Create app.py

app.py

@@ -0,0 +1,106 @@
+import os
+import streamlit as st
+import pandas as pd
+import requests
+
+# Load the scholarships data
+@st.cache_data
+def load_scholarships_data():
+    return pd.read_csv("scholarships_data.csv")
+
+# Function to filter scholarships based on user input
+def recommend_scholarships(data, user_details):
+    filtered_scholarships = []
+    for _, row in data.iterrows():
+        eligibility = row["Eligibility"].lower()
+        if (
+            (user_details["citizenship"] == "india" and "indian" in eligibility) or
+            (user_details["age"] <= 35 and "below 35" in eligibility) or
+            (user_details["income"] <= 250000 and "₹2,50,000" in eligibility) or
+            (user_details["education_level"] in eligibility) or
+            (user_details["category"] in eligibility)
+        ):
+            filtered_scholarships.append(row)
+    return pd.DataFrame(filtered_scholarships)
+
+# Function to call Gemini API
+def query_gemini(prompt):
+    gemini_api_key = os.getenv("GEMINI_API_KEY")
+    if not gemini_api_key:
+        st.error("Gemini API Key not found in environment variables.")
+        return None
+
+    url = "https://api.gemini.com/v1/query"
+    headers = {
+        "Authorization": f"Bearer {gemini_api_key}",
+        "Content-Type": "application/json",
+    }
+    payload = {"prompt": prompt}
+    response = requests.post(url, headers=headers, json=payload)
+    if response.status_code == 200:
+        return response.json().get("response", "")
+    else:
+        return "Error: Unable to fetch response from Gemini API."
+
+# Streamlit App
+def main():
+    st.title("Scholarship Recommendation System")
+
+    # User Input Form
+    st.header("Student Scholarship Application Form")
+    with st.form("student_form"):
+        st.subheader("Personal Details")
+        citizenship = st.selectbox("Citizenship", ["India", "Other"])
+        age = st.number_input("Age", min_value=1, max_value=100)
+        income = st.number_input("Annual Family Income (in ₹)", min_value=0, max_value=10000000)
+        education_level = st.selectbox(
+            "Education Level",
+            ["Class 10", "Class 12", "Undergraduate", "Postgraduate", "PhD"]
+        )
+        category = st.selectbox(
+            "Category",
+            ["General", "OBC", "SC", "ST", "EWS", "Minority"]
+        )
+
+        submit_button = st.form_submit_button("Find Scholarships")
+
+    # Process form submission
+    if submit_button:
+        # Load scholarships data
+        scholarships_data = load_scholarships_data()
+
+        # Prepare user details
+        user_details = {
+            "citizenship": citizenship.lower(),
+            "age": age,
+            "income": income,
+            "education_level": education_level.lower(),
+            "category": category.lower(),
+        }
+
+        # Filter scholarships
+        recommended_scholarships = recommend_scholarships(scholarships_data, user_details)
+
+        # Display results
+        st.subheader("Recommended Scholarships")
+        if not recommended_scholarships.empty:
+            for _, scholarship in recommended_scholarships.iterrows():
+                st.markdown(f"**{scholarship['Scholarship Name']}**")
+                st.write(f"**Eligibility:** {scholarship['Eligibility']}")
+                st.write(f"**Link:** {scholarship['Link']}")
+                st.write("---")
+        else:
+            st.warning("No scholarships found matching your criteria.")
+
+        # Ask Gemini for additional advice
+        prompt = (
+            f"Provide advice for a {age}-year-old {citizenship} citizen with an annual family income of ₹{income}, "
+            f"pursuing {education_level}, belonging to the {category} category, to find suitable scholarships."
+        )
+        gemini_response = query_gemini(prompt)
+        if gemini_response:
+            st.subheader("Additional Advice from Gemini")
+            st.write(gemini_response)
+
+if __name__ == "__main__":
+    main()