Update app.py

app.py

@@ -74,9 +74,22 @@ callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 
 # Function to create a conversational chain
 def create_conversational_chain(database):
+    model_name = “llama-7b-hf”
+    model_directory = “models”
+    #Check if the model file exists in the specified directory
+    model_file = os.path.join(model_directory, model_name)
+    if os.path.exists(model_file):
+        model_path = model_file
+        print(“Model file found in the directory. Using the local model file.”)
+    else:
+        model_path = model_name
+        print(“Model file not found in the directory. Downloading the model from the repository.”)
+    #Load the model
+    model = AutoModelForCausalLM.from_pretrained(model_path)
+    print(model_path)
     llama_llm = LlamaCpp(
         # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llama-2-7b-chat.Q8_0.gguf
-        model_path = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7b-Chat-GGUF", model_file="llama-2-7b-chat.Q8_0.gguf", model_type="llama", gpu_layers=0),
+        model_path = model_path,
         temperature=0.75,
         max_tokens=200,
         top_p=1,