Update app.py

app.py

@@ -38,7 +38,10 @@ def load_documents(docs_path):
             documents.append(text)
     return documents
 
+print ("loading documents")
 documents = load_documents(docs_path)
+print ("done loading documents")
+
 
 # Load model and tokenizer for encoding documents
 tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
@@ -51,15 +54,23 @@ def encode_documents(documents):
     embeddings = outputs.last_hidden_state.mean(dim=1).detach().numpy()
     return embeddings
 
+print ("encoding documents")
 embeddings = encode_documents(documents)
+print ("done encoding documents")
+
 
+print ("vector faiss documents")
 # Index embeddings using FAISS
 index = faiss.IndexFlatL2(embeddings.shape[1])
 index.add(embeddings)
+print ("done vector documents")
 
+print ("start tokenizing documents")
 # Load T5 model and tokenizer for question generation
 t5_tokenizer = T5Tokenizer.from_pretrained("t5-small")
 t5_model = T5ForConditionalGeneration.from_pretrained("t5-small")
+print ("done tokenizing documents")
+
 
 def generate_questions(text):
     input_text = f"generate question: {text}"
@@ -73,9 +84,11 @@ def retrieve_documents(query, index, documents):
     D, I = index.search(query_embedding, k=5)
     return [documents[i] for i in I[0]]
 
+print ("loading gpt-2")
 # Load GPT-2 model and tokenizer for answer generation
 gpt2_tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
 gpt2_model = GPT2LMHeadModel.from_pretrained("gpt2")
+print ("done gpt-2")
 
 def generate_answer(question, context):
     input_text = f"Question: {question}\nContext: {context}\nAnswer:"