Update app.py

app.py

@@ -44,7 +44,7 @@ def retrieve_relevant_doc(query):
 def generate_response(query):
     relevant_doc = retrieve_relevant_doc(query)
     if len(relevant_doc) > 512:  # Truncate long documents
-        relevant_doc = summarizer(relevant_doc, max_length=150, min_length=50, do_sample=False)[0]['summary_text']
+        relevant_doc = summarizer(relevant_doc, max_length=4096, min_length=50, do_sample=False)[0]['summary_text']
     
     input_text = f"Document: {relevant_doc}\n\nQuestion: {query}\n\nAnswer:"
     inputs = llama_tokenizer(input_text, return_tensors="pt").to(device)
@@ -54,7 +54,7 @@ def generate_response(query):
     outputs = llama_model.generate(
         inputs["input_ids"], 
         attention_mask=inputs["attention_mask"], 
-        max_length=150, 
+        max_length=512, 
         pad_token_id=pad_token_id
     )