Update app.py

app.py

@@ -2,9 +2,11 @@ from openai import OpenAI, RateLimitError
 import streamlit as st
 import time
 import os
+import re
 from typing import Dict, Optional
+from datetime import datetime
 
-# Page configuration
+# Page configuration (moved to top to ensure it's called only once)
 st.set_page_config(
     page_title="LinkedIn Recommendation Generator",
     page_icon="👔",
@@ -12,7 +14,132 @@ st.set_page_config(
     initial_sidebar_state="collapsed"
 )
 
-# Custom CSS for professional styling
+# Authentication functions
+def is_valid_email(email: str) -> bool:
+    """Validate email format"""
+    pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
+    return re.match(pattern, email) is not None
+
+def check_access(email: str) -> tuple[bool, str]:
+    """Check if user has access"""
+    email = email.strip().lower()
+    
+    if not is_valid_email(email):
+        return False, "Please enter a valid email address."
+    
+    # Get authorized emails from environment variables
+    paid_customers = os.getenv("PAID_CUSTOMERS", "").split(",")
+    paid_customers = [e.strip().lower() for e in paid_customers if e.strip()]
+    admin_email = os.getenv("ADMIN_EMAIL", "").lower()
+    
+    if email in paid_customers or email == admin_email:
+        return True, f"✅ Access granted! Welcome to the LinkedIn Recommendation Generator."
+    else:
+        return False, f"❌ Access denied. Your email is not authorized to use this system."
+
+def render_login_page():
+    """Render the authentication page"""
+    # Login page CSS
+    st.markdown("""
+    <style>
+        @import url('https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@300;400;600;700&display=swap');
+        
+        .login-container {
+            max-width: 500px;
+            margin: 100px auto;
+            padding: 3rem;
+            background: white;
+            border-radius: 20px;
+            box-shadow: 0 8px 32px rgba(0,0,0,0.1);
+            text-align: center;
+        }
+        
+        .login-header {
+            font-family: 'Source Sans Pro', sans-serif;
+            font-size: 2.5rem;
+            font-weight: 700;
+            color: #0077B5;
+            margin-bottom: 0.5rem;
+        }
+        
+        .login-subtitle {
+            font-family: 'Source Sans Pro', sans-serif;
+            font-size: 1.2rem;
+            color: #666;
+            margin-bottom: 2rem;
+        }
+        
+        .linkedin-logo {
+            width: 60px;
+            height: 60px;
+            background: linear-gradient(135deg, #0077B5 0%, #005885 100%);
+            border-radius: 15px;
+            display: inline-flex;
+            align-items: center;
+            justify-content: center;
+            margin-bottom: 1rem;
+            box-shadow: 0 4px 15px rgba(0,119,181,0.3);
+        }
+        
+        .stButton > button {
+            background: linear-gradient(135deg, #0077B5 0%, #005885 100%);
+            color: white;
+            border: none;
+            padding: 0.8rem 2rem;
+            border-radius: 25px;
+            font-weight: 600;
+            font-family: 'Source Sans Pro', sans-serif;
+            font-size: 1rem;
+            width: 100%;
+            margin-top: 1rem;
+        }
+        
+        .stTextInput > div > div > input {
+            background: #f8f9ff;
+            border: 1px solid #e8f4f8;
+            border-radius: 12px;
+            font-family: 'Source Sans Pro', sans-serif;
+            padding: 12px 16px;
+        }
+    </style>
+    """, unsafe_allow_html=True)
+    
+    st.markdown("""
+    <div class="login-container">
+        <div class="linkedin-logo">
+            <svg width="35" height="35" viewBox="0 0 24 24" fill="white">
+                <path d="M20.447 20.452h-3.554v-5.569c0-1.328-.027-3.037-1.852-3.037-1.853 0-2.136 1.445-2.136 2.939v5.667H9.351V9h3.414v1.561h.046c.477-.9 1.637-1.85 3.37-1.85 3.601 0 4.267 2.37 4.267 5.455v6.286zM5.337 7.433c-1.144 0-2.063-.926-2.063-2.065 0-1.138.92-2.063 2.063-2.063 1.14 0 2.064.925 2.064 2.063 0 1.139-.925 2.065-2.064 2.065zm1.782 13.019H3.555V9h3.564v11.452zM22.225 0H1.771C.792 0 0 .774 0 1.729v20.542C0 23.227.792 24 1.771 24h20.451C23.2 24 24 23.227 24 22.271V1.729C24 .774 23.2 0 22.222 0h.003z"/>
+            </svg>
+        </div>
+        <h1 class="login-header">🔐 Access Portal</h1>
+        <p class="login-subtitle">Enter your registered email to access the LinkedIn Recommendation Generator</p>
+    </div>
+    """, unsafe_allow_html=True)
+    
+    with st.form("login_form"):
+        email_input = st.text_input(
+            "📧 Email Address",
+            placeholder="Enter your registered email..."
+        )
+        login_button = st.form_submit_button("🚀 Access System")
+    
+    if login_button:
+        if email_input:
+            success, message = check_access(email_input)
+            if success:
+                timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+                print(f"[{timestamp}] Access granted to: {email_input}")
+                st.session_state.authenticated = True
+                st.session_state.user_email = email_input.strip().lower()
+                st.success(message)
+                time.sleep(1)
+                st.rerun()
+            else:
+                st.error(message)
+        else:
+            st.error("Please enter your email address.")
+
+# Original app CSS
 st.markdown("""
 <style>
     /* Import LinkedIn-style font */
@@ -246,6 +373,19 @@ st.markdown("""
     .form-field-container {
         padding: 0.5rem 0;
     }
+    
+    .user-info {
+        background: linear-gradient(135deg, #0077B5 0%, #005885 100%);
+        color: white;
+        padding: 10px;
+        border-radius: 5px;
+        margin-bottom: 20px;
+        text-align: center;
+    }
+    
+    .logout-btn {
+        background: #dc3545 !important;
+    }
 </style>
 """, unsafe_allow_html=True)
 
