Add document comparison, bulk validation, and projects features

.gitignore

@@ -44,3 +44,18 @@ Thumbs.db
 
 
 extracted_images_log/
+
+# Virtual environments (local)
+validatorvenv/
+
+# SQLite database (local data)
+projects.db
+
+# Debug/test files
+debug_*.py
+analyze_*.py
+
+# Test documents
+*.pdf
+*.docx
+*.pptx

app/database.py

@@ -0,0 +1,190 @@
+"""
+SQLite database layer for Projects feature.
+Manages projects and validation history.
+"""
+
+import sqlite3
+import json
+import logging
+from datetime import datetime
+from pathlib import Path
+from typing import List, Dict, Optional, Any
+
+logger = logging.getLogger(__name__)
+
+
+class ProjectDatabase:
+    """Database manager for projects and validations."""
+    
+    def __init__(self, db_path: str = "projects.db"):
+        """Initialize database connection and create tables if needed."""
+        self.db_path = db_path
+        self._init_database()
+    
+    def _init_database(self):
+        """Create tables if they don't exist."""
+        with sqlite3.connect(self.db_path) as conn:
+            cursor = conn.cursor()
+            
+            # Projects table
+            cursor.execute("""
+                CREATE TABLE IF NOT EXISTS projects (
+                    id INTEGER PRIMARY KEY AUTOINCREMENT,
+                    name TEXT NOT NULL UNIQUE,
+                    description TEXT,
+                    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+                )
+            """)
+            
+            # Validations table
+            cursor.execute("""
+                CREATE TABLE IF NOT EXISTS validations (
+                    id INTEGER PRIMARY KEY AUTOINCREMENT,
+                    project_id INTEGER,
+                    validation_type TEXT NOT NULL,
+                    template_key TEXT,
+                    filename TEXT,
+                    status TEXT,
+                    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+                    results_json TEXT,
+                    FOREIGN KEY (project_id) REFERENCES projects(id) ON DELETE CASCADE
+                )
+            """)
+            
+            conn.commit()
+            logger.info(f"Database initialized at {self.db_path}")
+    
+    # Project CRUD operations
+    
+    def create_project(self, name: str, description: str = "") -> int:
+        """Create a new project."""
+        with sqlite3.connect(self.db_path) as conn:
+            cursor = conn.cursor()
+            try:
+                cursor.execute(
+                    "INSERT INTO projects (name, description) VALUES (?, ?)",
+                    (name, description)
+                )
+                conn.commit()
+                project_id = cursor.lastrowid
+                logger.info(f"Created project: {name} (ID: {project_id})")
+                return project_id
+            except sqlite3.IntegrityError:
+                raise ValueError(f"Project '{name}' already exists")
+    
+    def list_projects(self) -> List[Dict[str, Any]]:
+        """List all projects."""
+        with sqlite3.connect(self.db_path) as conn:
+            conn.row_factory = sqlite3.Row
+            cursor = conn.cursor()
+            cursor.execute("""
+                SELECT p.*, COUNT(v.id) as validation_count
+                FROM projects p
+                LEFT JOIN validations v ON p.id = v.project_id
+                GROUP BY p.id
+                ORDER BY p.created_at DESC
+            """)
+            projects = [dict(row) for row in cursor.fetchall()]
+            return projects
+    
+    def get_project(self, project_id: int) -> Optional[Dict[str, Any]]:
+        """Get a specific project by ID."""
+        with sqlite3.connect(self.db_path) as conn:
+            conn.row_factory = sqlite3.Row
+            cursor = conn.cursor()
+            cursor.execute("""
+                SELECT p.*, COUNT(v.id) as validation_count
+                FROM projects p
+                LEFT JOIN validations v ON p.id = v.project_id
+                WHERE p.id = ?
+                GROUP BY p.id
+            """, (project_id,))
+            row = cursor.fetchone()
+            return dict(row) if row else None
+    
+    def delete_project(self, project_id: int) -> bool:
+        """Delete a project and all associated validations."""
+        with sqlite3.connect(self.db_path) as conn:
+            cursor = conn.cursor()
+            cursor.execute("DELETE FROM projects WHERE id = ?", (project_id,))
+            conn.commit()
+            deleted = cursor.rowcount > 0
+            if deleted:
+                logger.info(f"Deleted project ID: {project_id}")
+            return deleted
+    
+    # Validation operations
+    
+    def save_validation(
+        self,
+        project_id: Optional[int],
+        validation_type: str,
+        filename: str,
+        status: str,
+        results: Dict[str, Any],
+        template_key: Optional[str] = None
+    ) -> int:
+        """Save a validation result to a project."""
+        with sqlite3.connect(self.db_path) as conn:
+            cursor = conn.cursor()
+            cursor.execute("""
+                INSERT INTO validations 
+                (project_id, validation_type, template_key, filename, status, results_json)
+                VALUES (?, ?, ?, ?, ?, ?)
+            """, (
+                project_id,
+                validation_type,
+                template_key,
+                filename,
+                status,
+                json.dumps(results)
+            ))
+            conn.commit()
+            validation_id = cursor.lastrowid
+            logger.info(f"Saved {validation_type} validation (ID: {validation_id}) to project {project_id}")
+            return validation_id
+    
+    def get_project_validations(self, project_id: int) -> List[Dict[str, Any]]:
+        """Get all validations for a specific project."""
+        with sqlite3.connect(self.db_path) as conn:
+            conn.row_factory = sqlite3.Row
+            cursor = conn.cursor()
+            cursor.execute("""
+                SELECT * FROM validations
+                WHERE project_id = ?
+                ORDER BY created_at DESC
+            """, (project_id,))
+            validations = []
+            for row in cursor.fetchall():
+                validation = dict(row)
+                # Parse JSON results
+                if validation['results_json']:
+                    validation['results'] = json.loads(validation['results_json'])
+                    del validation['results_json']
+                validations.append(validation)
+            return validations
+    
+    def get_recent_validations(self, limit: int = 50) -> List[Dict[str, Any]]:
+        """Get recent validations across all projects."""
+        with sqlite3.connect(self.db_path) as conn:
+            conn.row_factory = sqlite3.Row
+            cursor = conn.cursor()
+            cursor.execute("""
+                SELECT v.*, p.name as project_name
+                FROM validations v
+                LEFT JOIN projects p ON v.project_id = p.id
+                ORDER BY v.created_at DESC
+                LIMIT ?
+            """, (limit,))
+            validations = []
+            for row in cursor.fetchall():
+                validation = dict(row)
+                if validation['results_json']:
+                    validation['results'] = json.loads(validation['results_json'])
+                    del validation['results_json']
+                validations.append(validation)
+            return validations
+
+
+# Global database instance
+db = ProjectDatabase()

app/main.py

@@ -7,7 +7,7 @@ To run this application:
 3. Run the server: uvicorn app.main:app --reload
 """
 
-from fastapi import FastAPI, File, UploadFile, HTTPException, Query
+from fastapi import FastAPI, File, UploadFile, HTTPException, Query, Form
 from fastapi.responses import JSONResponse, HTMLResponse, FileResponse
 from fastapi.staticfiles import StaticFiles
 from pydantic import BaseModel
@@ -28,7 +28,9 @@ logging.basicConfig(
 logger = logging.getLogger(__name__)
 
 from app.validator import Validator, load_templates, get_template, extract_images_from_document
+from app.database import db
 
+# Load environment variables
 app = FastAPI(
     title="Medical Document Validator API",
     description="API for validating medical documents against predefined templates using LLM",
@@ -65,7 +67,7 @@ class SpellCheckError(BaseModel):
     word: str
     context: str
     suggestions: List[str]
-    error_type: str  # "spelling", "grammar", "typo"
+    error_type: str  # "spelling", "grammar", "formatting", "typo"
     confidence: float
 
 
@@ -76,6 +78,15 @@ class SpellCheckReport(BaseModel):
     summary: str
 
 
+class LinkReport(BaseModel):
+    """Link validation report."""
+    url: str
+    status: str
+    status_code: int
+    message: str
+    page: str
+
+
 class ValidationReport(BaseModel):
     """Complete validation report response."""
     template_key: str
@@ -83,6 +94,68 @@ class ValidationReport(BaseModel):
     summary: str
     elements_report: List[ElementReport]
     spell_check: Optional[SpellCheckReport] = None  # Optional spell check results
+    link_report: Optional[List[LinkReport]] = None  # Optional link validation results
+
+
+class ComparisonChange(BaseModel):
+    """Individual change detected in comparison."""
+    type: str  # "addition", "deletion", "modification"
+    section: Optional[str] = None  # Section/area where change occurred
+    description: str  # Description of the change
+
+
+class ComparisonReport(BaseModel):
+    """Document comparison report."""
+    summary: str  # Natural language summary of changes
+    changes: List[ComparisonChange]  # Detailed list of changes
+    file1_name: str
+    file2_name: str
+
+
+class BulkValidationDetail(BaseModel):
+    """Individual validation result for bulk certificate validation."""
+    name: str
+    status: str  # "exact_match", "fuzzy_match", "missing", "extra"
+    certificate_file: Optional[str] = None
+    similarity: Optional[int] = None  # Percentage for fuzzy matches
+
+
+class BulkValidationResult(BaseModel):
+    """Bulk certificate validation result."""
+    total_names: int
+    total_certificates: int
+    exact_matches: int
+    fuzzy_matches: int
+    missing: int
+    extras: int
+    details: List[BulkValidationDetail]
+
+
+class Project(BaseModel):
+    """Project model."""
+    id: int
+    name: str
+    description: Optional[str] = ""
+    created_at: str
+    validation_count: int = 0
+
+
+class ProjectCreate(BaseModel):
+    """Project creation request."""
+    name: str
+    description: str = ""
+
+
+class ValidationHistory(BaseModel):
+    """Validation history item."""
+    id: int
+    project_id: Optional[int]
+    project_name: Optional[str]
+    validation_type: str
+    template_key: Optional[str]
+    filename: str
+    status: str
+    created_at: str
 
 
 # API Endpoints
@@ -131,7 +204,8 @@ async def get_templates():
 async def validate_document(
     file: UploadFile = File(..., description="Document file to validate (PDF, DOCX, or PPTX)"),
     template_key: str = Query(..., description="Template key to validate against"),
-    check_spelling: bool = Query(False, description="Enable spell checking (ignores proper names)")
+    check_spelling: bool = Query(False, description="Enable spell checking (ignores proper names)"),
+    custom_prompt: Optional[str] = Query(None, description="Optional custom instructions to adapt validation")
 ):
     """
     Validate a document against a specified template.
@@ -183,10 +257,11 @@ async def validate_document(
     
     # Perform validation
     try:
-        validation_report = validator.validate_document(
+        validation_report = await validator.validate_document(
             file_content=file_content,
             file_extension=file_extension,
-            template_key=template_key
+            template_key=template_key,
+            custom_prompt=custom_prompt
         )
         
         # Convert to Pydantic model for response validation
@@ -194,6 +269,11 @@ async def validate_document(
             ElementReport(**elem) for elem in validation_report.get("elements_report", [])
         ]
         
+        # Convert link report to Pydantic models
+        link_report = [
+            LinkReport(**link) for link in validation_report.get("link_report", [])
+        ]
+        
         # Perform spell checking if requested
         spell_check_result = None
         if check_spelling:
@@ -226,7 +306,8 @@ async def validate_document(
             status=validation_report.get("status", "FAIL"),
             summary=validation_report.get("summary", ""),
             elements_report=elements_report,
-            spell_check=spell_check_result
+            spell_check=spell_check_result,
+            link_report=link_report
         )
         
     except ValueError as e:
@@ -241,6 +322,91 @@ async def validate_document(
         )
 
 
+@app.post("/validate/spelling-only", tags=["Validation"])
+async def validate_spelling_only(
+    file: UploadFile = File(..., description="Document file to check spelling (PDF, DOCX, or PPTX)")
+):
+    """
+    Check spelling in a document without template validation.
+    
+    Args:
+        file: Uploaded document file (PDF, DOCX, or PPTX)
+    
+    Returns:
+        Spell check report only
+    
+    Raises:
+        400: Bad request (unsupported format)
+        422: Unprocessable entity (extraction failure)
+        500: Internal server error
+    """
+    # Validate file extension
+    filename = file.filename or ""
+    file_extension = Path(filename).suffix.lower()
+    supported_extensions = [".pdf", ".docx", ".pptx"]
+    
+    if file_extension not in supported_extensions:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Unsupported file format: {file_extension}. Supported formats: {', '.join(supported_extensions)}"
+        )
+    
+    # Read file content
+    try:
+        file_content = await file.read()
+        if not file_content:
+            raise HTTPException(
+                status_code=400,
+                detail="Uploaded file is empty"
+            )
+    except Exception as e:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Failed to read file: {str(e)}"
+        )
+    
+    # Extract text and perform spell checking only
+    try:
+        from app.validator import extract_document_text
+        
+        # Extract text from document
+        try:
+            document_text = extract_document_text(file_content, file_extension)
+        except Exception as e:
+            raise HTTPException(
+                status_code=422,
+                detail=f"Failed to extract text from document: {str(e)}"
+            )
+        
+        # Perform spell checking
+        spell_check_data = validator.check_spelling(document_text)
+        
+        # Convert to Pydantic model
+        spell_errors = [
+            SpellCheckError(**error) for error in spell_check_data.get("errors", [])
+        ]
+        spell_check_result = SpellCheckReport(
+            total_errors=spell_check_data.get("total_errors", 0),
+            errors=spell_errors,
+            summary=spell_check_data.get("summary", "")
+        )
+        
+        # Return spelling-only response
+        return {
+            "mode": "spelling_only",
+            "spell_check": spell_check_result
+        }
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Spell check failed: {str(e)}", exc_info=True)
+        raise HTTPException(
+            status_code=500,
+            detail=f"Internal server error during spell checking: {str(e)}"
+        )
+
+
 @app.get("/health", tags=["Health"])
 async def health_check():
     """Health check endpoint."""
@@ -408,6 +574,257 @@ async def debug_extract_images(
         )
 
