Update app.py

app.py

@@ -19,7 +19,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 # Constants / Globals
 # ==========================
 
-#NVIDIA_API_KEY    = os.environ["API_KEY"]                             # API Key for the LLM - Using NVIDIA's NIM to access an 8 Billion parameter Llama3 model
+API_KEY    = os.environ["API_KEY"]                                    # API Key for the LLM - Using NVIDIA's NIM to access an 8 Billion parameter Llama3 model
 
 CHATBOT_HEIGHT    = 500                                               # Height of Gradio Chatbot
 IMAGE_HEIGHT      = 500
@@ -36,12 +36,10 @@ game              = cMystery()                                        # New myst
 # Using NVIDIA's NIM (NVIDIA Inference Microservices) to access an 8 Billion parameter Llama3 model
 
 #llm = ChatOpenAI(model    = "meta/llama3-8b-instruct",temperature=0.5,max_tokens=1024,timeout=None,max_retries=2,
-#                 base_url = "https://integrate.api.nvidia.com/v1",
-#                 api_key  = NVIDIA_API_KEY)
+                 #base_url = "https://integrate.api.nvidia.com/v1",
+                 #api_key  = NVIDIA_API_KEY)
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
-model     = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
-llm       = ChatOpenAI(model= model)
+llm = ChatOpenAI(model = "gpt-4o",temperature=1.0,max_tokens=1024,timeout=None,max_retries=2,api_key=API_KEY)
 
 # ================================
 # Custom LangChain Tools and Pipes