@@ -262,7 +402,6 @@ def create_star_rating(label, key, help_text=None):
         
         with col2:
             pass
-
         rating = st.select_slider(
             "",
             options=[1, 2, 3, 4, 5],
@@ -271,15 +410,13 @@ def create_star_rating(label, key, help_text=None):
             label_visibility="collapsed"
         )
     
-    # Create visual stars
     stars = "".join(["⭐" if i < rating else "☆" for i in range(5)])
     st.markdown(f"<div style='font-size: 1.5rem; text-align: center; margin-top: -35px;'>{stars}</div>", unsafe_allow_html=True)
     return rating
 
-def generate_recommendation(employee_name, employee_type, relationship, time_worked, linkedin_url, ratings):
-    """Generate recommendation using a simple template-based approach"""
+def generate_recommendation(ratings: Dict[str, int], employee_type: str, employee_name: str, relationship: str, time_worked: str, linkedin_url: str) -> Optional[str]:
+    """Generate recommendation using OpenRouter API with input summary"""
     
-    # Organize ratings into categories for analysis
     performance_areas = {
         "Technical Competence": {
             "Domain Knowledge": ratings['domain'],
@@ -301,39 +438,90 @@ def generate_recommendation(employee_name, employee_type, relationship, time_wor
         }
     }
     
-    # Calculate category averages
     category_scores = {}
     for category, metrics in performance_areas.items():
         category_scores[category] = sum(metrics.values()) / len(metrics)
     
