Update app.py

app.py

@@ -34,26 +34,82 @@ Link: {row['Link']}\n\n"""
 def get_rag_model():
     return genai.GenerativeModel('gemini-1.5-pro')
 
+# Custom CSS for styling
+def load_css():
+    st.markdown("""
+    <style>
+    .stApp {
+        background: linear-gradient(135deg, #f5f7fa, #c3cfe2);
+    }
+    .stHeader {
+        color: #2c3e50;
+        font-size: 2.5rem;
+        font-weight: bold;
+    }
+    .stForm {
+        background: white;
+        padding: 20px;
+        border-radius: 10px;
+        box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+    }
+    .stButton button {
+        background-color: #3498db;
+        color: white;
+        border-radius: 5px;
+        padding: 10px 20px;
+        font-size: 1rem;
+        border: none;
+    }
+    .stButton button:hover {
+        background-color: #2980b9;
+    }
+    .stMarkdown h3 {
+        color: #2c3e50;
+        margin-top: 20px;
+    }
+    .stExpander {
+        background: white;
+        border-radius: 10px;
+        box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+    }
+    .stDataFrame {
+        border-radius: 10px;
+    }
+    </style>
+    """, unsafe_allow_html=True)
+
 # Streamlit app
 def main():
-    st.title("AI Scholarship Advisor 🎓")
-    
+    # Load custom CSS
+    load_css()
+
+    # Hero Section
+    st.markdown("""
+    <div style="text-align: center; padding: 50px 0;">
+        <h1 style="color: #2c3e50; font-size: 3rem;">🎓 AI Scholarship Advisor</h1>
+        <p style="color: #34495e; font-size: 1.2rem;">Find the best scholarships tailored just for you!</p>
+    </div>
+    """, unsafe_allow_html=True)
+
     # Load data and create RAG context
     df = load_scholarships()
     rag_context = create_rag_context(df)
-    
+
     # User input form
     with st.form("profile_form"):
-        st.header("Student Profile")
-        age = st.number_input("Age", 16, 50, 20)
-        citizenship = st.selectbox("Citizenship", ["India", "Other"])
-        income = st.number_input("Annual Family Income (₹)", 0, 10000000, 300000)
-        education = st.selectbox("Education Level", 
-                               ["High School", "Undergraduate", "Postgraduate", "PhD"])
-        category = st.selectbox("Category", 
-                              ["General", "OBC", "SC", "ST", "EWS", "Minority"])
+        st.markdown("### 📝 Student Profile")
+        col1, col2 = st.columns(2)
+        with col1:
+            age = st.number_input("Age", 16, 50, 20)
+            citizenship = st.selectbox("Citizenship", ["India", "Other"])
+            income = st.number_input("Annual Family Income (₹)", 0, 10000000, 300000)
+        with col2:
+            education = st.selectbox("Education Level", 
+                                   ["High School", "Undergraduate", "Postgraduate", "PhD"])
+            category = st.selectbox("Category", 
+                                  ["General", "OBC", "SC", "ST", "EWS", "Minority"])
         
-        submitted = st.form_submit_button("Get Recommendations")
+        submitted = st.form_submit_button("🚀 Get Recommendations")
 
     if submitted:
         # Create user profile
@@ -65,14 +121,14 @@ def main():
         - Education Level: {education}
         - Category: {category}
         """
-        
+
         # Generate response using RAG
         model = get_rag_model()
         prompt = f"""
         {rag_context}
-        
+
         {user_profile}
-        
+
         Task: 
         1. Analyze the student profile against all scholarships
         2. Identify top 5 most relevant scholarships with priority order
@@ -81,14 +137,14 @@ def main():
            - Explain why it's a good match
            - Provide direct application link
         4. Format response with markdown headers and bullet points
-        
+
         Important: 
         - Be specific about eligibility matches
         - Highlight deadlines if available
         - Never invent scholarships not in the database
         """
-        
-        with st.spinner("Analyzing 50+ scholarships..."):
+
+        with st.spinner("🔍 Analyzing 50+ scholarships..."):
             response = model.generate_content(
                 prompt,
                 generation_config=GenerationConfig(
@@ -97,12 +153,13 @@ def main():
                     max_output_tokens=2000
                 )
             )
-            
-        st.subheader("Personalized Recommendations")
+
+        # Display recommendations
+        st.markdown("### 🎉 Personalized Recommendations")
         st.markdown(response.text)
-        
+
         # Show raw data for transparency
-        with st.expander("View Full Scholarship Database"):
+        with st.expander("📊 View Full Scholarship Database"):
             st.dataframe(df)
 
 if __name__ == "__main__":