
+    ) as demo:
+        
+        gr.Markdown("""
+        # 🔍 CV Semantic Search System
+        
+        Upload CV PDFs and search for the best matches based on job descriptions using AI-powered semantic search.
+        """)
+        
+        with gr.Row():
+            with gr.Column(scale=1):
+                # Upload Section
+                with gr.Group():
+                    gr.Markdown("## 📁 Upload CVs")
+                    
+                    cv_files = gr.File(
+                        label="Upload CV PDFs",
+                        file_count="multiple",
+                        file_types=[".pdf"],
+                        elem_classes=["upload-section"]
+                    )
+                    
+                    upload_btn = gr.Button(
+                        "Upload CVs to Database",
+                        variant="primary",
+                        size="lg"
+                    )
+                    
+                    upload_output = gr.Markdown(
+                        "Upload CVs to build your searchable database.",
+                        elem_classes=["status-section"]
+                    )
+            
+            with gr.Column(scale=1):
+                # Search Section  
+                with gr.Group():
+                    gr.Markdown("## 🎯 Search CVs")
+                    
+                    job_description = gr.Textbox(
+                        label="Job Description",
+                        placeholder="Enter the job description here...\n\nExample: Looking for a senior software engineer with 5+ years experience in Python, React, and cloud technologies. Strong background in microservices and API development required.",
+                        lines=6,
+                        elem_classes=["search-section"]
+                    )
+                    
+                    num_results = gr.Slider(
+                        label="Number of Results",
+                        minimum=1,
+                        maximum=10,
+                        value=5,
+                        step=1
+                    )
+                    
+                    search_btn = gr.Button(
+                        "Search Matching CVs",
+                        variant="secondary",
+                        size="lg"
+                    )
+        
+        # Search Results
+        with gr.Row():
+            search_output = gr.Markdown(
+                "Enter a job description and click search to find matching CVs.",
+                elem_classes=["search-section"]
+            )
+        
+        # Database Management
+        with gr.Row():
+            with gr.Column(scale=2):
+                status_output = gr.Markdown(
+                    get_database_status(),
+                    elem_classes=["status-section"]
+                )
+            
+            with gr.Column(scale=1):
+                with gr.Group():
+                    refresh_btn = gr.Button("🔄 Refresh Status", size="sm")
+                    clear_btn = gr.Button("🗑️ Clear Database", size="sm", variant="stop")
+        
+        # Event handlers
+        upload_btn.click(
+            fn=upload_cvs,
+            inputs=[cv_files],
+            outputs=[upload_output]
+        ).then(
+            fn=get_database_status,
+            outputs=[status_output]
+        )
+        
+        search_btn.click(
+            fn=search_matching_cvs,
+            inputs=[job_description, num_results],
+            outputs=[search_output]
+        )
+        
+        refresh_btn.click(
+            fn=get_database_status,
+            outputs=[status_output]
+        )
+        
+        clear_btn.click(
+            fn=clear_database,
+            outputs=[status_output]
+        ).then(
+            fn=get_database_status,
+            outputs=[status_output]
+        )
+        
+        # Example usage
+        gr.Markdown("""
+        ## 📝 How to Use:
+        
+        1. **Upload CVs**: Use the file upload component to add multiple PDF CVs to the database
+        2. **Enter Job Description**: Paste or type the job requirements you want to match
+        3. **Search**: Click search to find the top matching CVs based on semantic similarity
+        4. **Review Results**: See ranked CVs with similarity scores and preview text
+        
+        ### 💡 Tips for Better Results:
+        - Include specific skills, technologies, and requirements in your job description
+        - The more detailed your job description, the better the matching accuracy
+        - The system analyzes semantic meaning, not just keyword matching
+        - Upload multiple CVs for better comparison and ranking
+        """)
+    
+    return demo
+
+# Main function to run the app
+if __name__ == "__main__":
+    demo = create_interface()
+    demo.launch(
+        share=True,  # Enable sharing for Hugging Face Spaces
+        server_name="0.0.0.0",  # Enable access from outside container
+        server_port=7860,  # Standard port for Hugging Face Spaces
+        show_error=True
+    )