 
+@app.post("/compare", response_model=ComparisonReport, tags=["Comparison"])
+async def compare_documents(
+    file1: UploadFile = File(..., description="First document (original version)"),
+    file2: UploadFile = File(..., description="Second document (modified version)")
+):
+    """
+    Compare two document versions using LLM to identify changes.
+    
+    Args:
+        file1: Original document
+        file2: Modified document
+    
+    Returns:
+        Comparison report with summary and detailed changes
+    """
+    # Validate file extensions
+    filename1 = file1.filename or ""
+    filename2 = file2.filename or ""
+    ext1 = Path(filename1).suffix.lower()
+    ext2 = Path(filename2).suffix.lower()
+    supported_extensions = [".pdf", ".docx", ".pptx"]
+    
+    if ext1 not in supported_extensions or ext2 not in supported_extensions:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Unsupported file format. Supported: {', '.join(supported_extensions)}"
+        )
+    
+    # Read file contents
+    try:
+        content1 = await file1.read()
+        content2 = await file2.read()
+        
+        if not content1 or not content2:
+            raise HTTPException(status_code=400, detail="One or both files are empty")
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Failed to read files: {str(e)}")
+    
+    # Perform comparison using validator
+    try:
+        comparison_result = await validator.compare_documents(
+            file1_content=content1,
+            file1_extension=ext1,
+            file1_name=filename1,
+            file2_content=content2,
+            file2_extension=ext2,
+            file2_name=filename2
+        )
+        
+        # Convert to Pydantic models
+        changes = [
+            ComparisonChange(**change) for change in comparison_result.get("changes", [])
+        ]
+        
+        return ComparisonReport(
+            summary=comparison_result.get("summary", "No summary available"),
+            changes=changes,
+            file1_name=filename1,
+            file2_name=filename2
+        )
+        
+    except Exception as e:
+        logger.error(f"Comparison failed: {str(e)}", exc_info=True)
+        raise HTTPException(
+            status_code=500,
+            detail=f"Comparison failed: {str(e)}"
+        )
+
+
+@app.post("/excel-columns", tags=["Bulk Validation"])
+async def get_excel_columns(file: UploadFile = File(...)):
+    """
+    Extract column headers from an Excel file.
+    
+    Args:
+        file: Excel file (.xlsx)
+    
+    Returns:
+        List of column names and row count
+    """
+    try:
+        import openpyxl
+        from io import BytesIO
+        
+        content = await file.read()
+        wb = openpyxl.load_workbook(BytesIO(content))
+        ws = wb.active
+        
+        # Get first row as headers
+        headers = []
+        for cell in ws[1]:
+            if cell.value:
+                headers.append(str(cell.value))
+        
+        row_count = ws.max_row - 1  # Exclude header row
+        
+        return {
+            "columns": headers,
+            "row_count": row_count
+        }
+    except Exception as e:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Failed to parse Excel file: {str(e)}"
+        )
+
+
+@app.post("/bulk-validate", response_model=BulkValidationResult, tags=["Bulk Validation"])
+async def bulk_validate_certificates(
+    excel_file: UploadFile = File(..., description="Excel file with names"),
+    name_column: str = Form(..., description="Column name containing names"),
+    certificate_files: List[UploadFile] = File(..., description="Certificate files (max 150)")
+):
+    """
+    Validate multiple certificates against an Excel list of names.
+    
+    Args:
+        excel_file: Excel file with attendee names
+        name_column: Column containing the names
+        certificate_files: List of certificate files to validate
+    
+    Returns:
+        Bulk validation results with matches, missing, and extras
+    """
+    if len(certificate_files) > 150:
+        raise HTTPException(
+            status_code=400,
+            detail="Maximum 150 certificates allowed"
+        )
+    
+    try:
+        # Read Excel file
+        excel_content = await excel_file.read()
+        
+        # Read all certificate files
+        cert_data = []
+        for cert_file in certificate_files:
+            content = await cert_file.read()
+            filename = cert_file.filename or "unknown"
+            ext = Path(filename).suffix.lower()
+            cert_data.append((filename, content, ext))
+        
+        # Call validator
+        result = await validator.bulk_validate_certificates(
+            excel_content=excel_content,
+            name_column=name_column,
+            certificate_data=cert_data
+        )
+        
+        # Convert to Pydantic models
+        details = [
+            BulkValidationDetail(**detail) for detail in result.get("details", [])
+        ]
+        
+        return BulkValidationResult(
+            total_names=result.get("total_names", 0),
+            total_certificates=result.get("total_certificates", 0),
+            exact_matches=result.get("exact_matches", 0),
+            fuzzy_matches=result.get("fuzzy_matches", 0),
+            missing=result.get("missing", 0),
+            extras=result.get("extras", 0),
+            details=details
+        )
+        
+    except Exception as e:
+        logger.error(f"Bulk validation failed: {str(e)}", exc_info=True)
+        raise HTTPException(
+            status_code=500,
+            detail=f"Bulk validation failed: {str(e)}"
+        )
+
+
+# ==================== PROJECTS ENDPOINTS ====================
+
+@app.get("/projects", response_model=List[Project], tags=["Projects"])
+async def list_projects():
+    """List all projects."""
+    try:
+        projects = db.list_projects()
+        return projects
+    except Exception as e:
+        logger.error(f"Failed to list projects: {str(e)}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@app.post("/projects", response_model=Project, tags=["Projects"])
+async def create_project(project: ProjectCreate):
+    """Create a new project."""
+    try:
+        project_id = db.create_project(project.name, project.description)
+        created_project = db.get_project(project_id)
+        return created_project
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Failed to create project: {str(e)}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@app.get("/projects/{project_id}", response_model=Project, tags=["Projects"])
+async def get_project(project_id: int):
+    """Get a specific project."""
+    try:
+        project = db.get_project(project_id)
+        if not project:
+            raise HTTPException(status_code=404, detail="Project not found")
+        return project
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Failed to get project: {str(e)}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@app.delete("/projects/{project_id}", tags=["Projects"])
+async def delete_project(project_id: int):
+    """Delete a project."""
+    try:
+        deleted = db.delete_project(project_id)
+        if not deleted:
+            raise HTTPException(status_code=404, detail="Project not found")
+        return {"message": "Project deleted successfully"}
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Failed to delete project: {str(e)}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@app.get("/projects/{project_id}/validations", tags=["Projects"])
+async def get_project_validations(project_id: int):
+    """Get all validations for a project."""
+    try:
+        validations = db.get_project_validations(project_id)
+        return validations
+    except Exception as e:
+        logger.error(f"Failed to get project validations: {str(e)}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@app.get("/validations/recent", tags=["Projects"])
+async def get_recent_validations(limit: int = Query(50, ge=1, le=200)):
+    """Get recent validations across all projects."""
+    try:
+        validations = db.get_recent_validations(limit)
+        return validations
+    except Exception as e:
+        logger.error(f"Failed to get recent validations: {str(e)}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run("app.main:app", host="0.0.0.0", port=8000, reload=True)

app/static/index.html

@@ -353,8 +353,6 @@
 
         .spell-error-type {
             display: inline-block;
-            background: #ffc107;
-            color: #856404;
             padding: 3px 10px;
             border-radius: 10px;
             font-size: 12px;
@@ -362,27 +360,53 @@
             margin-left: 10px;
         }
 
-        .checkbox-wrapper {
+        .type-spelling {
+            background: #ffc107;
+            color: #856404;
+        }
+
+        .type-grammar {
+            background: #007bff;
+            color: white;
+        }
+
+        .type-formatting {
+            background: #6f42c1;
+            color: white;
+        }
+
+        .button-group {
             display: flex;
-            align-items: center;
-            gap: 10px;
-            padding: 12px;
-            background: #f8f9fa;
-            border-radius: 8px;
-            margin-bottom: 20px;
+            gap: 15px;
+            margin-top: 20px;
         }
 
-        .checkbox-wrapper input[type="checkbox"] {
-            width: 20px;
-            height: 20px;
+        .btn-secondary {
+            background: linear-gradient(135deg, #6c757d 0%, #5a6268 100%);
+            color: white;
+            border: none;
+            padding: 14px 32px;
+            border-radius: 8px;
+            font-size: 16px;
+            font-weight: 600;
             cursor: pointer;
+            flex: 1;
+            transition: transform 0.2s, box-shadow 0.2s;
         }
 
-        .checkbox-wrapper label {
-            margin: 0;
-            cursor: pointer;
-            font-weight: 500;
-            user-select: none;
+        .btn-secondary:hover {
+            transform: translateY(-2px);
+            box-shadow: 0 10px 20px rgba(108, 117, 125, 0.4);
+        }
+
+        .btn-secondary:active {
+            transform: translateY(0);
+        }
+
+        .btn-secondary:disabled {
+            background: #ccc;
+            cursor: not-allowed;
+            transform: none;
         }
 
         .spell-check-no-errors {
@@ -393,6 +417,89 @@
             text-align: center;
             font-weight: 600;
         }
+
+        /* Link Validation Styles */
+        .link-validation-section {
+            margin-top: 20px;
+            padding: 20px;
+            background: #e8f4fd;
+            border-radius: 8px;
+            border-left: 4px solid #007bff;
+        }
+
+        .link-validation-header {
+            font-weight: 600;
+            font-size: 18px;
+            color: #333;
+            margin-bottom: 15px;
+            display: flex;
+            align-items: center;
+            gap: 10px;
+        }
+
+        .link-list {
+            list-style: none;
+        }
+
+        .link-item {
+            background: white;
+            padding: 12px;
+            margin-bottom: 8px;
+            border-radius: 6px;
+            border: 1px solid #dee2e6;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+        }
+
+        .link-item.broken {
+            border-left: 4px solid #dc3545;
+        }
+
+        .link-item.valid {
+            border-left: 4px solid #28a745;
+        }
+
+        .link-item.warning {
+            border-left: 4px solid #ffc107;
+        }
+
+        .link-url {
+            font-family: monospace;
+            color: #0056b3;
+            word-break: break-all;
+            margin-right: 10px;
+            font-size: 14px;
+        }
+
+        .link-meta {
+            color: #666;
+            font-size: 12px;
+            margin-top: 4px;
+        }
+
+        .link-status-badge {
+            padding: 4px 10px;
+            border-radius: 12px;
+            font-size: 12px;
+            font-weight: 600;
+            white-space: nowrap;
+        }
+
+        .status-valid {
+            background: #d4edda;
+            color: #155724;
+        }
+
+        .status-broken {
+            background: #f8d7da;
+            color: #721c24;
+        }
+
+        .status-warning {
+            background: #fff3cd;
+            color: #856404;
+        }
     </style>
 </head>
 
@@ -401,10 +508,52 @@
         <h1>Medical Document Validator</h1>
         <p class="subtitle">Upload a document and select a template to validate against</p>
 
+        <!-- Project Selector -->
+        <div
+            style="background: #e8f4f8; padding: 15px; border-radius: 8px; margin-bottom: 30px; border-left: 4px solid #007bff;">
+            <div style="display: flex; align-items: center; gap: 10px; flex-wrap: wrap;">
+                <label style="font-weight: 600; margin: 0;">📂 Current Project:</label>
+                <select id="currentProject"
+                    style="flex: 1; min-width: 200px; padding: 8px; border: 1px solid #ccc; border-radius: 4px;">
+                    <option value="">No Project (Not Saved)</option>
+                </select>
+                <button type="button" class="btn-secondary" id="createProjectBtn" style="white-space: nowrap;">
+                    + New Project
+                </button>
+                <button type="button" class="btn-secondary" id="viewProjectsBtn" style="white-space: nowrap;">
+                    📋 View All
+                </button>
+            </div>
+        </div>
+
+        <!-- Create Project Modal -->
+        <div id="createProjectModal"
+            style="display: none; position: fixed; top: 0; left: 0; width: 100%; height: 100%; background: rgba(0,0,0,0.5); z-index: 1000; align-items: center; justify-content: center;">
+            <div
+                style="background: white; padding: 30px; border-radius: 8px; max-width: 500px;  width: 90%; box-shadow: 0 4px 6px rgba(0,0,0,0.1);">
+                <h2 style="margin-top: 0;">Create New Project</h2>
+                <div class="form-group">
+                    <label for="projectName">Project Name: *</label>
+                    <input type="text" id="projectName" placeholder="e.g., Cardiology Conference Q1 2025"
+                        style="width: 100%; padding: 10px; border: 1px solid #ddd; border-radius: 4px;">
+                </div>
+                <div class="form-group">
+                    <label for="projectDescription">Description (Optional):</label>
+                    <textarea id="projectDescription" rows="3" placeholder="Brief description of this project..."
+                        style="width: 100%; padding: 10px; border: 1px solid #ddd; border-radius: 4px; resize: vertical;"></textarea>
+                </div>
+                <div style="display: flex; gap: 10px; justify-content: flex-end; margin-top: 20px;">
+                    <button type="button" class="btn-secondary" id="cancelProjectBtn">Cancel</button>
+                    <button type="button" class="btn" id="saveProjectBtn">Create Project</button>
+                </div>
+            </div>
+        </div>
+
         <form id="validationForm">
             <div class="form-group">
-                <label for="templateSelect">Select Template:</label>
-                <select id="templateSelect" name="template" required>
+                <label for="templateSelect">Select Template: <span style="color: #999; font-weight: 400;">(Optional for
+                        spelling-only check)</span></label>
+                <select id="templateSelect" name="template">
                     <option value="">Loading templates...</option>
                 </select>
             </div>
@@ -415,13 +564,20 @@
                 <div class="file-info" id="fileInfo"></div>
             </div>
 
-            <div class="checkbox-wrapper">
-                <input type="checkbox" id="spellCheckToggle" name="spell_check">
-                <label for="spellCheckToggle">✓ Check spelling in document (ignores proper names including Arabic
-                    names)</label>
+            <div class="form-group">
+                <label for="customPrompt">Custom Instructions (Optional):</label>
+                <textarea id="customPrompt" name="customPrompt" rows="3" maxlength="500"
+                    placeholder="Enter any additional instructions to customize the validation (e.g., 'Focus on date format validation' or 'Pay special attention to logo placement')..."
+                    style="width: 100%; padding: 10px; border: 1px solid #ddd; border-radius: 4px; font-family: inherit; font-size: 14px; resize: vertical;"></textarea>
+                <div style="text-align: right; font-size: 12px; color: #666; margin-top: 4px;">
+                    <span id="charCount">0</span>/500 characters
+                </div>
             </div>
 
-            <button type="submit" class="btn" id="submitBtn">Validate Document</button>
+            <div class="button-group">
+                <button type="button" class="btn" id="validateBtn">📋 Validate Document</button>
+                <button type="button" class="btn-secondary" id="spellingOnlyBtn">✨ Check Quality Only</button>
+            </div>
         </form>
 
         <div class="debug-section">
@@ -433,18 +589,105 @@
             <div class="debug-info" id="debugInfo" style="display: none;"></div>
         </div>
 
-        <div class="loading" id="loading">
-            <div class="spinner"></div>
-            <p>Validating document...</p>
+        <!-- Document Comparison Section -->
+        <div class="comparison-section"
+            style="background: #f8f9fa; padding: 25px; border-radius: 8px; margin-top: 30px;">
+            <h3 style="margin-bottom: 15px; font-size: 20px; color: #333;">🔄 Compare Documents</h3>
+            <p style="color: #666; font-size: 14px; margin-bottom: 20px;">
+                Upload two versions of a document to see what changed (e.g., before and after edits).
+            </p>
+
+            <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 20px; margin-bottom: 20px;">
+                <div class="form-group">
+                    <label for="compareFile1">📄 Original Document:</label>
+                    <input type="file" id="compareFile1" accept=".pdf,.docx,.pptx">
+                    <div class="file-info" id="compareFileInfo1"></div>
+                </div>
+
+                <div class="form-group">
+                    <label for="compareFile2">📝 Modified Document:</label>
+                    <input type="file" id="compareFile2" accept=".pdf,.docx,.pptx">
+                    <div class="file-info" id="compareFileInfo2"></div>
+                </div>
+            </div>
+
+            <button type="button" class="btn" id="compareBtn" style="width: 100%;">
+                🔍 Compare Documents
+            </button>
         </div>
 
