Initial Draft

app.py

@@ -172,7 +172,7 @@ def fn_generate_QnA_response(mv_selected_model, mv_user_question, lv_vector_stor
     lv_model = CTransformers(
                                 model="model/mistral-7b-instruct-v0.2.Q2_K.gguf",
                                 model_type=lv_model_type,
-                                max_new_tokens=2048,
+                                max_new_tokens=1024,
                                 temperature=0.00
                             )
     lv_retriever = lv_vector_store.as_retriever(search_kwargs={'k': 2})