Fix tokens

app.py

@@ -46,7 +46,7 @@ def chat(query):
     context = "\n".join([docs[i] for i in I[0]])
     prompt = f"Context: {context}\nQuestion: {query}\nAnswer:"
     
-    response = qa_pipeline(prompt, max_length=100, do_sample=False)
+    response = qa_pipeline(prompt, max_new_tokens=100, do_sample=False)
     return response[0]['generated_text'].split("Answer:")[-1].strip()
 
 # Gradio UI