Update with new model google/gemma-2-2b-it

app.py

@@ -5,7 +5,7 @@ import torch
 import numpy as np
 
 # this client will handle making requests to the model to generate responses
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("google/gemma-2-2b-it")
 
 # Load and process the knowledge base text file
 with open("knowledge.txt", "r", encoding="utf-8") as f:
@@ -52,11 +52,12 @@ def respond(message, history):
     messages = [{"role": "system",
                  "content": system_message}]
 
-    # add all previous messages to the messages list
     if history:
-        messages.extend(history)
+        for user_msg, assistant_msg in history:
+            messages.append({"role": "user", "content": user_msg})
+            messages.append({"role": "assistant", "content": assistant_msg})
 
-    # add the current user’s message to the messages list
+    # add the current user's message to the messages list
     messages.append({"role": "user", "content": message})
 
     # makes the chat completion API call,