Update app.py

app.py

@@ -1,70 +1,62 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# -------------------------------
+# Load a lightweight GPT-like model (CPU)
+# -------------------------------
+model_name = "microsoft/DialoGPT-medium"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# -------------------------------
+# Chat function
+# -------------------------------
+def generate_response(history, message):
+    inputs = tokenizer.encode(message + tokenizer.eos_token, return_tensors="pt")
+
+    outputs = model.generate(
+        inputs,
+        max_length=300,
+        pad_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+        top_p=0.90,
+        temperature=0.75
+    )
+
+    reply = tokenizer.decode(outputs[:, inputs.shape[-1]:][0], skip_special_tokens=True)
+
+    history.append((message, reply))
+    return history
+
+# -------------------------------
+# Interface (Creative UI)
+# -------------------------------
+with gr.Blocks(
+    theme=gr.themes.Soft(
+        primary_hue="purple",
+        secondary_hue="blue",
+        neutral_hue="slate"
+    )
+) as demo:
+
+    # Header
+    gr.Markdown("""
+    <h1 style='text-align:center; color:#6D28D9;'>🤖 GPT-Lite Chatbot</h1>
+    <p style='text-align:center; font-size:18px;'>
+    A smart, lightweight, multi-language chatbot that runs <b>100% on CPU</b>.  
+    Ask anything — I'll answer like a mini GPT!
+    </p>
+    <br>
+    """)
+
+    chatbot = gr.Chatbot(height=450, label="ChatGPT-Style Assistant")
+    user_input = gr.Textbox(placeholder="Type your message here...", label="Your Message")
+    clear_btn = gr.Button("Clear Chat")
+
+    user_input.submit(generate_response, [chatbot, user_input], chatbot)
+    user_input.submit(lambda: "", None, user_input)
+    clear_btn.click(lambda: None, None, chatbot)
+
+demo.launch()