Update app.py

app.py

@@ -2,6 +2,8 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 import edge_tts
 import asyncio
+import requests
+from bs4 import BeautifulSoup
 
 client = InferenceClient("google/gemma-2b-it")
 
@@ -44,15 +46,15 @@ def respond(message, history):
     messages = []
 
     functions_metadata = [
-            {"type": "function", "function": {"name": "web_search", "description": "Search query on google", "parameters": {"type": "object", "properties": {"query": {"type": "string", "description": "web search query"}}, "required": ["query"]}}},
-        ]
+        {"type": "function", "function": {"name": "web_search", "description": "Search query on google", "parameters": {"type": "object", "properties": {"query": {"type": "string", "description": "web search query"}}, "required": ["query"]}}},
+    ]
 
-    system_messages = f'[SYSTEM]You are a helpful assistant, and respond without emoji, You have access to the following functions: \n {str(functions_metadata)}\n\nTo use these functions respond with:\n<functioncall> {{ "name": "function_name", "arguments": {{ "arg_1": "value_1", "arg_1": "value_1", ... }} }}  </functioncall>  [USER] {message_text}'
+    system_messages = f'[SYSTEM]You are a helpful assistant, and respond without emoji, You have access to the following functions: \n {str(functions_metadata)}\n\nTo use these functions respond with:\n<functioncall> {{ "name": "function_name", "arguments": {{ "arg_1": "value_1", "arg_1": "value_1", ... }} }}  </functioncall>  [USER] {message}'
     for val in history:
         if val[0]:
-            messages.append({"role": "user", "content": system_messages})
+            messages.append({"role": "user", "content": val[0]})
         if val[1]:
-            messages.append({"role": "assistant", "content": system_messages})
+            messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
 
@@ -69,23 +71,27 @@ def respond(message, history):
         response += token
         yield response
 
+
 async def tts(response):
     tts = edge_tts.Communicate(response, voice="en-US-JennyNeural")
     await tts.save("output.mp3")
     return "output.mp3"
 
+
 def generate_tts(response):
     return asyncio.run(tts(response))
 
+
 def process(message, history):
     response = list(respond(message, history))[-1]
     tts_file = generate_tts(response)
     history.append((message, response))
     return history, history, tts_file
 
+
 with gr.Blocks() as demo:
     gr.Markdown("<h1><center>gemma-2b-it</center></h1>")
-    
+
     chatbot = gr.Chatbot()
     audio = gr.Audio(label='Your audio output')
 
@@ -93,7 +99,7 @@ with gr.Blocks() as demo:
     submit_button = gr.Button("Submit")
 
     submit_button.click(
-        process, 
+        process,
         inputs=[input_text, chatbot],
         outputs=[chatbot, chatbot, audio]
     )