Update app.py

app.py

@@ -55,11 +55,11 @@ def search(query):
 client_gemma = InferenceClient("google/gemma-1.1-7b-it")
 client_mixtral = InferenceClient("NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO")
 client_llama = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
+messages = []
 
 # Define the main chat function
 def respond(message, history):
     global messages # Make messages global for persistent storage 
-    messages = [] # Initialize messages list (this gets overwritten each turn)
     vqa = ""
 
     # Handle image processing
@@ -98,6 +98,8 @@ def respond(message, history):
     response = response.replace('\\"', '"')
     print(f"\n{response}")
 
+    messages.append({"role": "assistant", "content": f"<functioncall>{str(response)}</functioncall>"})
+
     # Process and return the response based on the function call
     try:
         json_data = json.loads(str(response))