Update app.py

app.py

@@ -35,8 +35,45 @@ from xml.etree import ElementTree as ET
 
 # 0 - Load USMLE dataset with answers:
 from datasets import load_dataset
+
+# 📚 Load USMLE Step 1 dataset
 dataset = load_dataset("augtoma/usmle_step_1")
 
+# 🎉 Streamlit App 🎉
+st.title("USMLE Step 1 Dataset Viewer")
+st.write("""
+🔍 Use the search box to filter questions or use the grid to scroll through the dataset.
+""")
+
+# 👩‍🔬 Search Box
+search_term = st.text_input("Search for a specific question:", "")
+
+# 🎛 Pagination
+records_per_page = 100
+num_records = len(dataset['train'])
+num_pages = int(num_records / records_per_page) + 1
+page_number = st.select_slider("Select page:", options=list(range(1, num_pages + 1)))
+
+# 📊 Display Data
+start_idx = (page_number - 1) * records_per_page
+end_idx = start_idx + records_per_page
+
+# 🧪 Apply the Search Filter
+if search_term:
+    filtered_data = [record for record in dataset['train'][start_idx:end_idx] if search_term.lower() in record['text'].lower()]
+else:
+    filtered_data = dataset['train'][start_idx:end_idx]
+
+# 🌐 Render the Grid
+for record in filtered_data:
+    st.write(f"## Question ID: {record['id']}")
+    st.write(f"### Question:")
+    st.write(f"{record['text']}")
+    st.write(f"### Answer:")
+    st.write(f"{record['answer']}")
+    st.write("---")
+
+st.write(f"😊 Total Records: {num_records} | 📄 Displaying {start_idx+1} to {min(end_idx, num_records)}")
 
 # 1. Constants and Top Level UI Variables