Update app.py

app.py

@@ -1,64 +1,72 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-"""
-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")
+# Load a lightweight, conversational model
+model_name = "microsoft/DialoGPT-small"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
+# Store chat history
+chat_history_ids = None
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Inference function
+def chat_with_bot(user_input, history=[]):
+    global chat_history_ids
+    new_input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors='pt')
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    if chat_history_ids is not None:
+        bot_input_ids = torch.cat([chat_history_ids, new_input_ids], dim=-1)
+    else:
+        bot_input_ids = new_input_ids
 
-    messages.append({"role": "user", "content": message})
+    chat_history_ids = model.generate(
+        bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id,
+        no_repeat_ngram_size=3, do_sample=True, top_k=100, top_p=0.7, temperature=0.8
+    )
 
-    response = ""
+    response = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+    history.append((user_input, response))
+    return history, history
 
-    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
+# Gradio Interface
+def reset_history():
+    global chat_history_ids
+    chat_history_ids = None
+    return []
 
-        response += token
-        yield response
+theme_css = """
+body {
+  background-color: #FFF3E0;
+  font-family: Arial, sans-serif;
+}
 
+h1 {
+  color: darkorange;
+  text-align: center;
+  font-weight: bold;
+}
 
+.gradio-container {
+  max-width: 900px;
+  margin: auto;
+  padding: 20px;
+  box-shadow: 0 4px 12px rgba(0, 0, 0, 0.2);
+  border-radius: 12px;
+  background-color: white;
+}
 """
-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)",
-        ),
-    ],
-)
 
+with gr.Blocks(css=theme_css) as demo:
+    gr.Markdown("""<h1>🤖 AI Chatbot Assistant</h1>""")
+
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(placeholder="Type your message here...", label="Your Message")
+    clear = gr.Button("🧹 Clear Chat")
+
+    state = gr.State([])
+
+    msg.submit(chat_with_bot, [msg, state], [chatbot, state])
+    clear.click(fn=reset_history, outputs=[chatbot, state])
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()