Update app.py

app.py

@@ -7,115 +7,58 @@ For more information on `huggingface_hub` Inference API support, please check th
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-# suppress warnings
-import warnings
-warnings.filterwarnings("ignore")
-
-# import libraries
-from dotenv import load_dotenv
-import os
-import gradio as gr
-from together import Together
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
-# Load environment variables from .env file
-load_dotenv("/Users/ay/Documents/projects/Agentic AI hackathon/.env")
-
-# Get the API key from environment variables
-TOGETHER_API_KEY = os.getenv("TOGETHER_API_KEY")
-if not TOGETHER_API_KEY:
-    raise ValueError("TOGETHER_API_KEY is not set in the .env file at /Users/ay/Documents/projects/Agentic AI hackathon/.env")
-
-# Initialize the Together client
-client = Together(api_key=TOGETHER_API_KEY)
-
-# Load personality context from file
-PERSONALITY_FILE = "/Users/ay/Documents/projects/Agentic AI hackathon/personality.txt"
-try:
-    with open(PERSONALITY_FILE, "r") as f:
-        personality_context = f.read()
-except FileNotFoundError:
-    personality_context = "Default personality: A friendly and witty chatbot with a passion for horror and gaming."
-    warnings.warn(f"Personality file not found at {PERSONALITY_FILE}. Using default personality.")
-
-def chatbot_response(message, history):
-    """
-    Generate a response using the Together AI LLM (meta-llama/Meta-Llama-3-8B-Instruct-Lite)
-    with RAG to enforce a specific personality defined in personality.txt.
-    Incorporates chat history to maintain context.
-    """
-    if not message.strip():
-        return "Please say something, survivor! The zombies are waiting!"
-
-    # Build the conversation history
-    messages = [
-        {
-            "role": "system",
-            "content": (
-                "You are a chatbot with a specific personality defined below. Follow the personality, tone, and guidelines in all responses:\n\n"
-                f"{personality_context}\n\n"
-                "Use the conversation history and the user's message to generate a response that aligns with your personality."
-            )
-        }
-    ]
-    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})
 
-    # Call the Together AI LLM
-    try:
-        response = client.chat.completions.create(
-            model="meta-llama/Meta-Llama-3-8B-Instruct-Lite",
-            messages=messages,
-            max_tokens=200,  # Limit response length for brevity
-            temperature=0.7,  # Adjust for creativity
-        )
-        bot_message = response.choices[0].message.content
-    except Exception as e:
-        bot_message = f"Error in the apocalypse: {str(e)}. Try again, survivor!"
+    response = ""
 
-    return bot_message
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
 
-# Create the Gradio interface
-def create_chatbot():
-    with gr.Blocks(title="ZombieSlayerBot") as demo:
-        gr.Markdown("# 🧟‍♂️ ZombieSlayerBot")
-        gr.Markdown("Welcome, survivor! I'm ZombieSlayerBot, your witty guide through the zombie-infested world of Resident Evil. Let’s lock and load—chat with me!")
+        response += token
+        yield response
 
-        chatbot = gr.Chatbot(height=400, show_label=False, container=True)
 
-        with gr.Row():
-            msg = gr.Textbox(
-                placeholder="Type your message here, survivor...",
-                show_label=False,
-                container=False,
-                scale=4,
-            )
-            submit_btn = gr.Button("Send", variant="primary", scale=1)
-
-        clear = gr.Button("Clear Chat", variant="secondary")
-
-        def respond(message, chat_history):
-            bot_message = chatbot_response(message, chat_history)
-            chat_history.append((message, bot_message))
-            return "", chat_history
-
-        # Connect both textbox submit and button click
-        msg.submit(respond, [msg, chatbot], [msg, chatbot])
-        submit_btn.click(respond, [msg, chatbot], [msg, chatbot])
-        clear.click(lambda: None, None, chatbot, queue=False)
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
 
-    return demo
 
 if __name__ == "__main__":
-    demo = create_chatbot()
-    demo.launch(server_name="0.0.0.0", server_port=7860, share=True, debug=False)
+    demo.launch()