Update app.py

app.py

@@ -1,21 +1,10 @@
-# Install dependencies (only needed once)
-!pip install gradio pandas scikit-learn
-
-# Imports
 import pandas as pd
 import gradio as gr
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 
-# Load dataset
-df = pd.read_csv("mcq_dataset.csv")
-
-# Normalize text to avoid case/whitespace mismatches
-df['domain'] = df['domain'].str.strip().str.lower()
-df['subdomain'] = df['subdomain'].str.strip()
-
 # Core logic to retrieve top MCQs
-def get_top_mcqs(user_input, domain, subdomain, top_n=10):
+def get_top_mcqs(user_input, domain, subdomain, df, top_n=10):
     domain = domain.strip().lower()
     subdomain = subdomain.strip()
 
@@ -39,8 +28,8 @@ def get_top_mcqs(user_input, domain, subdomain, top_n=10):
     return top_questions.reset_index(drop=True)
 
 # Quiz generation logic
-def run_quiz(domain, subdomain, keyword_input):
-    mcq_df = get_top_mcqs(keyword_input, domain, subdomain)
+def run_quiz(domain, subdomain, keyword_input, df):
+    mcq_df = get_top_mcqs(keyword_input, domain, subdomain, df)
     
     if mcq_df.empty:
         return "⚠️ No questions found for the selected domain/subdomain."
@@ -57,26 +46,47 @@ def run_quiz(domain, subdomain, keyword_input):
     return quiz_output
 
 # Dynamic subdomain update
-def update_subdomains(domain):
+def update_subdomains(domain, df):
     domain = domain.strip().lower()
     subdomains = df[df["domain"] == domain]["subdomain"].dropna().unique().tolist()
     return gr.Dropdown.update(choices=sorted(subdomains), value=None)
 
 # Gradio UI
-with gr.Blocks() as demo:
-    gr.Markdown("## 🧠 Domain-Based MCQ Quiz System")
+def launch_interface():
+    with gr.Blocks() as demo:
+        gr.Markdown("## 🧠 Domain-Based MCQ Quiz System")
+
+        with gr.Row():
+            domain_dropdown = gr.Dropdown(label="Select Domain", choices=[])
+            subdomain_dropdown = gr.Dropdown(label="Select Subdomain", choices=[])
+
+        file_upload = gr.File(label="Upload MCQ Dataset (CSV)", type="file")
+
+        # Update domain list when file is uploaded
+        def load_and_update(file):
+            if file is not None:
+                df = pd.read_csv(file.name)
+                # Normalize text to avoid case/whitespace mismatches
+                df['domain'] = df['domain'].str.strip().str.lower()
+                df['subdomain'] = df['subdomain'].str.strip()
+                
+                domains = sorted(df['domain'].unique().tolist())
+                domain_dropdown.update(choices=domains)
+
+                return df
+            return None
+
+        file_upload.change(fn=load_and_update, inputs=file_upload, outputs=None)
 
-    with gr.Row():
-        domain_dropdown = gr.Dropdown(label="Select Domain", choices=sorted(df['domain'].unique().tolist()))
-        subdomain_dropdown = gr.Dropdown(label="Select Subdomain", choices=[])
+        domain_dropdown.change(fn=update_subdomains, inputs=domain_dropdown, outputs=subdomain_dropdown)
 
-    domain_dropdown.change(fn=update_subdomains, inputs=domain_dropdown, outputs=subdomain_dropdown)
+        keyword_input = gr.Textbox(label="Enter keywords or topic")
+        quiz_button = gr.Button("Get Top MCQs")
+        quiz_output = gr.Textbox(label="Quiz Questions", lines=20)
 
-    keyword_input = gr.Textbox(label="Enter keywords or topic")
-    quiz_button = gr.Button("Get Top MCQs")
-    quiz_output = gr.Textbox(label="Quiz Questions", lines=20)
+        quiz_button.click(fn=run_quiz, inputs=[domain_dropdown, subdomain_dropdown, keyword_input, file_upload], outputs=quiz_output)
 
-    quiz_button.click(fn=run_quiz, inputs=[domain_dropdown, subdomain_dropdown, keyword_input], outputs=quiz_output)
+    demo.launch()
 
-# Launch interface
-demo.launch()
+# Run the interface
+launch_interface()