-        <div class="error" id="error"></div>
+        <!-- Bulk Certificate Validation Section -->
+        <div class="bulk-validation-section"
+            style="background: #f0f8ff; padding: 25px; border-radius: 8px; margin-top: 30px;">
+            <h3 style="margin-bottom: 15px; font-size: 20px; color: #333;">📋 Bulk Certificate Validation</h3>
+            <p style="color: #666; font-size: 14px; margin-bottom: 20px;">
+                Upload an Excel list of names and multiple certificates to verify all attendees received their
+                certificates.
+            </p>
+
+            <!-- Step 1: Excel Upload -->
+            <div class="form-group" style="margin-bottom: 20px;">
+                <label for="excelFile">1️⃣ Upload Excel File with Names:</label>
+                <input type="file" id="excelFile" accept=".xlsx">
+                <div class="file-info" id="excelFileInfo"></div>
+            </div>
+
+            <!-- Step 2: Column Selection -->
+            <div class="form-group" style="margin-bottom: 20px; display: none;" id="columnSelectorGroup">
+                <label for="nameColumn">2️⃣ Select Column Containing Names:</label>
+                <select id="nameColumn" style="width: 100%; padding: 10px; border: 1px solid #ddd; border-radius: 4px;">
+                    <option value="">Loading columns...</option>
+                </select>
+                <div style="margin-top: 8px; color: #666; font-size: 13px;">
+                    Preview: <span id="namePreview" style="font-weight: 500;"></span>
+                </div>
+            </div>
 
-        <div class="results" id="results">
-            <div class="status" id="status"></div>
-            <div class="summary" id="summary"></div>
-            <ul class="elements-list" id="elementsList"></ul>
+            <!-- Step 3: Certificates Upload -->
+            <div class="form-group" style="margin-bottom: 20px;">
+                <label for="certificateFiles">3️⃣ Upload Certificates (Max 150):</label>
+                <input type="file" id="certificateFiles" multiple accept=".pdf,.pptx"">
+                <div style=" margin-top: 8px;">
+                <span style="font-weight: 600; color: #007bff;" id="certCount">0</span>
+                <span style="color: #666;">/150 files selected</span>
+            </div>
         </div>
+
+        <!-- Step 4: Validate Button -->
+        <button type="button" class="btn" id="bulkValidateBtn" style="width: 100%;" disabled>
+            ✅ Validate All Certificates
+        </button>
+    </div>
+
+    <div class="loading" id="loading">
+        <div class="spinner"></div>
+        <p>Validating document...</p>
+    </div>
+
+    <div class="error" id="error"></div>
+
+    <div class="results" id="results">
+        <div class="status" id="status"></div>
+        <div class="summary" id="summary"></div>
+        <ul class="elements-list" id="elementsList"></ul>
+    </div>
+
+    <!-- Comparison Results -->
+    <div class="results" id="comparisonResults" style="display: none;">
+        <h2 style="margin-bottom: 20px;">📊 Comparison Results</h2>
+        <div id="comparisonSummary" style="margin-bottom: 20px;"></div>
+        <div id="comparisonDetails"></div>
+    </div>
+
+    <!-- Bulk Validation Results -->
+    <div class="results" id="bulkResults" style="display: none;">
+        <h2 style="margin-bottom: 20px;">📊 Bulk Validation Results</h2>
+        <div id="bulkSummary" style="margin-bottom: 20px;"></div>
+        <button type="button" class="btn-secondary" id="downloadCSVBtn" style="margin-bottom: 20px;">
+            📥 Download CSV Report
+        </button>
+        <div id="bulkDetails"></div>
+    </div>
     </div>
 
     <script>
@@ -481,17 +724,83 @@
             }
         });
 
-        // Handle form submission
-        document.getElementById('validationForm').addEventListener('submit', async function (e) {
-            e.preventDefault();
+        // Handle character count for custom prompt
+        document.getElementById('customPrompt').addEventListener('input', function () {
+            const count = this.value.length;
+            document.getElementById('charCount').textContent = count;
+        });
+
+        // Handle comparison file 1 input
+        document.getElementById('compareFile1').addEventListener('change', function (e) {
+            const file = e.target.files[0];
+            const fileInfo = document.getElementById('compareFileInfo1');
+            if (file) {
+                fileInfo.textContent = `${file.name} (${(file.size / 1024).toFixed(2)} KB)`;
+            } else {
+                fileInfo.textContent = '';
+            }
+        });
+
+        // Handle comparison file 2 input
+        document.getElementById('compareFile2').addEventListener('change', function (e) {
+            const file = e.target.files[0];
+            const fileInfo = document.getElementById('compareFileInfo2');
+            if (file) {
+                fileInfo.textContent = `${file.name} (${(file.size / 1024).toFixed(2)} KB)`;
+            } else {
+                fileInfo.textContent = '';
+            }
+        });
+
+        // Handle Compare Documents button
+        document.getElementById('compareBtn').addEventListener('click', async function () {
+            const file1 = document.getElementById('compareFile1').files[0];
+            const file2 = document.getElementById('compareFile2').files[0];
+
+            if (!file1 || !file2) {
+                showError('Please select both documents to compare');
+                return;
+            }
+
+            // Hide previous results
+            document.getElementById('results').style.display = 'none';
+            document.getElementById('comparisonResults').style.display = 'none';
+            document.getElementById('error').style.display = 'none';
+            document.getElementById('loading').querySelector('p').textContent = 'Comparing documents...';
+            document.getElementById('loading').style.display = 'block';
+
+            try {
+                const formData = new FormData();
+                formData.append('file1', file1);
+                formData.append('file2', file2);
+
+                const response = await fetch('/compare', {
+                    method: 'POST',
+                    body: formData
+                });
+
+                const data = await response.json();
+
+                if (!response.ok) {
+                    throw new Error(data.detail || 'Comparison failed');
+                }
+
+                displayComparisonResults(data);
+            } catch (error) {
+                showError(error.message || 'An error occurred during comparison');
+            } finally {
+                document.getElementById('loading').style.display = 'none';
+            }
+        });
 
+        // Handle Validate Document button (Template + Spelling)
+        document.getElementById('validateBtn').addEventListener('click', async function () {
             const templateKey = document.getElementById('templateSelect').value;
             const fileInput = document.getElementById('fileInput');
             const file = fileInput.files[0];
-            const spellCheckEnabled = document.getElementById('spellCheckToggle').checked;
 
             if (!templateKey) {
-                showError('Please select a template');
+                showError('Please select a template for validation');
                 return;
             }
 
@@ -512,14 +821,21 @@
             document.getElementById('results').style.display = 'none';
             document.getElementById('error').style.display = 'none';
             document.getElementById('loading').style.display = 'block';
-            document.getElementById('submitBtn').disabled = true;
+            document.getElementById('validateBtn').disabled = true;
+            document.getElementById('spellingOnlyBtn').disabled = true;
 
             try {
                 const formData = new FormData();
                 formData.append('file', file);
 
-                // Build URL with spell check parameter
-                const url = `/validate?template_key=${encodeURIComponent(templateKey)}&check_spelling=${spellCheckEnabled}`;
+                // Get custom prompt if provided
+                const customPrompt = document.getElementById('customPrompt').value.trim();
+
+                // Build URL - always include spell checking for validate mode
+                let url = `/validate?template_key=${encodeURIComponent(templateKey)}&check_spelling=true`;
+                if (customPrompt) {
+                    url += `&custom_prompt=${encodeURIComponent(customPrompt)}`;
+                }
 
                 const response = await fetch(url, {
                     method: 'POST',
@@ -537,10 +853,65 @@
                 showError(error.message || 'An error occurred during validation');
             } finally {
                 document.getElementById('loading').style.display = 'none';
-                document.getElementById('submitBtn').disabled = false;
+                document.getElementById('validateBtn').disabled = false;
+                document.getElementById('spellingOnlyBtn').disabled = false;
+            }
+        });
+
+        // Handle Check Spelling Only button
+        document.getElementById('spellingOnlyBtn').addEventListener('click', async function () {
+            const fileInput = document.getElementById('fileInput');
+            const file = fileInput.files[0];
+
+            if (!file) {
+                showError('Please select a file to upload');
+                return;
+            }
+
+            // Validate file type
+            const validExtensions = ['.pdf', '.docx', '.pptx'];
+            const fileExtension = '.' + file.name.split('.').pop().toLowerCase();
+            if (!validExtensions.includes(fileExtension)) {
+                showError('Invalid file type. Please upload a PDF, DOCX, or PPTX file.');
+                return;
+            }
+
+            // Hide previous results and errors
+            document.getElementById('results').style.display = 'none';
+            document.getElementById('error').style.display = 'none';
+            document.getElementById('loading').style.display = 'block';
+            document.getElementById('validateBtn').disabled = true;
+            document.getElementById('spellingOnlyBtn').disabled = true;
+
+            try {
+                const formData = new FormData();
+                formData.append('file', file);
+
+                // Spelling-only mode endpoint
+                const url = `/validate/spelling-only`;
+
+                const response = await fetch(url, {
+                    method: 'POST',
+                    body: formData
+                });
+
+                const data = await response.json();
+
+                if (!response.ok) {
+                    throw new Error(data.detail || 'Spell check failed');
+                }
+
+                displaySpellingOnlyResults(data);
+            } catch (error) {
+                showError(error.message || 'An error occurred during spell checking');
+            } finally {
+                document.getElementById('loading').style.display = 'none';
+                document.getElementById('validateBtn').disabled = false;
+                document.getElementById('spellingOnlyBtn').disabled = false;
             }
         });
 
+
         function showError(message) {
             const errorDiv = document.getElementById('error');
             errorDiv.textContent = message;
@@ -599,6 +970,11 @@
                 displaySpellCheck(data.spell_check);
             }
 
+            // Display link validation results if available
+            if (data.link_report) {
+                displayLinkReport(data.link_report);
+            }
+
             resultsDiv.style.display = 'block';
             document.getElementById('error').style.display = 'none';
         }
@@ -612,13 +988,13 @@
 
             const header = document.createElement('div');
             header.className = 'spell-check-header';
-            header.innerHTML = `📝 Spelling Check<span style="font-size: 14px; color: #666; font-weight: normal; margin-left: auto;">${spellCheck.summary}</span>`;
+            header.innerHTML = `✨ Quality & Spelling Check<span style="font-size: 14px; color: #666; font-weight: normal; margin-left: auto;">${spellCheck.summary}</span>`;
             spellSection.appendChild(header);
 
             if (spellCheck.total_errors === 0) {
                 const noErrors = document.createElement('div');
                 noErrors.className = 'spell-check-no-errors';
-                noErrors.textContent = '✓ No spelling errors found!';
+                noErrors.textContent = '✓ No quality or spelling errors found!';
                 spellSection.appendChild(noErrors);
             } else {
                 spellCheck.errors.forEach(error => {
@@ -627,7 +1003,7 @@
 
                     const wordDiv = document.createElement('div');
                     wordDiv.className = 'spell-error-word';
-                    wordDiv.innerHTML = `"${error.word}"<span class="spell-error-type">${error.error_type}</span>`;
+                    wordDiv.innerHTML = `"${error.word}"<span class="spell-error-type type-${error.error_type}">${error.error_type}</span>`;
                     errorItem.appendChild(wordDiv);
 
                     if (error.context) {
@@ -664,6 +1040,93 @@
             elementsList.appendChild(spellSection);
         }
 
+        function displayLinkReport(linkReport) {
+            const elementsList = document.getElementById('elementsList');
+
+            // Create link results section
+            const linkSection = document.createElement('div');
+            linkSection.className = 'link-validation-section';
+
+            const header = document.createElement('div');
+            header.className = 'link-validation-header';
+            header.innerHTML = `🔗 Link Validation <span style="font-size: 14px; color: #666; font-weight: normal; margin-left: auto;">${linkReport.length} link(s) checked</span>`;
+            linkSection.appendChild(header);
+
+            if (linkReport.length === 0) {
+                const noLinks = document.createElement('div');
+                noLinks.style.padding = '10px';
+                noLinks.style.color = '#666';
+                noLinks.style.fontStyle = 'italic';
+                noLinks.textContent = 'No links found in document.';
+                linkSection.appendChild(noLinks);
+            } else {
+                const list = document.createElement('ul');
+                list.className = 'link-list';
+
+                linkReport.forEach(link => {
+                    const item = document.createElement('li');
+                    let statusClass = 'valid';
+                    if (link.status === 'broken') statusClass = 'broken';
+                    if (link.status === 'warning') statusClass = 'warning';
+
+                    item.className = `link-item ${statusClass}`;
+
+                    const leftDiv = document.createElement('div');
+                    leftDiv.style.flex = '1';
+                    leftDiv.style.marginRight = '10px';
+                    leftDiv.style.overflow = 'hidden';
+
+                    const urlDiv = document.createElement('div');
+                    urlDiv.className = 'link-url';
+                    urlDiv.textContent = link.url;
+                    leftDiv.appendChild(urlDiv);
+
+                    const metaDiv = document.createElement('div');
+                    metaDiv.className = 'link-meta';
+                    const pageInfo = link.page !== 'Unknown' ? `Page: ${link.page}` : '';
+                    metaDiv.textContent = `${pageInfo} ${link.message ? '• ' + link.message : ''}`;
+                    leftDiv.appendChild(metaDiv);
+
+                    const badge = document.createElement('span');
+                    badge.className = `link-status-badge status-${statusClass}`;
+                    badge.textContent = link.status.toUpperCase();
+
+                    item.appendChild(leftDiv);
+                    item.appendChild(badge);
+                    list.appendChild(item);
+                });
+                linkSection.appendChild(list);
+            }
+
+            elementsList.appendChild(linkSection);
+        }
+
+        function displaySpellingOnlyResults(data) {
+            const resultsDiv = document.getElementById('results');
+            const statusDiv = document.getElementById('status');
+            const summaryDiv = document.getElementById('summary');
+            const elementsList = document.getElementById('elementsList');
+
+            // Set status for spelling-only mode
+            const hasErrors = data.spell_check && data.spell_check.total_errors > 0;
+            statusDiv.textContent = hasErrors ? '⚠️ Issues Found' : '✓ Text Quality OK';
+            statusDiv.className = `status ${hasErrors ? 'fail' : 'pass'}`;
+
+            // Set summary
+            summaryDiv.textContent = data.spell_check ? data.spell_check.summary : 'Spell check completed';
+
+            // Clear elements list
+            elementsList.innerHTML = '';
+
+            // Display spell check results
+            if (data.spell_check) {
+                displaySpellCheck(data.spell_check);
+            }
+
+            resultsDiv.style.display = 'block';
+            document.getElementById('error').style.display = 'none';
+        }
+
         // Debug: Extract images
         document.getElementById('debugBtn').addEventListener('click', async function () {
             const templateKey = document.getElementById('templateSelect').value;
@@ -741,7 +1204,355 @@
             }
         });
 