-    # Identify top strengths (ratings of 4 or 5)
-    strengths = [k.replace('_', ' ').title() for k, v in ratings.items() if v >= 4]
-    
-    # Generate a simple template-based recommendation
-    avg_rating = sum(ratings.values()) / len(ratings)
-    
-    if avg_rating >= 4.5:
-        performance_descriptor = "exceptional"
-        impact_descriptor = "consistently exceeded expectations"
-    elif avg_rating >= 4.0:
-        performance_descriptor = "outstanding"
-        impact_descriptor = "consistently delivered excellent results"
-    elif avg_rating >= 3.5:
-        performance_descriptor = "strong"
-        impact_descriptor = "consistently met and often exceeded expectations"
-    else:
-        performance_descriptor = "solid"
-        impact_descriptor = "demonstrated reliable performance"
-    
-    recommendation = f"""I had the pleasure of working with {employee_name} as their {relationship.lower()} for {time_worked.lower()}. During this time, {employee_name} served as a {employee_type} and {impact_descriptor}.
-
-{employee_name} demonstrated {performance_descriptor} performance across multiple areas. Their key strengths include {', '.join(strengths[:3]) if strengths else 'dedication and professionalism'}. What impressed me most was their ability to tackle complex challenges with creativity and persistence.
-
-{employee_name} was not only technically competent but also a valuable team player who contributed positively to our work environment. Their communication skills and collaborative approach made them a pleasure to work with.
-
-I would highly recommend {employee_name} for any role that values {performance_descriptor} performance and team collaboration. They would be a valuable addition to any organization."""
-
-    return recommendation
+    strengths = [k for k, v in ratings.items() if v >= 4]
+    
+    analysis_text = ""
+    for category, score in category_scores.items():
+        analysis_text += f"\n- {category}: {score:.1f}/5"
+    
+    recommendation_prompt = f"""
+    You are an expert in writing professional LinkedIn recommendations.
+    Your task is to generate a recommendation for {employee_name}.
+    First, silently analyze the provided performance data. Do not output this analysis.
+    - Employee: {employee_name}
+    - Role: {employee_type}
+    - My Relationship to them: {relationship}
+    - Duration we worked together: {time_worked}
+    - Performance Summary by Category:{analysis_text}
+    - Employee's LinkedIn Profile (for context, do not mention the URL in the output): {linkedin_url or 'Not provided'}
+    - Key Strengths (rated 4 or 5): {', '.join(strengths) if strengths else 'None specified'}
+    
+    Now, using that analysis, write a detailed and comprehensive LinkedIn recommendation of 200-250 words. The recommendation must:
+    - Be complete, with no abrupt endings or incomplete sentences.
+    - Be professional, warm, and authentic in tone.
+    - Be free of grammatical errors, spelling mistakes, or awkward phrasing.
+    - End with a strong, forward-looking statement about the employee's potential.
+    
+    Instructions for the recommendation:
+    1. Start by clearly stating the working relationship ({relationship}) and the duration ({time_worked}).
+    2. Highlight their role as a {employee_type} and their key responsibilities.
+    3. Weave their key strengths ({', '.join(strengths) if strengths else 'None specified'}) into a brief narrative or specific example that illustrates their positive impact (e.g., how their 'Problem Solving' skills unblocked a project or how their 'Team Collaboration' improved team morale).
+    4. Conclude with a clear, confident statement about their future potential and value to any organization.
+    5. Use vivid, descriptive language to make the recommendation personal and human.
+    6. Ensure the recommendation is a complete text, ending with a full sentence and a period, and meets the 200-250 word requirement.
+    """
+    
+    try:
+        client_kwargs = {
+            "base_url": "https://openrouter.ai/api/v1",
+            "api_key": os.environ.get('OPENROUTER_API_KEY')
+        }
+        
+        try:
+            client = OpenAI(**client_kwargs)
+        except TypeError as e:
+            if "proxies" in str(e) or "unexpected keyword argument" in str(e):
+                import openai
+                openai.api_key = os.environ.get('OPENROUTER_API_KEY')
+                openai.base_url = "https://openrouter.ai/api/v1"
+                client = openai
+            else:
+                raise e
+        
+        try:
+            final_response = client.chat.completions.create(
+                model="openai/gpt-3.5-turbo",
+                messages=[
+                    {"role": "system", "content": "You are an expert in writing professional, warm, and authentic LinkedIn recommendations. Ensure the output is complete, polished, and free of errors."},
+                    {"role": "user", "content": recommendation_prompt}
+                ],
+                max_tokens=400,  # Increased to accommodate 200-250 words
+                temperature=0.75
+            )
+            return final_response.choices[0].message.content.strip()
+        except AttributeError:
+            final_response = client.ChatCompletion.create(
+                model="openai/gpt-3.5-turbo",
+                messages=[
+                    {"role": "system", "content": "You are an expert in writing professional, warm, and authentic LinkedIn recommendations. Ensure the output is complete, polished, and free of errors."},
+                    {"role": "user", "content": recommendation_prompt}
+                ],
+                max_tokens=400,  # Increased to accommodate 200-250 words
+                temperature=0.75
+            )
+            return final_response['choices'][0]['message']['content'].strip()
+            
+    except RateLimitError:
+        st.error("API rate limit or quota exceeded. Please check your OpenRouter account and billing details.")
+        return None
+    except Exception as e:
+        st.error(f"An error occurred while generating the recommendation: {str(e)}")
+        st.error(f"Error details: {type(e).__name__}")
+        return None
 
