Update app.py

app.py

@@ -1,66 +1,53 @@
 from flask import Flask, request, jsonify
 from flask_cors import CORS
 from transformers import pipeline
-import nltk
+import os
 
-# The SSL and nltk.download sections have been removed.
-# The 'punkt' tokenizer is now pre-installed via the Dockerfile.
-
-# --- Model Loading ---
-# We use a T5 (Transformer) model fine-tuned for Question Generation.
-print("Loading question generation model...")
-# The invalid 'revision' parameter has been removed.
-# The pipeline will now load the latest version of the model.
-question_generator = pipeline("text2text-generation", model="valhalla/t5-base-qg-hl")
+print("Loading End-to-End question generation model...")
+question_generator = pipeline("text2text-generation", model="valhalla/t5-base-e2e-qg")
 print("Model loaded successfully!")
 
-
-# --- Flask App Setup ---
 app = Flask(__name__)
-# Enable Cross-Origin Resource Sharing (CORS) to allow your frontend
-# to communicate with this API.
 CORS(app)
 
-# --- API Endpoint ---
 @app.route('/generate-quiz', methods=['POST'])
 def generate_quiz():
-    """
-    This function handles the API request to generate a quiz.
-    It expects a JSON payload with a 'context' key.
-    """
-    # Get the JSON data from the request
     data = request.get_json()
     if not data or 'context' not in data:
         return jsonify({'error': 'No context provided in the request.'}), 400
 
     context = data['context']
-    
-    # 1. Split the context into individual sentences using the pre-downloaded tokenizer.
-    sentences = nltk.sent_tokenize(context)
-    
-    # We'll limit the number of questions to avoid long processing times.
-    max_questions = 10
-    sentences = sentences[:max_questions]
+    print(f"Generating questions for the provided context...")
 
     generated_questions = []
-    
-    print(f"Generating questions for {len(sentences)} sentences...")
-
-    # 2. Generate a question for each sentence.
-    for sentence in sentences:
-        try:
-            # The model generates a string which might contain multiple questions
-            # separated by <sep>. We take the first one.
-            output = question_generator(sentence, max_length=64, num_beams=4)
-            question = output[0]['generated_text'].split('<sep>')[0].strip()
-            # Basic validation to ensure the question is meaningful
-            if question.endswith('?') and len(question.split()) > 3:
-                 generated_questions.append({'question': question, 'context': sentence})
-        except Exception as e:
-            print(f"Error generating question for sentence: '{sentence}'. Error: {e}")
-
-
-    print(f"Successfully generated {len(generated_questions)} questions.")
-
-    # 3. Return the list of questions as a JSON response.
+    try:
+        output = question_generator(
+            context,
+            max_length=64,
+            num_beams=5,
+            num_return_sequences=5,
+            early_stopping=True
+        )
+
+        question_set = set()
+        for item in output:
+            question_str = item['generated_text']
+            questions = question_str.split('<sep>')
+            for q in questions:
+                clean_q = q.strip()
+                if clean_q.endswith('?') and len(clean_q.split()) > 3:
+                    question_set.add(clean_q)
+
+        generated_questions = [{'question': q, 'context': context} for q in question_set]
+        generated_questions = generated_questions[:10]
+
+    except Exception as e:
+        print(f"Error generating questions: {e}")
+        return jsonify({'error': 'Failed to generate quiz.'}), 500
+
+    print(f"Successfully generated {len(generated_questions)} unique questions.")
     return jsonify({'quiz': generated_questions})
+
+if __name__ == '__main__':
+    port = int(os.environ.get("PORT", 5000))
+    app.run(host='0.0.0.0', port=port)