+        // Function to display comparison results
+        function displayComparisonResults(data) {
+            const resultsDiv = document.getElementById('comparisonResults');
+            const summaryDiv = document.getElementById('comparisonSummary');
+            const detailsDiv = document.getElementById('comparisonDetails');
+
+            // Display summary
+            summaryDiv.innerHTML = `
+                <div class="summary" style="background: #f8f9fa; padding: 20px; border-radius: 8px;">
+                    <h3 style="margin-bottom: 15px;">📝 Summary</h3>
+                    <div style="white-space: pre-wrap; line-height: 1.6;">${data.summary || 'No summary available'}</div>
+                </div>
+            `;
+
+            // Display detailed changes
+            if (data.changes && data.changes.length > 0) {
+                let changesHTML = '<h3 style="margin: 20px 0 15px 0;">🔍 Detailed Changes</h3><ul class="elements-list">';
+
+                data.changes.forEach(change => {
+                    const typeClass = change.type === 'addition' ? 'status-pass' :
+                        change.type === 'deletion' ? 'status-fail' : 'status-warning';
+                    const typeIcon = change.type === 'addition' ? '➕' :
+                        change.type === 'deletion' ? '➖' : '🔄';
+
+                    changesHTML += `
+                        <li style="margin-bottom: 15px; padding: 15px; background: white; border-left: 4px solid ${change.type === 'addition' ? '#28a745' : change.type === 'deletion' ? '#dc3545' : '#ffc107'}; border-radius: 4px;">
+                            <div style="display: flex; align-items: center; margin-bottom: 8px;">
+                                <span class="status-badge ${typeClass}" style="margin-right: 10px;">${typeIcon} ${change.type.toUpperCase()}</span>
+                                ${change.section ? `<strong>${change.section}</strong>` : ''}
+                            </div>
+                            <div style="color: #666; white-space: pre-wrap;">${change.description}</div>
+                        </li>
+                    `;
+                });
+
+                changesHTML += '</ul>';
+                detailsDiv.innerHTML = changesHTML;
+            } else {
+                detailsDiv.innerHTML = '<p style="color: #666; text-align: center; padding: 20px;">✅ No significant changes detected between the documents.</p>';
+            }
+
+            resultsDiv.style.display = 'block';
+            resultsDiv.scrollIntoView({ behavior: 'smooth', block: 'start' });
+        }
+
+        // Bulk Validation: Excel file handler
+        let excelFileData = null;
+        let excelColumns = [];
+
+        document.getElementById('excelFile').addEventListener('change', async function (e) {
+            const file = e.target.files[0];
+            const fileInfo = document.getElementById('excelFileInfo');
+
+            if (file) {
+                fileInfo.textContent = `${file.name} (${(file.size / 1024).toFixed(2)} KB)`;
+
+                // Read and parse Excel to get columns
+                try {
+                    excelFileData = file;
+                    const formData = new FormData();
+                    formData.append('file', file);
+
+                    const response = await fetch('/excel-columns', {
+                        method: 'POST',
+                        body: formData
+                    });
+
+                    const data = await response.json();
+
+                    if (response.ok) {
+                        excelColumns = data.columns;
+                        const nameColumnSelect = document.getElementById('nameColumn');
+                        nameColumnSelect.innerHTML = '<option value="">-- Select Column --</option>';
+
+                        excelColumns.forEach(col => {
+                            const option = document.createElement('option');
+                            option.value = col;
+                            option.textContent = col;
+                            nameColumnSelect.appendChild(option);
+                        });
+
+                        document.getElementById('columnSelectorGroup').style.display = 'block';
+                        document.getElementById('namePreview').textContent = `${data.row_count} names found`;
+                    }
+                } catch (error) {
+                    showError('Failed to parse Excel file: ' + error.message);
+                }
+            } else {
+                fileInfo.textContent = '';
+                document.getElementById('columnSelectorGroup').style.display = 'none';
+            }
+        });
+
+        // Bulk Validation: Certificate files handler
+        document.getElementById('certificateFiles').addEventListener('change', function (e) {
+            const files = e.target.files;
+            const count = files.length;
+            document.getElementById('certCount').textContent = count;
+
+            if (count > 150) {
+                showError('Maximum 150 certificates allowed. Please reduce your selection.');
+                this.value = '';
+                document.getElementById('certCount').textContent = '0';
+                return;
+            }
+
+            checkBulkValidateReady();
+        });
+
+        // Bulk Validation: Column selection handler
+        document.getElementById('nameColumn').addEventListener('change', function () {
+            checkBulkValidateReady();
+        });
+
+        // Check if bulk validate button should be enabled
+        function checkBulkValidateReady() {
+            const excelFile = document.getElementById('excelFile').files[0];
+            const column = document.getElementById('nameColumn').value;
+            const certFiles = document.getElementById('certificateFiles').files;
+
+            const btn = document.getElementById('bulkValidateBtn');
+            btn.disabled = !(excelFile && column && certFiles.length > 0);
+        }
+
+        // Bulk Validation: Validate button handler
+        document.getElementById('bulkValidateBtn').addEventListener('click', async function () {
+            const excelFile = document.getElementById('excelFile').files[0];
+            const nameColumn = document.getElementById('nameColumn').value;
+            const certFiles = document.getElementById('certificateFiles').files;
+
+            if (!excelFile || !nameColumn || certFiles.length === 0) {
+                showError('Please complete all steps before validating');
+                return;
+            }
+
+            // Hide previous results
+            document.getElementById('results').style.display = 'none';
+            document.getElementById('comparisonResults').style.display = 'none';
+            document.getElementById('bulkResults').style.display = 'none';
+            document.getElementById('error').style.display = 'none';
+            document.getElementById('loading').querySelector('p').textContent = `Processing ${certFiles.length} certificates...`;
+            document.getElementById('loading').style.display = 'block';
+            this.disabled = true;
+
+            try {
+                const formData = new FormData();
+                formData.append('excel_file', excelFile);
+                formData.append('name_column', nameColumn);
+
+                for (let i = 0; i < certFiles.length; i++) {
+                    formData.append('certificate_files', certFiles[i]);
+                }
+
+                const response = await fetch('/bulk-validate', {
+                    method: 'POST',
+                    body: formData
+                });
+
+                const data = await response.json();
+
+                if (!response.ok) {
+                    throw new Error(data.detail || 'Bulk validation failed');
+                }
+
+                displayBulkResults(data);
+            } catch (error) {
+                showError(error.message || 'An error occurred during bulk validation');
+            } finally {
+                document.getElementById('loading').style.display = 'none';
+                this.disabled = false;
+            }
+        });
+
+        // Display bulk validation results
+        let bulkResultsData = null;
+
+        function displayBulkResults(data) {
+            bulkResultsData = data;
+            const resultsDiv = document.getElementById('bulkResults');
+            const summaryDiv = document.getElementById('bulkSummary');
+            const detailsDiv = document.getElementById('bulkDetails');
+
+            // Summary
+            summaryDiv.innerHTML = `
+                <div class="summary" style="background: #f8f9fa; padding: 20px; border-radius: 8px;">
+                    <h3 style="margin-bottom: 15px;">📊 Summary</h3>
+                    <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(150px, 1fr)); gap: 15px;">
+                        <div style="text-align: center; padding: 15px; background: white; border-radius: 6px;">
+                            <div style="font-size: 32px; font-weight: bold; color: #007bff;">${data.total_names}</div>
+                            <div style="color: #666; font-size: 14px;">Total Names</div>
+                        </div>
+                        <div style="text-align: center; padding: 15px; background: white; border-radius: 6px;">
+                            <div style="font-size: 32px; font-weight: bold; color: #6c757d;">${data.total_certificates}</div>
+                            <div style="color: #666; font-size: 14px;">Certificates</div>
+                        </div>
+                        <div style="text-align: center; padding: 15px; background: white; border-radius: 6px;">
+                            <div style="font-size: 32px; font-weight: bold; color: #28a745;">${data.exact_matches}</div>
+                            <div style="color: #666; font-size: 14px;">✅ Exact</div>
+                        </div>
+                        <div style="text-align: center; padding: 15px; background: white; border-radius: 6px;">
+                            <div style="font-size: 32px; font-weight: bold; color: #ffc107;">${data.fuzzy_matches}</div>
+                            <div style="color: #666; font-size: 14px;">⚠️ Fuzzy</div>
+                        </div>
+                        <div style="text-align: center; padding: 15px; background: white; border-radius: 6px;">
+                            <div style="font-size: 32px; font-weight: bold; color: #dc3545;">${data.missing}</div>
+                            <div style="color: #666; font-size: 14px;">❌ Missing</div>
+                        </div>
+                        <div style="text-align: center; padding: 15px; background: white; border-radius: 6px;">
+                            <div style="font-size: 32px; font-weight: bold; color: #17a2b8;">${data.extras}</div>
+                            <div style="color: #666; font-size: 14px;">➕ Extra</div>
+                        </div>
+                    </div>
+                </div>
+            `;
+
+            // Details
+            let detailsHTML = '<h3 style="margin: 20px 0 15px 0;">📋 Detailed Results</h3><ul class="elements-list">';
+
+            data.details.forEach(item => {
+                const status = item.status;
+                const bgColor = status === 'exact_match' ? '#d4edda' :
+                    status === 'fuzzy_match' ? '#fff3cd' :
+                        status === 'missing' ? '#f8d7da' : '#d1ecf1';
+                const icon = status === 'exact_match' ? '✅' :
+                    status === 'fuzzy_match' ? '⚠️' :
+                        status === 'missing' ? '❌' : '➕';
+                const label = status === 'exact_match' ? 'EXACT MATCH' :
+                    status === 'fuzzy_match' ? `FUZZY MATCH (${item.similarity}%)` :
+                        status === 'missing' ? 'MISSING' : 'EXTRA';
+
+                detailsHTML += `
+                    <li style="margin-bottom: 10px; padding: 12px; background: ${bgColor}; border-radius: 4px;">
+                        <div style="display: flex; justify-content: space-between; align-items: center;">
+                            <div>
+                                <strong>${item.name}</strong>
+                                ${item.certificate_file ? `<div style="font-size: 12px; color: #666; margin-top: 4px;">📄 ${item.certificate_file}</div>` : ''}
+                            </div>
+                            <span style="font-size: 14px; font-weight: 600;">${icon} ${label}</span>
+                        </div>
+                    </li>
+                `;
+            });
+
+            detailsHTML += '</ul>';
+            detailsDiv.innerHTML = detailsHTML;
+
+            resultsDiv.style.display = 'block';
+            resultsDiv.scrollIntoView({ behavior: 'smooth', block: 'start' });
+        }
+
+        // CSV Download handler
+        document.getElementById('downloadCSVBtn').addEventListener('click', function () {
+            if (!bulkResultsData) return;
+
+            let csv = 'Name,Status,Certificate File,Match Type,Similarity\n';
+
+            bulkResultsData.details.forEach(item => {
+                const status = item.status === 'exact_match' ? 'Found' :
+                    item.status === 'fuzzy_match' ? 'Found' :
+                        item.status === 'missing' ? 'Missing' : 'Extra';
+                const matchType = item.status === 'exact_match' ? 'Exact' :
+                    item.status === 'fuzzy_match' ? 'Fuzzy' : '-';
+                const similarity = item.similarity || '-';
+                const certFile = item.certificate_file || '-';
+
+                csv += `"${item.name}","${status}","${certFile}","${matchType}","${similarity}"\n`;
+            });
+
+            const blob = new Blob([csv], { type: 'text/csv' });
+            const url = window.URL.createObjectURL(blob);
+            const a = document.createElement('a');
+            a.href = url;
+            a.download = 'bulk_validation_results.csv';
+            a.click();
+            window.URL.revokeObjectURL(url);
+        });
+
+        // ==================== PROJECTS FUNCTIONALITY ====================
+
+        // Load projects list
+        async function loadProjects() {
+            try {
+                const response = await fetch('/projects');
+                const projects = await response.json();
+
+                const selector = document.getElementById('currentProject');
+                selector.innerHTML = '<option value="">No Project (Not Saved)</option>';
+
+                projects.forEach(project => {
+                    const option = document.createElement('option');
+                    option.value = project.id;
+                    option.textContent = `${project.name} (${project.validation_count} validations)`;
+                    selector.appendChild(option);
+                });
+            } catch (error) {
+                console.error('Failed to load projects:', error);
+            }
+        }
+
+        // Create project modal handlers
+        document.getElementById('createProjectBtn').addEventListener('click', function () {
+            document.getElementById('createProjectModal').style.display = 'flex';
+            document.getElementById('projectName').value = '';
+            document.getElementById('projectDescription').value = '';
+        });
+
+        document.getElementById('cancelProjectBtn').addEventListener('click', function () {
+            document.getElementById('createProjectModal').style.display = 'none';
+        });
+
+        document.getElementById('saveProjectBtn').addEventListener('click', async function () {
+            const name = document.getElementById('projectName').value.trim();
+            const description = document.getElementById('projectDescription').value.trim();
+
+            if (!name) {
+                showError('Project name is required');
+                return;
+            }
+
+            try {
+                const response = await fetch('/projects', {
+                    method: 'POST',
+                    headers: { 'Content-Type': 'application/json' },
+                    body: JSON.stringify({ name, description })
+                });
+
+                if (!response.ok) {
+                    const error = await response.json();
+                    throw new Error(error.detail || 'Failed to create project');
+                }
+
+                const project = await response.json();
+                document.getElementById('createProjectModal').style.display = 'none';
+                await loadProjects();
+                document.getElementById('currentProject').value = project.id;
+                showError(''); // clear error
+            } catch (error) {
+                showError(error.message);
+            }
+        });
+
+        // View all projects
+        document.getElementById('viewProjectsBtn').addEventListener('click', function () {
+            // For now, just alert - can be enhanced later
+            alert('Projects view coming soon! For now, use the dropdown to select projects.');
+        });
+
         // Load templates when page loads
+        loadProjects();
         loadTemplates();
     </script>
 </body>

