Update app.py

app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 import fitz  # PyMuPDF
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Function to extract text from PDF
 def extract_text_from_pdf(pdf_file):
@@ -13,11 +13,18 @@ def extract_text_from_pdf(pdf_file):
 
 # Function to generate MCQs using Hugging Face model
 def generate_mcqs(text, num_questions=5):
-    # Define a Hugging Face text generation pipeline
-    text_generation = pipeline("text-generation")
+    # Load HuggingFace model
+    tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2-large")
+    model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2-large")
 
-    # Generate MCQs by providing the text as a prompt
-    mcqs = text_generation(text, max_length=100, num_return_sequences=num_questions)
+    # Tokenize the input text
+    inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True)
+
+    # Generate MCQs by providing the text as input to the model
+    outputs = model.generate(**inputs, max_length=100, num_return_sequences=num_questions, temperature=0.7)
+
+    # Decode the generated sequences
+    mcqs = [tokenizer.decode(output, skip_special_tokens=True) for output in outputs]
 
     return mcqs
 
@@ -37,4 +44,4 @@ if uploaded_file is not None:
 
     st.write("Generated MCQs:")
     for idx, mcq in enumerate(mcqs):
-        st.write(f"{idx+1}. {mcq['generated_text']}")
+        st.write(f"{idx+1}. {mcq}")