Update app.py

app.py

@@ -2,43 +2,32 @@ from huggingface_hub import InferenceClient
 import gradio as gr
 import random
 
-client = InferenceClient("google/gemma-3-27b-it")
-#this is where you change the LLM
+# Initialize the inference client
+client = InferenceClient("google/gemma-1.1-7b-it")  # Replace with a smaller model if needed
 
-def respond(message,history):
-   # with gr.Blocks() as demo:
-     #   gr.Markdown("# Simple Q&A Chatbot")
-
-       # question = gr.Textbox(label="Your Question", placeholder="Type your question here...")
-       # answer = gr.Textbox(label="Chatbot Answer", interactive=False)
-
-   # question.submit(fn=chatbot_response, inputs=question, outputs=answer)
-
-   messages = [{"role": "system", "content": "You are a mean chatbot."}]
-   
-if history:
-    messages.extend(history)
+# Define the response function
+def respond(message, history):
+    messages = [{"role": "system", "content": "You are a mean chatbot."}]
     
-    message.append({"role": "user", "content": message})
+    # Convert history to OpenAI-style messages
+    if history:
+        for user_msg, bot_msg in history:
+            messages.append({"role": "user", "content": user_msg})
+            messages.append({"role": "assistant", "content": bot_msg})
+    
+    messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(messages,max_tokens=50, stream=True):
-        token = message.choices[0].delta.content
-        response += token
-        yield response
-                                                                   
-    #temperature=.9,
-    #top_p=.7) #changes the length of message
-
-def echo(message, history):
-    choices = ["so true", "shut up", "you need help", "ts pmo sybau"] #change personality
-    #use random to select choices
-    chat_answer = random.choice(choices)
-    return chat_answer
-
-chatbot = gr.ChatInterface(respond, type = "messages")
-
-chatbot.launch()
-
-chatbot.launch(debug=True)
+    
+    # Call the model with streaming response
+    for chunk in client.chat_completion(messages, max_tokens=100, stream=True):
+        if chunk.choices and chunk.choices[0].delta:
+            token = chunk.choices[0].delta.get("content", "")
+            response += token
+            yield response
+
+# Set up the Gradio chat interface
+chatbot = gr.ChatInterface(fn=respond, chatbot=gr.Chatbot(), title="Mean Chatbot")
+
+# Launch the chatbot
+chatbot.launch(debug=True)