app/templates.json

@@ -4,292 +4,1765 @@
       "template_key": "certificate_appreciation_speaker",
       "friendly_name": "Certificate of Appreciation (Speaker/Chairperson)",
       "elements": [
-        { "id": "certificate_title", "label": "Certificate Title", "type": "text", "required": true, "expected_phrases": ["Certificate of Appreciation"] },
-        { "id": "recipient_name", "label": "Recipient Name", "type": "person_name", "required": true, "placeholder_examples": ["Dr << Name >>"] },
-        { "id": "purpose_text", "label": "Purpose Text", "type": "text", "required": true, "expected_phrases": ["to express our gratitude and appreciation for participating as a Speaker/Chairperson"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true, "placeholder_examples": ["<<Event Name>>"] },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true, "placeholder_examples": ["<<Event Date>>"] },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true, "placeholder_examples": ["<<Venue>>"] },
-        { "id": "event_chairperson_signature", "label": "Event Chairperson Signature", "type": "signature_block", "required": true, "expected_phrases": ["Event Chairperson", "<<Signature>>"] },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true, "logo_role": "event" },
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true, "logo_role": "company" }
+        {
+          "id": "certificate_title",
+          "label": "Certificate Title",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Certificate of Appreciation"
+          ]
+        },
+        {
+          "id": "recipient_name",
+          "label": "Recipient Name",
+          "type": "person_name",
+          "required": true,
+          "placeholder_examples": [
+            "Dr << Name >>"
+          ]
+        },
+        {
+          "id": "purpose_text",
+          "label": "Purpose Text",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "to express our gratitude and appreciation for participating as a Speaker/Chairperson"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true,
+          "placeholder_examples": [
+            "<<Event Name>>"
+          ]
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true,
+          "placeholder_examples": [
+            "<<Event Date>>"
+          ]
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true,
+          "placeholder_examples": [
+            "<<Venue>>"
+          ]
+        },
+        {
+          "id": "event_chairperson_signature",
+          "label": "Event Chairperson Signature",
+          "type": "signature_block",
+          "required": true,
+          "expected_phrases": [
+            "Event Chairperson",
+            "<<Signature>>"
+          ]
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        },
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "company"
+        }
       ]
     },
     {
       "template_key": "certificate_attendance",
       "friendly_name": "Certificate of Attendance",
       "elements": [
-        { "id": "certificate_title", "label": "Certificate Title", "type": "text", "required": true, "expected_phrases": ["Certificate of Attendance"] },
-        { "id": "recipient_name", "label": "Recipient Name", "type": "person_name", "required": true, "placeholder_examples": ["Dr. << Name >>"] },
-        { "id": "confirmation_text", "label": "Confirmation Text", "type": "text", "required": true, "expected_phrases": ["This certificate confirms that", "has attended the meeting titled"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "event_chairperson_signature", "label": "Event Chairperson Signature", "type": "signature_block", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true, "logo_role": "event" },
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true, "logo_role": "company" }
+        {
+          "id": "certificate_title",
+          "label": "Certificate Title",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Certificate of Attendance"
+          ]
+        },
+        {
+          "id": "recipient_name",
+          "label": "Recipient Name",
+          "type": "person_name",
+          "required": true,
+          "placeholder_examples": [
+            "Dr. << Name >>"
+          ]
+        },
+        {
+          "id": "confirmation_text",
+          "label": "Confirmation Text",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "This certificate confirms that",
+            "has attended the meeting titled"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "event_chairperson_signature",
+          "label": "Event Chairperson Signature",
+          "type": "signature_block",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        },
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "company"
+        }
       ]
     },
     {
       "template_key": "cpd_certificate_accreditation_generic",
       "friendly_name": "CPD Certificate of Accreditation (Generic)",
       "elements": [
-        { "id": "certificate_title", "label": "Certificate Title", "type": "text", "required": true, "expected_phrases": ["Certificate of Accreditation"] },
-        { "id": "recipient_name", "label": "Recipient Full Name", "type": "person_name", "required": true, "placeholder_examples": ["<<Full Name>>"] },
-        { "id": "accreditation_code", "label": "Accreditation Code Number", "type": "code", "required": true },
-        { "id": "cpd_points", "label": "CPD Credit Points", "type": "number_or_text", "required": true },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true },
-        { "id": "confirmation_text", "label": "Attendance Confirmation Text", "type": "text", "required": true, "expected_phrases": ["This certificate confirms that", "Has attended the event"] }
+        {
+          "id": "certificate_title",
+          "label": "Certificate Title",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Certificate of Accreditation"
+          ]
+        },
+        {
+          "id": "recipient_name",
+          "label": "Recipient Full Name",
+          "type": "person_name",
+          "required": true,
+          "placeholder_examples": [
+            "<<Full Name>>"
+          ]
+        },
+        {
+          "id": "accreditation_code",
+          "label": "Accreditation Code Number",
+          "type": "code",
+          "required": true
+        },
+        {
+          "id": "cpd_points",
+          "label": "CPD Credit Points",
+          "type": "number_or_text",
+          "required": true
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true
+        },
+        {
+          "id": "confirmation_text",
+          "label": "Attendance Confirmation Text",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "This certificate confirms that",
+            "Has attended the event"
+          ]
+        }
       ]
     },
     {
       "template_key": "html_email_reminder",
       "friendly_name": "HTML Email Reminder",
       "elements": [
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true },
-        { "id": "greeting", "label": "Greeting with First Name Merge Tag", "type": "text", "required": true, "expected_phrases": ["Dear Dr.", "*|FNAME|*"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "time", "label": "Time Range", "type": "time_range", "required": true },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true },
-        { "id": "chairpersons_block", "label": "Chairpersons Block", "type": "section", "required": true, "expected_subfields": ["Pic", "Name", "Bio"] },
-        { "id": "speakers_block", "label": "Speakers Block", "type": "section", "required": true, "expected_subfields": ["Pic", "Name", "Bio"] },
-        { "id": "agenda_table", "label": "Agenda Table", "type": "table", "required": true, "expected_columns": ["Time", "Topic", "Faculty"] },
-        { "id": "cta_register_join", "label": "CTA to Register/Join", "type": "cta", "required": true, "expected_phrases": ["Click here to register", "Click here to join"] },
-        { "id": "disclaimer", "label": "Disclaimer", "type": "text", "required": true },
-        { "id": "preparation_date", "label": "Preparation Date", "type": "date_or_placeholder", "required": true },
-        { "id": "approval_code", "label": "Approval Code", "type": "code", "required": true }
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "greeting",
+          "label": "Greeting with First Name Merge Tag",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Dear Dr.",
+            "*|FNAME|*"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "time",
+          "label": "Time Range",
+          "type": "time_range",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true
+        },
+        {
+          "id": "chairpersons_block",
+          "label": "Chairpersons Block",
+          "type": "section",
+          "required": true,
+          "expected_subfields": [
+            "Pic",
+            "Name",
+            "Bio"
+          ]
+        },
+        {
+          "id": "speakers_block",
+          "label": "Speakers Block",
+          "type": "section",
+          "required": true,
+          "expected_subfields": [
+            "Pic",
+            "Name",
+            "Bio"
+          ]
+        },
+        {
+          "id": "agenda_table",
+          "label": "Agenda Table",
+          "type": "table",
+          "required": true,
+          "expected_columns": [
+            "Time",
+            "Topic",
+            "Faculty"
+          ]
+        },
+        {
+          "id": "cta_register_join",
+          "label": "CTA to Register/Join",
+          "type": "cta",
+          "required": true,
+          "expected_phrases": [
+            "Click here to register",
+            "Click here to join"
+          ]
+        },
+        {
+          "id": "disclaimer",
+          "label": "Disclaimer",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "html_invitation",
       "friendly_name": "HTML Invitation",
       "elements": [
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true },
-        { "id": "greeting", "label": "Greeting with First Name Merge Tag", "type": "text", "required": true, "expected_phrases": ["Dear Dr", "*|FNAME|*"] },
-        { "id": "invite_phrase", "label": "Invitation Phrase", "type": "text", "required": true, "expected_phrases": ["You are cordially invited to attend"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "time", "label": "Time Range", "type": "time_range", "required": true },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true },
-        { "id": "chairpersons_block", "label": "Chairpersons Block", "type": "section", "required": true },
-        { "id": "speakers_block", "label": "Speakers Block", "type": "section", "required": true },
-        { "id": "agenda_table", "label": "Agenda Table", "type": "table", "required": true, "expected_columns": ["Time", "Topic", "Faculty"] },
-        { "id": "cta_register", "label": "CTA to Register", "type": "cta", "required": true, "expected_phrases": ["Click here to register"] },
-        { "id": "disclaimer", "label": "Disclaimer", "type": "text", "required": true },
-        { "id": "preparation_date", "label": "Preparation Date", "type": "date_or_placeholder", "required": true },
-        { "id": "approval_code", "label": "Approval Code", "type": "code", "required": true }
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "greeting",
+          "label": "Greeting with First Name Merge Tag",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Dear Dr",
+            "*|FNAME|*"
+          ]
+        },
+        {
+          "id": "invite_phrase",
+          "label": "Invitation Phrase",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "You are cordially invited to attend"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "time",
+          "label": "Time Range",
+          "type": "time_range",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true
+        },
+        {
+          "id": "chairpersons_block",
+          "label": "Chairpersons Block",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "speakers_block",
+          "label": "Speakers Block",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "agenda_table",
+          "label": "Agenda Table",
+          "type": "table",
+          "required": true,
+          "expected_columns": [
+            "Time",
+            "Topic",
+            "Faculty"
+          ]
+        },
+        {
+          "id": "cta_register",
+          "label": "CTA to Register",
+          "type": "cta",
+          "required": true,
+          "expected_phrases": [
+            "Click here to register"
+          ]
+        },
+        {
+          "id": "disclaimer",
+          "label": "Disclaimer",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "pdf_invitation",
       "friendly_name": "PDF Invitation",
       "elements": [
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true },
-        { "id": "greeting", "label": "Greeting (Dear Doctor)", "type": "text", "required": true, "expected_phrases": ["Dear Doctor"] },
-        { "id": "invite_phrase", "label": "Invitation Phrase", "type": "text", "required": true, "expected_phrases": ["You are cordially invited to attend"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "date", "label": "Date", "type": "date", "required": true },
-        { "id": "time", "label": "Time Range", "type": "time_range", "required": true },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true },
-        { "id": "chairpersons_block", "label": "Chairpersons Block", "type": "section", "required": true },
-        { "id": "speakers_block", "label": "Speakers Block", "type": "section", "required": true },
-        { "id": "agenda_table", "label": "Agenda Table", "type": "table", "required": true },
-        { "id": "cta_register", "label": "CTA to Register", "type": "cta", "required": true },
-        { "id": "disclaimer", "label": "Disclaimer", "type": "text", "required": true },
-        { "id": "preparation_date", "label": "Preparation Date", "type": "date_or_placeholder", "required": true },
-        { "id": "approval_code", "label": "Approval Code", "type": "code", "required": true }
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "greeting",
+          "label": "Greeting (Dear Doctor)",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Dear Doctor"
+          ]
+        },
+        {
+          "id": "invite_phrase",
+          "label": "Invitation Phrase",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "You are cordially invited to attend"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "date",
+          "label": "Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "time",
+          "label": "Time Range",
+          "type": "time_range",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true
+        },
+        {
+          "id": "chairpersons_block",
+          "label": "Chairpersons Block",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "speakers_block",
+          "label": "Speakers Block",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "agenda_table",
+          "label": "Agenda Table",
+          "type": "table",
+          "required": true
+        },
+        {
+          "id": "cta_register",
+          "label": "CTA to Register",
+          "type": "cta",
+          "required": true
+        },
+        {
+          "id": "disclaimer",
+          "label": "Disclaimer",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "pdf_save_the_date",
       "friendly_name": "PDF Save the Date",
       "elements": [
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true },
-        { "id": "header_save_the_date", "label": "Save the Date Header", "type": "text", "required": true, "expected_phrases": ["Save the Date"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "time", "label": "Time", "type": "time", "required": true },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true },
-        { "id": "cta_add_to_calendar", "label": "Add to Calendar CTA", "type": "cta", "required": true, "expected_phrases": ["Click here to add to your calendar"] },
-        { "id": "chairpersons_block", "label": "Chairpersons Block", "type": "section", "required": false },
-        { "id": "speakers_block", "label": "Speakers Block", "type": "section", "required": false },
-        { "id": "disclaimer", "label": "Disclaimer", "type": "text", "required": true },
-        { "id": "preparation_date", "label": "Preparation Date", "type": "date_or_placeholder", "required": true },
-        { "id": "approval_code", "label": "Approval Code", "type": "code", "required": true }
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "header_save_the_date",
+          "label": "Save the Date Header",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Save the Date"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "time",
+          "label": "Time",
+          "type": "time",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true
+        },
+        {
+          "id": "cta_add_to_calendar",
+          "label": "Add to Calendar CTA",
+          "type": "cta",
+          "required": true,
+          "expected_phrases": [
+            "Click here to add to your calendar"
+          ]
+        },
+        {
+          "id": "chairpersons_block",
+          "label": "Chairpersons Block",
+          "type": "section",
+          "required": false
+        },
+        {
+          "id": "speakers_block",
+          "label": "Speakers Block",
+          "type": "section",
+          "required": false
+        },
+        {
+          "id": "disclaimer",
+          "label": "Disclaimer",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "printed_invitation",
       "friendly_name": "Printed Invitation",
       "elements": [
-        { "id": "company_logo_top", "label": "Top Company Logo", "type": "logo", "required": true },
-        { "id": "invitation_header", "label": "Invitation Header", "type": "text", "required": true, "expected_phrases": ["Invitation"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "time", "label": "Time Range", "type": "time_range", "required": true },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true },
-        { "id": "welcome_or_greeting", "label": "Welcome Note or Greeting", "type": "text", "required": true, "placeholder_examples": ["<<Welcome Message>>", "Dear Doctor"] },
-        { "id": "chairpersons_block", "label": "Chairpersons Block", "type": "section", "required": true },
-        { "id": "speakers_block", "label": "Speakers Block", "type": "section", "required": true },
-        { "id": "agenda_table", "label": "Agenda Table", "type": "table", "required": true },
-        { "id": "qr_registration", "label": "QR Code for Registration", "type": "qr_code_or_image", "required": true },
-        { "id": "company_logo_bottom", "label": "Bottom Company Logo", "type": "logo", "required": true },
-        { "id": "disclaimer", "label": "Disclaimer", "type": "text", "required": true },
-        { "id": "preparation_date", "label": "Preparation Date", "type": "date_or_placeholder", "required": true },
-        { "id": "approval_code", "label": "Approval Code", "type": "code", "required": true }
+        {
+          "id": "company_logo_top",
+          "label": "Top Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "invitation_header",
+          "label": "Invitation Header",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Invitation"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "time",
+          "label": "Time Range",
+          "type": "time_range",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true
+        },
+        {
+          "id": "welcome_or_greeting",
+          "label": "Welcome Note or Greeting",
+          "type": "text",
+          "required": true,
+          "placeholder_examples": [
+            "<<Welcome Message>>",
+            "Dear Doctor"
+          ]
+        },
+        {
+          "id": "chairpersons_block",
+          "label": "Chairpersons Block",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "speakers_block",
+          "label": "Speakers Block",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "agenda_table",
+          "label": "Agenda Table",
+          "type": "table",
+          "required": true
+        },
+        {
+          "id": "qr_registration",
+          "label": "QR Code for Registration",
+          "type": "qr_code_or_image",
+          "required": true
+        },
+        {
+          "id": "company_logo_bottom",
+          "label": "Bottom Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "disclaimer",
+          "label": "Disclaimer",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "rcp_certificate_attendance",
       "friendly_name": "RCP Certificate of Attendance",
       "elements": [
-        { "id": "certificate_title", "label": "Certificate Title", "type": "text", "required": true, "expected_phrases": ["Royal College of Physicians Certificate of Accreditation"] },
-        { "id": "recipient_name", "label": "Recipient Name", "type": "person_name", "required": true, "placeholder_examples": ["Dr << Name >>"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "rcp_activity_code", "label": "RCP Activity Code Number", "type": "code", "required": true },
-        { "id": "cpd_statement", "label": "CPD Credits Statement", "type": "text", "required": true, "expected_phrases": ["approved by the Federation of the Royal Colleges of Physicians of the United Kingdom", "category 1 (external) CPD credit"] },
-        { "id": "event_chairperson_signature", "label": "Event Chairperson Signature", "type": "signature_block", "required": true }
+        {
+          "id": "certificate_title",
+          "label": "Certificate Title",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Royal College of Physicians Certificate of Accreditation"
+          ]
+        },
+        {
+          "id": "recipient_name",
+          "label": "Recipient Name",
+          "type": "person_name",
+          "required": true,
+          "placeholder_examples": [
+            "Dr << Name >>"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "rcp_activity_code",
+          "label": "RCP Activity Code Number",
+          "type": "code",
+          "required": true
+        },
+        {
+          "id": "cpd_statement",
+          "label": "CPD Credits Statement",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "approved by the Federation of the Royal Colleges of Physicians of the United Kingdom",
+            "category 1 (external) CPD credit"
+          ]
+        },
+        {
+          "id": "event_chairperson_signature",
+          "label": "Event Chairperson Signature",
+          "type": "signature_block",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "agenda",
       "friendly_name": "Agenda Page",
       "elements": [
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "date", "label": "Date", "type": "date", "required": true },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true },
-        { "id": "agenda_header", "label": "Agenda Header", "type": "text", "required": true, "expected_phrases": ["Agenda"] },
-        { "id": "agenda_table", "label": "Agenda Table", "type": "table", "required": true, "expected_columns": ["Time", "Topic", "Faculty"] },
-        { "id": "disclaimer", "label": "Disclaimer", "type": "text", "required": true },
-        { "id": "preparation_date", "label": "Preparation Date", "type": "date_or_placeholder", "required": true },
-        { "id": "approval_code", "label": "Approval Code", "type": "code", "required": true }
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "date",
+          "label": "Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true
+        },
+        {
+          "id": "agenda_header",
+          "label": "Agenda Header",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Agenda"
+          ]
+        },
+        {
+          "id": "agenda_table",
+          "label": "Agenda Table",
+          "type": "table",
+          "required": true,
+          "expected_columns": [
+            "Time",
+            "Topic",
+            "Faculty"
+          ]
+        },
+        {
+          "id": "disclaimer",
+          "label": "Disclaimer",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "certificate_accreditation_dha_full",
       "friendly_name": "DHA Certificate of Accreditation (President + Chairs)",
       "elements": [
-        { "id": "certificate_title", "label": "Certificate Title", "type": "text", "required": true, "expected_phrases": ["Certificate of Accreditation"] },
-        { "id": "president_name", "label": "President Name", "type": "person_name", "required": true },
-        { "id": "chair_scientific_committee", "label": "Chair of Scientific Committee", "type": "person_name", "required": true },
-        { "id": "chair_organizing_committee", "label": "Chair of Organizing Committee", "type": "person_name", "required": true },
-        { "id": "recipient_name", "label": "Recipient Name", "type": "person_name", "required": true },
