Update app.py

app.py

@@ -20,14 +20,15 @@ def generate_mcqs(text, num_questions=5):
     if not text.strip():
         return ["No text extracted from the PDF. Unable to generate MCQs."]
 
-    # Tokenize the input text
-    inputs = tokenizer(text, return_tensors="pt", max_length=512, truncation=True)
+    # Truncate text to fit within the model's max token limit
+    max_input_length = 512 - 100  # Reserve space for generated tokens
+    inputs = tokenizer(text, return_tensors="pt", max_length=max_input_length, truncation=True)
 
     mcqs = []
     generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
     for _ in range(num_questions):
         # Generate a single MCQ at a time
-        mcq = generator(text, max_length=512, max_new_tokens=100)[0]["generated_text"]
+        mcq = generator(tokenizer.decode(inputs['input_ids'][0]), max_new_tokens=100)[0]["generated_text"]
         mcqs.append(mcq)
 
     return mcqs