 def render_header():
     """Renders the main header of the application."""
@@ -368,8 +556,8 @@ def render_input_form() -> Dict:
     with col2:
         employee_type = st.selectbox(
             "Employee Role/Department",
-            ["", "Software Developer", "AI Engineer", "Marketing Specialist", "Sales Representative", 
-             "Project Manager", "Data Analyst", "UI/UX Designer", "Customer Support", "Business Analyst", 
+            ["", "Software Developer", "AI Engineer", "Marketing Specialist", "Sales Representative",
+             "Project Manager", "Data Analyst", "UI/UX Designer", "Customer Support", "Business Analyst",
              "Product Manager", "DevOps Engineer", "Content Creator", "HR Specialist", "Other"],
             key="employee_type"
         )
@@ -378,7 +566,7 @@ def render_input_form() -> Dict:
             ["", "Less than 6 months", "6 months - 1 year", "1-2 years", "2-3 years", "3-5 years", "More than 5 years"],
             key="time_worked"
         )
-
+    
     linkedin_url = st.text_input(
         "Enter LinkedIn Profile URL",
         key="linkedin_url",
@@ -391,49 +579,49 @@ def render_input_form() -> Dict:
     ratings = {}
     st.markdown("<div class='sub-section-header'>Core Competencies</div>", unsafe_allow_html=True)
     ratings['domain'] = create_star_rating(
-        "How would you rate the employee's knowledge and expertise in their specific field or role?", 
+        "How would you rate the employee's knowledge and expertise in their specific field or role?",
         "domain"
     )
     ratings['problem_solving'] = create_star_rating(
-        "How effectively does the employee address challenges and find solutions?", 
+        "How effectively does the employee address challenges and find solutions?",
         "problem_solving"
     )
     ratings['initiative'] = create_star_rating(
-        "How proactive is the employee in taking initiative and contributing to company objectives?", 
+        "How proactive is the employee in taking initiative and contributing to company objectives?",
         "initiative"
     )
-
+    
     st.markdown("<div class='sub-section-header'>Professional Skills</div>", unsafe_allow_html=True)
     ratings['adaptability'] = create_star_rating(
-        "How well does the employee handle change or take on new responsibilities?", 
+        "How well does the employee handle change or take on new responsibilities?",
         "adaptability"
     )
     ratings['communication'] = create_star_rating(
-        "How clearly and professionally does the employee communicate ideas or information?", 
+        "How clearly and professionally does the employee communicate ideas or information?",
         "communication"
     )
-
+    
     st.markdown("<div class='sub-section-header'>Interpersonal Skills</div>", unsafe_allow_html=True)
     ratings['teamwork'] = create_star_rating(
-        "How well does the employee work with colleagues or teams to achieve goals?", 
+        "How well does the employee work with colleagues or teams to achieve goals?",
         "teamwork"
     )
     ratings['support'] = create_star_rating(
-        "How well does the employee support or guide others in the work environment?", 
+        "How well does the employee support or guide others in the work environment?",
         "support"
     )
-
+    
     st.markdown("<div class='sub-section-header'>Performance & Potential</div>", unsafe_allow_html=True)
     ratings['reliability'] = create_star_rating(
-        "How consistently does the employee demonstrate dedication and reliability?", 
+        "How consistently does the employee demonstrate dedication and reliability?",
         "reliability"
     )
     ratings['overall'] = create_star_rating(
-        "How would you rate the employee's overall contribution to their role and the team?", 
+        "How would you rate the employee's overall contribution to their role and the team?",
         "overall"
     )
     ratings['potential'] = create_star_rating(
-        "How would you rate the employee's potential for further growth or advancement within the organization?", 
+        "How would you rate the employee's potential for further growth or advancement within the organization?",
         "potential"
     )
     
@@ -458,7 +646,6 @@ def render_results_section(ratings: Dict[str, int]):
         </div>
         """, unsafe_allow_html=True)
         
-        # Action buttons
         col1, col2 = st.columns(2)
         with col1:
             if st.button("📋 Show Text for Copying"):
@@ -470,7 +657,13 @@ def render_results_section(ratings: Dict[str, int]):
                 st.session_state.recommendation_generated = False
                 st.rerun()
         
-        # Instructions
+        if st.session_state.saved_linkedin_url:
+            st.markdown(f"""
+            <div style="background: linear-gradient(135deg, #0077B5 0%, #005885 100%); color: white; padding: 8px; border-radius: 5px; margin: 1rem 0; text-align: center; font-family: 'Source Sans Pro', sans-serif; font-size: 1rem;">
+                Click on the Employee's LinkedIn Profile: <a href="{st.session_state.saved_linkedin_url}" target="_blank" style="color: #ffffff; text-decoration: none;">{st.session_state.saved_linkedin_url}</a>
+            </div>
+            """, unsafe_allow_html=True)
+        
         st.markdown("""
         <div class="result-container">
             <h4 style="color: white; margin-bottom: 1rem;">📖 How to Post on LinkedIn</h4>
@@ -483,8 +676,7 @@ def render_results_section(ratings: Dict[str, int]):
             </ol>
         </div>
         """, unsafe_allow_html=True)
-
-        # Analytics section
+        
         st.markdown('<h4 style="color: #0077B5;">📊 Rating Summary</h4>', unsafe_allow_html=True)
         