-        { "id": "attendance_text", "label": "Attendance Confirmation Text", "type": "text", "required": true, "expected_phrases": ["This certificate confirms that", "Has attended"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "cpd_points", "label": "CPD Credit Points", "type": "number_or_text", "required": true, "expected_phrases": ["Awarded", "CPD Credit Point", "Dubai Health Authority"] },
-        { "id": "accreditation_code", "label": "Accreditation Code", "type": "code", "required": true, "expected_phrases": ["Accreditation #", "CODE"] },
-        { "id": "completion_date", "label": "Completion Date", "type": "date", "required": true },
-        { "id": "venue", "label": "Venue & Location", "type": "venue", "required": true }
+        {
+          "id": "certificate_title",
+          "label": "Certificate Title",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Certificate of Accreditation"
+          ]
+        },
+        {
+          "id": "president_name",
+          "label": "President Name",
+          "type": "person_name",
+          "required": true
+        },
+        {
+          "id": "chair_scientific_committee",
+          "label": "Chair of Scientific Committee",
+          "type": "person_name",
+          "required": true
+        },
+        {
+          "id": "chair_organizing_committee",
+          "label": "Chair of Organizing Committee",
+          "type": "person_name",
+          "required": true
+        },
+        {
+          "id": "recipient_name",
+          "label": "Recipient Name",
+          "type": "person_name",
+          "required": true
+        },
+        {
+          "id": "attendance_text",
+          "label": "Attendance Confirmation Text",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "This certificate confirms that",
+            "Has attended"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "cpd_points",
+          "label": "CPD Credit Points",
+          "type": "number_or_text",
+          "required": true,
+          "expected_phrases": [
+            "Awarded",
+            "CPD Credit Point",
+            "Dubai Health Authority"
+          ]
+        },
+        {
+          "id": "accreditation_code",
+          "label": "Accreditation Code",
+          "type": "code",
+          "required": true,
+          "expected_phrases": [
+            "Accreditation #",
+            "CODE"
+          ]
+        },
+        {
+          "id": "completion_date",
+          "label": "Completion Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue & Location",
+          "type": "venue",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "certificate_appreciation_sponsor",
       "friendly_name": "Certificate of Appreciation (Sponsor)",
       "elements": [
-        { "id": "certificate_title", "label": "Certificate Title", "type": "text", "required": true, "expected_phrases": ["Certificate of Appreciation"] },
-        { "id": "recipient_company_name", "label": "Sponsor Company Name", "type": "company_name", "required": true, "placeholder_examples": ["<< Company Name >>"] },
-        { "id": "purpose_text", "label": "Purpose Text", "type": "text", "required": true, "expected_phrases": ["to express our gratitude and appreciation for generously supporting"] },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true },
-        { "id": "event_chairperson_signature", "label": "Event Chairperson Signature", "type": "signature_block", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true },
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true }
+        {
+          "id": "certificate_title",
+          "label": "Certificate Title",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Certificate of Appreciation"
+          ]
+        },
+        {
+          "id": "recipient_company_name",
+          "label": "Sponsor Company Name",
+          "type": "company_name",
+          "required": true,
+          "placeholder_examples": [
+            "<< Company Name >>"
+          ]
+        },
+        {
+          "id": "purpose_text",
+          "label": "Purpose Text",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "to express our gratitude and appreciation for generously supporting"
+          ]
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true
+        },
+        {
+          "id": "event_chairperson_signature",
+          "label": "Event Chairperson Signature",
+          "type": "signature_block",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "evaluation_form_post_event",
       "friendly_name": "Evaluation Form (Post-Event)",
       "elements": [
-        { "id": "header_title", "label": "Header Title", "type": "text", "required": true, "expected_phrases": ["Evaluation and Feedback"] },
-        { "id": "company_reference", "label": "Company Medical & Scientific Affairs Reference", "type": "text", "required": true },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "likert_questions", "label": "Likert Scale Questions (1–8)", "type": "list_of_questions", "required": true },
-        { "id": "open_question_learnings", "label": "Open Question: Key Learnings", "type": "open_question", "required": true },
-        { "id": "open_question_future_topics", "label": "Open Question: Future Topics", "type": "open_question", "required": true },
-        { "id": "optional_name", "label": "Optional Name Field", "type": "person_name_field", "required": false },
-        { "id": "optional_title", "label": "Optional Title Field", "type": "text_field", "required": false }
+        {
+          "id": "header_title",
+          "label": "Header Title",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Evaluation and Feedback"
+          ]
+        },
+        {
+          "id": "company_reference",
+          "label": "Company Medical & Scientific Affairs Reference",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "likert_questions",
+          "label": "Likert Scale Questions (1–8)",
+          "type": "list_of_questions",
+          "required": true
+        },
+        {
+          "id": "open_question_learnings",
+          "label": "Open Question: Key Learnings",
+          "type": "open_question",
+          "required": true
+        },
+        {
+          "id": "open_question_future_topics",
+          "label": "Open Question: Future Topics",
+          "type": "open_question",
+          "required": true
+        },
+        {
+          "id": "optional_name",
+          "label": "Optional Name Field",
+          "type": "person_name_field",
+          "required": false
+        },
+        {
+          "id": "optional_title",
+          "label": "Optional Title Field",
+          "type": "text_field",
+          "required": false
+        }
       ]
     },
     {
       "template_key": "event_booklet",
       "friendly_name": "Event Booklet",
       "elements": [
-        { "id": "back_cover_logos", "label": "Back Cover Logos", "type": "logo_group", "required": true },
-        { "id": "back_cover_disclaimer", "label": "Back Cover Disclaimer", "type": "text", "required": true },
-        { "id": "back_cover_prep_approval", "label": "Back Cover Preparation Date & Approval Code", "type": "date_and_code", "required": true },
-        { "id": "front_cover_logos", "label": "Front Cover Logos", "type": "logo_group", "required": true },
-        { "id": "front_cover_event_name", "label": "Front Cover Event Name", "type": "event_name", "required": true },
-        { "id": "front_cover_company_logo", "label": "Front Cover Company Logo", "type": "logo", "required": true },
-        { "id": "event_details_block", "label": "Event Details Block (Date/Time/Venue)", "type": "section", "required": true },
-        { "id": "welcome_note", "label": "Welcome Note", "type": "text", "required": true },
-        { "id": "summary_objectives", "label": "Summary & Objectives", "type": "text", "required": true },
-        { "id": "accreditation_information", "label": "Accreditation Information", "type": "text", "required": true },
-        { "id": "program_description", "label": "Program Description", "type": "text", "required": true },
-        { "id": "agenda_table", "label": "Agenda Table", "type": "table", "required": true },
-        { "id": "faculty_section", "label": "Faculty Section (Chairpersons & Speakers)", "type": "section", "required": true },
-        { "id": "speaker_page_structure", "label": "Speaker Pages Structure", "type": "section", "required": true, "expected_subfields": ["Speaker's name", "Bio", "Topic", "Time", "Short bio", "Objective", "Notes"] },
-        { "id": "notes_section", "label": "Notes Page", "type": "notes_area", "required": false },
-        { "id": "sponsors_logos", "label": "Sponsors Logos Section", "type": "logo_group", "required": true }
+        {
+          "id": "back_cover_logos",
+          "label": "Back Cover Logos",
+          "type": "logo_group",
+          "required": true
+        },
+        {
+          "id": "back_cover_disclaimer",
+          "label": "Back Cover Disclaimer",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "back_cover_prep_approval",
+          "label": "Back Cover Preparation Date & Approval Code",
+          "type": "date_and_code",
+          "required": true
+        },
+        {
+          "id": "front_cover_logos",
+          "label": "Front Cover Logos",
+          "type": "logo_group",
+          "required": true
+        },
+        {
+          "id": "front_cover_event_name",
+          "label": "Front Cover Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "front_cover_company_logo",
+          "label": "Front Cover Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_details_block",
+          "label": "Event Details Block (Date/Time/Venue)",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "welcome_note",
+          "label": "Welcome Note",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "summary_objectives",
+          "label": "Summary & Objectives",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "accreditation_information",
+          "label": "Accreditation Information",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "program_description",
+          "label": "Program Description",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "agenda_table",
+          "label": "Agenda Table",
+          "type": "table",
+          "required": true
+        },
+        {
+          "id": "faculty_section",
+          "label": "Faculty Section (Chairpersons & Speakers)",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "speaker_page_structure",
+          "label": "Speaker Pages Structure",
+          "type": "section",
+          "required": true,
+          "expected_subfields": [
+            "Speaker's name",
+            "Bio",
+            "Topic",
+            "Time",
+            "Short bio",
+            "Objective",
+            "Notes"
+          ]
+        },
+        {
+          "id": "notes_section",
+          "label": "Notes Page",
+          "type": "notes_area",
+          "required": false
+        },
+        {
+          "id": "sponsors_logos",
+          "label": "Sponsors Logos Section",
+          "type": "logo_group",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "landing_page_registration",
       "friendly_name": "Landing Page & Registration",
       "elements": [
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true },
-        { "id": "welcome_note", "label": "Welcome Note", "type": "text", "required": true },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_overview", "label": "Event Overview & Details", "type": "text", "required": true },
-        { "id": "date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "time", "label": "Time Range", "type": "time_range", "required": true },
-        { "id": "venue", "label": "Venue", "type": "venue", "required": true },
-        { "id": "chairpersons_block", "label": "Chairpersons Block", "type": "section", "required": true },
-        { "id": "speakers_block", "label": "Speakers Block", "type": "section", "required": true },
-        { "id": "agenda_table", "label": "Agenda Table", "type": "table", "required": true },
-        { "id": "cta_register_buttons", "label": "Register Buttons", "type": "cta", "required": true, "expected_phrases": ["Click here to register"] },
-        { "id": "countdown", "label": "Time Countdown Widget/Placeholder", "type": "widget_or_placeholder", "required": false },
-        { "id": "disclaimer", "label": "Disclaimer", "type": "text", "required": true },
-        { "id": "preparation_date", "label": "Preparation Date", "type": "date_or_placeholder", "required": true },
-        { "id": "approval_code", "label": "Approval Code", "type": "code", "required": true },
-        { "id": "form_first_name", "label": "Form Field: First Name", "type": "text_field", "required": true },
-        { "id": "form_last_name", "label": "Form Field: Last Name", "type": "text_field", "required": true },
-        { "id": "form_phone", "label": "Form Field: Phone", "type": "phone_field", "required": true },
-        { "id": "form_email", "label": "Form Field: Email", "type": "email_field", "required": true },
-        { "id": "form_specialty", "label": "Form Field: Specialty", "type": "select_field", "required": true },
-        { "id": "form_country", "label": "Form Field: Country", "type": "select_field", "required": true },
-        { "id": "form_affiliation", "label": "Form Field: Affiliation/Hospital", "type": "text_field", "required": true },
-        { "id": "form_scfhs", "label": "Form Field: SCFHS (For Saudi only)", "type": "text_field", "required": false },
-        { "id": "mandatory_disclaimer_tick", "label": "Mandatory Disclaimer Tick Box", "type": "checkbox", "required": true }
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "welcome_note",
+          "label": "Welcome Note",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_overview",
+          "label": "Event Overview & Details",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "time",
+          "label": "Time Range",
+          "type": "time_range",
+          "required": true
+        },
+        {
+          "id": "venue",
+          "label": "Venue",
+          "type": "venue",
+          "required": true
+        },
+        {
+          "id": "chairpersons_block",
+          "label": "Chairpersons Block",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "speakers_block",
+          "label": "Speakers Block",
+          "type": "section",
+          "required": true
+        },
+        {
+          "id": "agenda_table",
+          "label": "Agenda Table",
+          "type": "table",
+          "required": true
+        },
+        {
+          "id": "cta_register_buttons",
+          "label": "Register Buttons",
+          "type": "cta",
+          "required": true,
+          "expected_phrases": [
+            "Click here to register"
+          ]
+        },
+        {
+          "id": "countdown",
+          "label": "Time Countdown Widget/Placeholder",
+          "type": "widget_or_placeholder",
+          "required": false
+        },
+        {
+          "id": "disclaimer",
+          "label": "Disclaimer",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        },
+        {
+          "id": "form_first_name",
+          "label": "Form Field: First Name",
+          "type": "text_field",
+          "required": true
+        },
+        {
+          "id": "form_last_name",
+          "label": "Form Field: Last Name",
+          "type": "text_field",
+          "required": true
+        },
+        {
+          "id": "form_phone",
+          "label": "Form Field: Phone",
+          "type": "phone_field",
+          "required": true
+        },
+        {
+          "id": "form_email",
+          "label": "Form Field: Email",
+          "type": "email_field",
+          "required": true
+        },
+        {
+          "id": "form_specialty",
+          "label": "Form Field: Specialty",
+          "type": "select_field",
+          "required": true
+        },
+        {
+          "id": "form_country",
+          "label": "Form Field: Country",
+          "type": "select_field",
+          "required": true
+        },
+        {
+          "id": "form_affiliation",
+          "label": "Form Field: Affiliation/Hospital",
+          "type": "text_field",
+          "required": true
+        },
+        {
+          "id": "form_scfhs",
+          "label": "Form Field: SCFHS (For Saudi only)",
+          "type": "text_field",
+          "required": false
+        },
+        {
+          "id": "mandatory_disclaimer_tick",
+          "label": "Mandatory Disclaimer Tick Box",
+          "type": "checkbox",
+          "required": true
+        }
       ]
     },
     {
       "template_key": "slides_permission",
       "friendly_name": "Slides Permission Form",
       "elements": [
-        { "id": "company_logo", "label": "Company Logo", "type": "logo", "required": true },
-        { "id": "event_logo", "label": "Event Logo", "type": "logo", "required": true },
-        { "id": "permission_header", "label": "Permission Header", "type": "text", "required": true, "expected_phrases": ["Permission"] },
-        { "id": "permission_body", "label": "Permission Body Text", "type": "text", "required": true, "expected_phrases": ["give my permission", "share my slides", "PDF Via email", "Video in a webcast mode"] },
-        { "id": "company_name_reference", "label": "Company Name Reference", "type": "company_name", "required": true },
-        { "id": "event_name", "label": "Event Name", "type": "event_name", "required": true },
-        { "id": "event_date", "label": "Event Date", "type": "date", "required": true },
-        { "id": "comments_section", "label": "Comments Section", "type": "multiline_text_area", "required": false },
-        { "id": "name_field", "label": "Name Field", "type": "person_name_field", "required": true },
-        { "id": "signature_field", "label": "Signature Field", "type": "signature_block", "required": true }
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true
+        },
+        {
+          "id": "permission_header",
+          "label": "Permission Header",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Permission"
+          ]
+        },
+        {
+          "id": "permission_body",
+          "label": "Permission Body Text",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "give my permission",
+            "share my slides",
+            "PDF Via email",
+            "Video in a webcast mode"
+          ]
+        },
+        {
+          "id": "company_name_reference",
+          "label": "Company Name Reference",
+          "type": "company_name",
+          "required": true
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        },
+        {
+          "id": "event_date",
+          "label": "Event Date",
+          "type": "date",
+          "required": true
+        },
+        {
+          "id": "comments_section",
+          "label": "Comments Section",
+          "type": "multiline_text_area",
+          "required": false
+        },
+        {
+          "id": "name_field",
+          "label": "Name Field",
+          "type": "person_name_field",
+          "required": true
+        },
+        {
+          "id": "signature_field",
+          "label": "Signature Field",
+          "type": "signature_block",
+          "required": true
+        }
+      ]
+    },
+    {
+      "template_key": "backdrop",
+      "friendly_name": "Event Backdrop",
+      "elements": [
+        {
+          "id": "event_visuals",
+          "label": "Event Visuals",
+          "type": "visual_elements",
+          "required": true
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        },
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "company"
+        },
+        {
+          "id": "disclaimers",
+          "label": "Disclaimers",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
+      ]
+    },
+    {
+      "template_key": "registration_desk",
+      "friendly_name": "Registration Desk Sign",
+      "elements": [
+        {
+          "id": "event_visuals_or_logo",
+          "label": "Event Visuals or Logo",
+          "type": "visual_or_logo",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
+      ]
+    },
+    {
+      "template_key": "registration_desk_table_tent",
+      "friendly_name": "Registration Desk Table Tent",
+      "elements": [
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        },
+        {
+          "id": "country_or_city",
+          "label": "Country/City",
+          "type": "location",
+          "required": true
+        },
+        {
+          "id": "registration_status",
+          "label": "Registered/Non-registered Label",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Registered",
+            "Nonregistered"
+          ]
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
+      ]
+    },
+    {
+      "template_key": "name_tags",
+      "friendly_name": "Name Tags",
+      "elements": [
+        {
+          "id": "doctor_name",
+          "label": "Doctor Name Placeholder",
+          "type": "person_name",
+          "required": true,
+          "placeholder_examples": [
+            "Dr Name"
+          ]
+        },
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "company"
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        }
+      ]
+    },
+    {
+      "template_key": "signage",
+      "friendly_name": "Room Signage",
+      "elements": [
+        {
+          "id": "room_name",
+          "label": "Room Name",
+          "type": "text",
+          "required": true
+        },
+        {
+          "id": "organized_by",
+          "label": "Organized By Text",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Organized by"
+          ]
+        },
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "company"
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        }
+      ]
+    },
+    {
+      "template_key": "airport_signage",
+      "friendly_name": "Airport Signage (A3 size)",
+      "elements": [
+        {
+          "id": "organized_by",
+          "label": "Organized By Text",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Organized by"
+          ]
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        },
+        {
+          "id": "doctor_name",
+          "label": "Doctor Name (A4 Space)",
+          "type": "person_name",
+          "required": true,
+          "placeholder_examples": [
+            "Dr Name"
+          ]
+        }
+      ]
+    },
+    {
+      "template_key": "table_tent_qr",
+      "friendly_name": "Table Tent with QR Code",
+      "elements": [
+        {
+          "id": "instruction_text",
+          "label": "QR Code Instruction Text",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Please scan the QR code to ask questions and fill in the meeting evaluation form"
+          ]
+        },
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "company"
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        },
+        {
+          "id": "qr_code",
+          "label": "QR Code",
+          "type": "qr_code_or_image",
+          "required": true
+        },
+        {
+          "id": "preparation_date",
+          "label": "Preparation Date",
+          "type": "date_or_placeholder",
+          "required": true
+        },
+        {
+          "id": "approval_code",
+          "label": "Approval Code",
+          "type": "code",
+          "required": true
+        }
+      ]
+    },
+    {
+      "template_key": "faculty_table_tent",
+      "friendly_name": "Faculty Table Tent",
+      "elements": [
+        {
+          "id": "doctor_name",
+          "label": "Doctor Name Placeholder",
+          "type": "person_name",
+          "required": true,
+          "placeholder_examples": [
+            "Dr Name"
+          ]
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        }
+      ]
+    },
+    {
+      "template_key": "block_note",
+      "friendly_name": "Block Note",
+      "elements": [
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "company"
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        },
+        {
+          "id": "event_name",
+          "label": "Event Name",
+          "type": "event_name",
+          "required": true
+        }
+      ]
+    },
+    {
+      "template_key": "question_card",
+      "friendly_name": "Question Card (A5 Double Face)",
+      "elements": [
+        {
+          "id": "questions_header",
+          "label": "Questions Header",
+          "type": "text",
+          "required": true,
+          "expected_phrases": [
+            "Questions"
+          ]
+        },
+        {
+          "id": "writing_lines",
+          "label": "Lines for Writing Questions",
+          "type": "text_area",
+          "required": true
+        },
+        {
+          "id": "company_logo",
+          "label": "Company Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "company"
+        },
+        {
+          "id": "event_logo",
+          "label": "Event Logo",
+          "type": "logo",
+          "required": true,
+          "logo_role": "event"
+        }
       ]
     }
   ]
-}
-
+}

app/validator.py

@@ -10,8 +10,9 @@ import tempfile
 import logging
 import time
 import shutil
+import io
 from io import BytesIO
-from typing import Dict, List, Optional, Tuple
+from typing import Dict, List, Optional, Tuple, Any
 from pathlib import Path
 from dataclasses import dataclass, asdict
 from datetime import datetime
@@ -585,6 +586,436 @@ class Validator:
         self.client = load_llm_client()
         # Use Claude Opus 4 which supports multimodal (images)
         self.model = "claude-opus-4-20250514"
+
+    async def check_links(self, links: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+        """
+        Check health of extracted links using HTTP HEAD/GET requests.
+        """
+        import aiohttp
+        import asyncio
+        
+        results = []
+        if not links:
+            return results
+        
+        # Add headers to avoid being blocked as a bot
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
+        }
+        
+        # Increase timeout to 10 seconds for slower sites
+        async with aiohttp.ClientSession(timeout=aiohttp.ClientTimeout(total=10), headers=headers) as session:
+            for link in links:
+                url = link["url"]
+                # Handle www without protocol
+                check_url = url
+                if url.startswith("www."):
+                    check_url = "https://" + url
+                    
+                status = "unknown"
+                message = ""
+                status_code = 0
+                
+                try:
+                    if check_url.startswith("mailto:"):
+                        status = "valid"  # Assume mailto is valid format
+                        message = "Email link"
+                        status_code = 200
+                    else:
+                        try:
+                            # Try GET directly (skip HEAD since many sites block it)
+                            async with session.get(check_url, allow_redirects=True, ssl=False) as response:
+                                status_code = response.status
+                                if 200 <= status_code < 400:
+                                    status = "valid"
+                                    message = "OK"
+                                else:
+                                    status = "broken"
+                                    message = f"HTTP {status_code}"
+                        except aiohttp.ClientError as e:
+                            # More specific error message
+                            status = "broken"
+                            message = f"Connection error: {type(e).__name__}"
+                            status_code = 0
+                except asyncio.TimeoutError:
+                    status = "broken"
+                    message = "Timeout (>10s)"
+                    status_code = 408
+                except Exception as e:
+                    status = "broken" 
+                    message = f"Error: {type(e).__name__}"
+                    status_code = 0
+                    
+                results.append({
+                    "url": url,
+                    "status": status,
+                    "status_code": status_code,
+                    "message": message,
+                    "page": str(link.get("page", "Unknown"))
+                })
+                
+        return results
+
+    async def compare_documents(
+        self,
+        file1_content: bytes,
+        file1_extension: str,
+        file1_name: str,
+        file2_content: bytes,
+        file2_extension: str,
+        file2_name: str
+    ) -> Dict[str, Any]:
+        """
+        Compare two document versions using LLM to identify semantic changes.
+        
+        Args:
+            file1_content: Binary content of first document
+            file1_extension: File extension of first document
+            file1_name: Filename of first document
+            file2_content: Binary content of second document
+            file2_extension: File extension of second document
+            file2_name: Filename of second document
+        
+        Returns:
+            Dictionary with comparison results including summary and detailed changes
+        """
+        logger.info(f"Starting comparison: {file1_name} vs {file2_name}")
+        
+        # Extract text from both documents
+        text1 = extract_document_text(file1_content, file1_extension)
+        text2 = extract_document_text(file2_content, file2_extension)
+        
+        logger.info(f"Extracted text - File 1: {len(text1)} chars, File 2: {len(text2)} chars")
+        
+        if not text1 and not text2:
+            raise ValueError("Both documents appear to be empty or contain no extractable text")
+        
+        # Build LLM prompt for comparison
+        comparison_prompt = f"""You are comparing two versions of a document to identify what changed.
+
+DOCUMENT 1 ({file1_name}):
+{text1[:10000]}  # Limit to avoid token limits
+
+DOCUMENT 2 ({file2_name}):
+{text2[:10000]}
+
+Please analyze the differences between these two documents and provide:
+
+1. A natural language summary of the main changes (2-3 sentences)
+2. A detailed list of specific changes
+
+Format your response as a JSON object with this structure:
+{{
+    "summary": "Brief summary of changes...",
+    "changes": [
+        {{
+            "type": "addition|deletion|modification",
+            "section": "Optional section name where change occurred",
+            "description": "Description of the change"
+        }}
+    ]
+}}
+
+Focus on:
+- Content additions or deletions
+- Text modifications
+- Structural changes (headings, lists, tables)
+- Significant formatting changes
+
+If the documents are identical, return an empty changes array.
+"""
+
+        try:
+            # Call LLM API
+            logger.info("Calling LLM for document comparison...")
+            
+            message = self.client.messages.create(
+                model="claude-opus-4-20250514",
+                max_tokens=4096,
+                temperature=0.1,
+                messages=[
+                    {
+                        "role": "user",
+                        "content": comparison_prompt
+                    }
+                ]
+            )
+            
+            response_text = message.content[0].text if message.content else ""
+            logger.info(f"Received comparison response ({len(response_text)} chars)")
+            
+            # Parse JSON response
+            import json
+            comparison_data = json.loads(response_text)
+            
+            logger.info(f"Comparison complete: {len(comparison_data.get('changes', []))} changes detected")
+            
+            return comparison_data
+            
+        except Exception as e:
+            logger.error(f"Comparison failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Failed to compare documents: {str(e)}")
+
+    async def bulk_validate_certificates(
+        self,
+        excel_content: bytes,
+        name_column: str,
+        certificate_data: List[Tuple[str, bytes, str]]
+    ) -> Dict[str, Any]:
+        """
+        Validate multiple certificates against Excel name list with fuzzy matching.
+        
+        Args:
+            excel_content: Binary content of Excel file
+            name_column: Column name containing names
+            certificate_data: List of (filename, content, extension) tuples
+        
+        Returns:
+            Dictionary with validation results including exact/fuzzy matches
+        """
+        logger.info(f"Starting bulk validation: {len(certificate_data)} certificates")
+        
+        try:
+            import openpyxl
+            from io import BytesIO
+            from difflib import SequenceMatcher
+            
+            # Parse Excel and extract names
+            wb = openpyxl.load_workbook(BytesIO(excel_content))
+            ws = wb.active
+            
+            # Find column index
+            headers = [str(cell.value) for cell in ws[1] if cell.value]
+            if name_column not in headers:
+                raise ValueError(f"Column '{name_column}' not found in Excel file")
+            
+            col_idx = headers.index(name_column) + 1
+            
+            # Extract names from Excel (skip header row)
+            excel_names = []
+            for row in ws.iter_rows(min_row=2, min_col=col_idx, max_col=col_idx):
+                if row[0].value:
+                    excel_names.append(str(row[0].value).strip())
+            
+            logger.info(f"Extracted {len(excel_names)} names from Excel")
+            
+            # Extract names from certificates (parallel processing)
+            cert_names = {}
+            for filename, content, ext in certificate_data:
+                try:
+                    text = extract_document_text(content, ext)
+                    # Store extracted text for this certificate
+                    cert_names[filename] = text
+                except Exception as e:
+                    logger.warning(f"Failed to extract from {filename}: {str(e)}")
+                    cert_names[filename] = ""
+            
+            logger.info(f"Extracted text from {len(cert_names)} certificates")
+            
+            # Match names
+            results = {
+                "total_names": len(excel_names),
+                "total_certificates": len(certificate_data),
+                "exact_matches": 0,
+                "fuzzy_matches": 0,
+                "missing": 0,
+                "extras": 0,
+                "details": []
+            }
+            
+            matched_certs = set()
+            
+            # Check each Excel name against certificates
+            for name in excel_names:
+                found = False
+                best_match = None
+                best_similarity = 0
+                
+                for cert_file, cert_text in cert_names.items():
+                    # Exact match
+                    if name.lower() in cert_text.lower():
+                        results["exact_matches"] += 1
+                        results["details"].append({
+                            "name": name,
+                            "status": "exact_match",
+                            "certificate_file": cert_file,
+                            "similarity": 100
+                        })
+                        matched_certs.add(cert_file)
+                        found = True
+                        break
+                    
+                    # Fuzzy match
+                    similarity = SequenceMatcher(None, name.lower(), cert_text.lower()).ratio() * 100
+                    if similarity >= 90 and similarity > best_similarity:
+                        best_similarity = similarity
+                        best_match = cert_file
+                
+                if not found:
+                    if best_match and best_similarity >= 90:
+                        # Fuzzy match found
+                        results["fuzzy_matches"] += 1
+                        results["details"].append({
+                            "name": name,
+                            "status": "fuzzy_match",
+                            "certificate_file": best_match,
+                            "similarity": int(best_similarity)
+                        })
+                        matched_certs.add(best_match)
+                    else:
+                        # Missing
+                        results["missing"] += 1
+                        results["details"].append({
+                            "name": name,
+                            "status": "missing",
+                            "certificate_file": None,
+                            "similarity": None
+                        })
+            
+            # Find extra certificates (not matched to any Excel name)
+            for cert_file in cert_names.keys():
+                if cert_file not in matched_certs:
+                    results["extras"] += 1
+                    results["details"].append({
+                        "name": f"[Certificate: {cert_file}]",
+                        "status": "extra",
+                        "certificate_file": cert_file,
+                        "similarity": None
+                    })
+            
+            logger.info(f"Bulk validation complete: {results['exact_matches']} exact, "
+                       f"{results['fuzzy_matches']} fuzzy, {results['missing']} missing, "
+                       f"{results['extras']} extra")
+            
+            return results
+            
+        except Exception as e:
+            logger.error(f"Bulk validation failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Failed to validate certificates: {str(e)}")
+
+    def extract_links(self, file_content: bytes, file_extension: str) -> List[Dict[str, Any]]:
+        """
+        Extract links from PDF, DOCX, or PPTX files.
+        """
+        links = []
+        logger.info(f"Extracting links from {file_extension} document (size: {len(file_content)} bytes)")
+        
+        try:
+            if file_extension == ".pdf":
+                with fitz.open(stream=file_content, filetype="pdf") as doc:
+                    logger.info(f"PDF page count: {len(doc)}")
+                    for page_num, page in enumerate(doc):
+                        page_links = page.get_links()
+                        logger.info(f"Page {page_num+1} has {len(page_links)} link objects")
+                        for link in page_links:
+                            if "uri" in link:
+                                logger.info(f"  Found PDF URI: {link['uri']}")
+                                links.append({
+                                    "url": link["uri"],
+                                    "page": page_num + 1,
+                                    "source": "page_link"
+                                })
+                                
+            elif file_extension == ".docx":
+                # For DOCX, we need to inspect the relationship files in the zip
+                from zipfile import ZipFile
+                from lxml import etree
+                
+                logger.info("Processing DOCX for links...")
+                with io.BytesIO(file_content) as docx_file:
+                    with ZipFile(docx_file) as zip_ref:
+                        # List all files for debugging
+                        # logger.info(f"Files in DOCX: {zip_ref.namelist()}")
+                        
+                        # Find all relationship files
+                        rel_files = [f for f in zip_ref.namelist() if f.endswith(".rels")]
+                        logger.info(f"Found {len(rel_files)} relationship files: {rel_files}")
+                        
+                        for rel_file in rel_files:
+                            try:
+                                with zip_ref.open(rel_file) as f:
+                                    tree = etree.parse(f)
+                                    root = tree.getroot()
+                                    namespaces = {'rel': 'http://schemas.openxmlformats.org/package/2006/relationships'}
+                                    
+                                    rels = root.findall(".//rel:Relationship", namespaces)
+                                    logger.info(f"  Scanning {rel_file}: found {len(rels)} relationships")
+                                    
+                                    for rel in rels:
+                                        target = rel.get("Target")
+                                        type_attr = rel.get("Type")
+                                        
+                                        if type_attr and "hyperlink" in type_attr and target:
+                                            logger.info(f"  Found DOCX Hyperlink: {target}")
+                                            links.append({
+                                                "url": target,
+                                                "page": "Unknown",  # DOCX doesn't have fixed pages
+                                                "source": "document_link"
+                                            })
+                            except Exception as e:
+                                logger.error(f"Error parsing {rel_file}: {e}")
+                                continue
+                                
+            elif file_extension == ".pptx":
+                from pptx import Presentation
+                logger.info("Processing PPTX for links...")
+                with io.BytesIO(file_content) as ppt_file:
+                    prs = Presentation(ppt_file)
+                    for slide_num, slide in enumerate(prs.slides):
+                        logger.info(f"Scanning Slide {slide_num+1} with {len(slide.shapes)} shapes")
+                        for shape in slide.shapes:
+                            # Check shape click action
+                            try:
+                                if shape.click_action and shape.click_action.hyperlink and shape.click_action.hyperlink.address:
+                                    url = shape.click_action.hyperlink.address
+                                    logger.info(f"  Found PPTX Shape Link: {url}")
+                                    links.append({
+                                        "url": url,
+                                        "page": f"Slide {slide_num + 1}",
+                                        "source": "shape_link"
+                                    })
+                            except AttributeError:
+                                pass
+                                
+                            # Check text runs
+                            if hasattr(shape, "text_frame"):
+                                try:
+                                    for paragraph in shape.text_frame.paragraphs:
+                                        for run in paragraph.runs:
+                                            if run.hyperlink and run.hyperlink.address:
+                                                url = run.hyperlink.address
+                                                logger.info(f"  Found PPTX Text Link: {url}")
+                                                links.append({
+                                                    "url": url,
+                                                    "page": f"Slide {slide_num + 1}",
+                                                    "source": "text_link"
+                                                })
+                                except AttributeError:
+                                    pass
+
+        except Exception as e:
+            logger.error(f"Error extracting links: {str(e)}", exc_info=True)
+            
+        # Deduplicate links
+        unique_links = []
+        seen_urls = set()
+        logger.info(f"Total raw links found: {len(links)}")
+        
+        for link in links:
+            url = link["url"].strip()
+            # Relaxed filtering logic for debugging: accept everything that looks like a potential link
+            # We'll filter strictly later if needed, but for now we want to see what we rejected
+            is_valid_format = (url.startswith("http") or url.startswith("mailto:") or url.startswith("www."))
+            
+            if not is_valid_format:
+                 logger.warning(f"Rejected link format: '{url}'")
+            
+            if url and url not in seen_urls and is_valid_format:
+                seen_urls.add(url)
+                unique_links.append(link)
+                
+        logger.info(f"Unique valid links returned: {len(unique_links)}")
+        return unique_links
     