         col1, col2, col3, col4 = st.columns(4)
@@ -504,24 +696,65 @@ def render_results_section(ratings: Dict[str, int]):
 
 def main():
     """Main function to run the Streamlit application."""
-    # Skip all authentication - go directly to the app
+    # Initialize session state for authentication
+    if 'authenticated' not in st.session_state:
+        st.session_state.authenticated = False
+    if 'user_email' not in st.session_state:
+        st.session_state.user_email = ""
+    
+    # If not authenticated, show login page
+    if not st.session_state.authenticated:
+        render_login_page()
+        return
+    
+    # If authenticated, show user info and logout button
+    col1, col2 = st.columns([4, 1])
+    with col1:
+        st.markdown(f"""
+        <div class="user-info">
+            👤 Logged in as: <strong>{st.session_state.user_email}</strong>
+        </div>
+        """, unsafe_allow_html=True)
+    
+    with col2:
+        if st.button("🚪 Logout", key="logout_btn", help="Click to log out"):
+            st.session_state.authenticated = False
+            st.session_state.user_email = ""
+            st.session_state.recommendation_generated = False
+            st.session_state.generated_text = ""
+            st.session_state.saved_linkedin_url = ""
+            st.rerun()
+    
+    # Original main function logic
+    api_key = os.environ.get('OPENROUTER_API_KEY')
+    
+    if not api_key:
+        try:
+            if hasattr(st, 'secrets') and 'OPENROUTER_API_KEY' in st.secrets:
+                api_key = st.secrets['OPENROUTER_API_KEY']
+                os.environ['OPENROUTER_API_KEY'] = api_key
+        except Exception:
+            pass
+    
+    if not api_key:
+        st.error("🔑 OpenRouter API key not found. Please add it to your Hugging Face Space secrets in the 'Settings' tab.")
+        st.info("Debug: Check that your OPENROUTER_API_KEY is properly set in the Hugging Face Space settings under 'Repository secrets'.")
+        st.stop()
+    
     render_header()
-
-    # Initialize session state
+    
     if 'recommendation_generated' not in st.session_state:
         st.session_state.recommendation_generated = False
     if 'generated_text' not in st.session_state:
         st.session_state.generated_text = ""
     if 'saved_linkedin_url' not in st.session_state:
         st.session_state.saved_linkedin_url = ""
-
+    
     form_data = render_input_form()
     
-    # Generate recommendation button
     col1, col2, col3 = st.columns([1, 2, 1])
     with col2:
         if st.button("🚀 Generate LinkedIn Recommendation", type="primary"):
-            # Validate required fields
             required_fields = ["employee_name", "employee_type", "relationship", "time_worked"]
             if not all(form_data[field] for field in required_fields):
                 st.error("Please fill in all required fields in the 'Basic Information' section.")
@@ -533,18 +766,28 @@ def main():
                     
                     recommendation = generate_recommendation(**form_data)
                     
-                    progress_bar.progress(100, text="Done!")
-                    time.sleep(0.5)
-                    progress_bar.empty()
-                
-                if recommendation:
-                    st.session_state.recommendation_generated = True
-                    st.session_state.generated_text = recommendation
-                    st.session_state.saved_linkedin_url = form_data["linkedin_url"]
-                    st.success("✅ Recommendation generated successfully!")
-                    st.rerun()
-
-    # Display results in a separate container
+                    # Validate recommendation
+                    if recommendation:
+                        word_count = len(recommendation.split())
+                        # Check if recommendation is within 150-300 words and ends with a period
+                        if word_count < 150 or not recommendation.strip().endswith('.'):
+                            st.error("The generated recommendation is incomplete or too short. Please try again.")
+                            st.session_state.recommendation_generated = False
+                            progress_bar.empty()
+                            time.sleep(0.5)
+                            st.rerun()
+                        else:
+                            st.session_state.recommendation_generated = True
+                            st.session_state.generated_text = recommendation
+                            st.session_state.saved_linkedin_url = form_data["linkedin_url"]
+                            st.success("✅ Recommendation generated successfully!")
+                            progress_bar.progress(100, text="Done!")
+                            time.sleep(0.5)
+                            progress_bar.empty()
+                            st.rerun()
+                    else:
+                        progress_bar.empty()
+    
     render_results_section(form_data["ratings"])
 
 if __name__ == "__main__":