     def _generate_image_catalog(self, extracted_images: List[ExtractedImage]) -> str:
         """
@@ -1328,11 +1759,12 @@ RESPOND WITH JSON ONLY - NO ADDITIONAL TEXT OR MARKDOWN.
         
         return report
     
-    def validate_document(
+    async def validate_document(
         self, 
         file_content: bytes, 
         file_extension: str, 
-        template_key: str
+        template_key: str,
+        custom_prompt: Optional[str] = None
     ) -> Dict:
         """
         Validate a document against a template using multimodal LLM.
@@ -1341,6 +1773,7 @@ RESPOND WITH JSON ONLY - NO ADDITIONAL TEXT OR MARKDOWN.
             file_content: Binary content of the document file
             file_extension: File extension (e.g., '.pdf', '.docx', '.pptx')
             template_key: Template key to validate against
+            custom_prompt: Optional custom instructions to adapt validation
         
         Returns:
             Validation report dictionary with status and element reports
@@ -1348,6 +1781,28 @@ RESPOND WITH JSON ONLY - NO ADDITIONAL TEXT OR MARKDOWN.
         Raises:
             ValueError: If template not found, extraction fails, or validation fails
         """
+        logger.info(f"Starting validation for {file_extension} document against template {template_key}")
+
+        # 1. Extract Links & Check Health (Async)
+        logger.info("======================================")
+        logger.info("STARTING LINK VALIDATION")
+        logger.info("======================================")
+        logger.info("Extracting and checking links...")
+        try:
+            extracted_links = self.extract_links(file_content, file_extension)
+            logger.info(f"✓ extract_links returned {len(extracted_links)} links")
+            if extracted_links:
+                logger.info(f"  Links: {[link.get('url') for link in extracted_links]}")
+            
+            link_validation_results = await self.check_links(extracted_links)
+            logger.info(f"✓ check_links returned {len(link_validation_results)} results")
+        except Exception as e:
+            logger.error(f"❌ Link validation failed with exception: {e}", exc_info=True)
+            link_validation_results = []
+        
+        logger.info(f"Final link_validation_results count: {len(link_validation_results)}")
+        logger.info("======================================")
+
         # Load template
         template = get_template(template_key)
         if not template:
@@ -1480,6 +1935,7 @@ RESPOND WITH JSON ONLY - NO ADDITIONAL TEXT OR MARKDOWN.
                 logger.warning("No text extracted, but rendered image available. Proceeding with visual validation.")
                 extracted_text = "[NO TEXT EXTRACTED - RELYING ON VISUAL VALIDATION]"
             
+            
             # Build multimodal prompt for rendered page
             logger.info("Building multimodal prompt for LLM...")
             if rendered_image_path:
@@ -1491,6 +1947,15 @@ RESPOND WITH JSON ONLY - NO ADDITIONAL TEXT OR MARKDOWN.
                 content = self._build_text_only_prompt(extracted_text, template)
                 logger.info(f"Prompt contains {len(content)} content block(s) (text-only validation)")
             
+            # Append custom instructions if provided
+            if custom_prompt and custom_prompt.strip():
+                custom_instruction_block = {
+                    "type": "text",
+                    "text": f"\n\n ADDITIONAL USER INSTRUCTIONS:\n{custom_prompt.strip()}\n\nPlease incorporate these additional instructions into your validation process."
+                }
+                content.append(custom_instruction_block)
+                logger.info(f"Added custom instructions to prompt ({len(custom_prompt)} characters)")
+            
             # Call LLM API with fallback models (all support multimodal)
             models_to_try = [
                 "claude-opus-4-20250514",
@@ -1576,6 +2041,9 @@ RESPOND WITH JSON ONLY - NO ADDITIONAL TEXT OR MARKDOWN.
                 else:
                     raise ValueError("LLM API error: Unable to connect to any Claude model")
             
+            # Add link report to result
+            validation_report["link_report"] = link_validation_results
+            
             return validation_report
             
         finally:
@@ -1629,58 +2097,53 @@ RESPOND WITH JSON ONLY - NO ADDITIONAL TEXT OR MARKDOWN.
             
         logger.info(f"Starting spell check for text ({len(document_text)} characters)")
         
-        # Build spell check prompt
-        SPELL_CHECK_PROMPT = f"""
-You are a professional spell checker for medical and professional documents.
-
-CRITICAL RULES:
-1. IGNORE all proper nouns including:
-   - Person names (English, Arabic, South Asian, and all other origins)
-   - Place names (cities, countries, hospitals, venues, universities)
-   - Organization names (companies, institutions, medical organizations)
-   - Event names
-   - Brand names
-   - Medical titles: Dr., Prof., Sheikh, etc.
-
-2. ONLY flag genuine errors:
-   - Misspelled common words
-   - Typos (swapped letters, missing letters, duplicated letters)
-   - Wrong word usage in context
-   - Basic grammar errors
-
-3. For each error found, provide:
-   - The incorrect word (exactly as it appears)
-   - Surrounding context (about 20-30 characters before and after the word)
-   - 2-3 suggestions for correction
-   - Error type: "spelling", "grammar", or "typo"
-   - Confidence level (0.0-1.0) - only flag errors you're confident about (>0.7)
-
-4. SPECIAL CONSIDERATION FOR NAMES:
-   - Arabic names and transliterations: محمد, أحمد, فاطمة, Muhammad, Ahmed, Fatima, etc.
-   - Names following titles like Dr., Prof., Sheikh
-   - Names in speaker lists, attendee lists, or after "presented by", "Speaker:", etc.
-   - DO NOT flag unfamiliar names as errors
-
-5. MEDICAL TERMINOLOGY:
-   - Do not flag medical terms, abbreviations, or technical jargon
-   - Accept CPD, DHA, RCP, and other medical organization acronyms
-
-DOCUMENT TEXT TO CHECK:
-{document_text}
+        
+        # Prepare prompt for quality checking (spelling, grammar, formatting)
+        prompt = f"""
+Analyze the following text from a medical document for spelling, grammar, and formatting consistency issues.
 
-OUTPUT FORMAT: Return ONLY valid JSON with no markdown formatting:
+TEXT TO ANALYZE:
+---
+{document_text}
+---
+
+INSTRUCTIONS:
+1. **Spelling & Arabic Support**:
+   - Check both English and Arabic text for spelling errors.
+   - IGNORE proper names (including common Arabic names like Mohammed, Ahmed, etc.), locations, and medical terminology.
+   - IGNORE brand names or specialized abbreviations.
+
+2. **Grammar**:
+   - Identify grammatical errors, awkward phrasing, or punctuation issues.
+   - Ensure the tone remains professional.
+
+3. **Formatting Consistency (CRITICAL)**:
+   - **AM/PM Consistency**: Strictly only uppercase "AM" and "PM" are permitted. 
+   - Flag ANY variation such as "Am", "am", "aM", "Pm", "pm", "pM" as a "formatting" error.
+   - Example: if you see "10:00am" or "10:00 Am", flag it and suggest "10:00 AM".
+   - **Date Consistency**: Check for inconsistent date formats (e.g., mixing MM/DD/YYYY and DD.MM.YYYY).
+
+4. **Output Format**:
+Return your findings STRICTLY as a JSON object with this structure:
 {{
-  "total_errors": 0,
+  "total_errors": number,
   "errors": [
     {{
-      "word": "incorrect_word",
-      "context": "...surrounding text...",
-      "suggestions": ["suggestion1", "suggestion2", "suggestion3"],
-      "error_type": "spelling|grammar|typo",
-      "confidence": 0.95
+      "word": "the specific word or phrase with the issue",
+      "context": "a short snippet of the surrounding text (about 5 words before and after)",
+      "suggestions": ["suggestion1", "suggestion2"],
+      "error_type": "spelling" | "grammar" | "formatting",
+      "confidence": 0.0 to 1.0
     }}
   ],
-  "summary": "Brief summary of findings (e.g., 'Found 3 spelling errors' or 'No spelling errors found')"
+  "summary": "a brief 1-2 sentence overview of the issues found"
+}}
+
+If no errors are found, return exactly:
+{{
+  "total_errors": 0,
+  "errors": [],
+  "summary": "No spelling, grammar, or formatting issues found."
 }}
 
 RESPOND WITH JSON ONLY - NO ADDITIONAL TEXT OR MARKDOWN.
@@ -1697,7 +2160,7 @@ RESPOND WITH JSON ONLY - NO ADDITIONAL TEXT OR MARKDOWN.
                 messages=[
                     {
                         "role": "user",
-                        "content": [{"type": "text", "text": SPELL_CHECK_PROMPT}]
+                        "content": [{"type": "text", "text": prompt}]
                     }
                 ]
             )

requirements.txt

@@ -10,3 +10,8 @@ python-dotenv>=1.0.1
 Pillow>=10.0.0
 pytesseract>=0.3.10
 pdf2image>=1.17.0
+aiohttp>=3.9.1
+python-docx>=1.1.2
+python-pptx>=0.6.23
+lxml>=4.9.2
+openpyxl>=3.1.0