Update app.py

app.py

@@ -1,39 +1,64 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-
-# Model name (use a specialized medical model for better results)
-model_name = "microsoft/DialoGPT-medium"
-
-# Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
-
-# Initialize the pipeline
-chatbot_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
-
-def generate_response(user_input):
-    try:
-        # Generate a response using the model
-        responses = chatbot_pipeline(user_input, max_length=150, num_return_sequences=1)
-        response = responses[0]['generated_text']
-        return response.strip()
-    except Exception as e:
-        return "I'm sorry, I encountered an error while processing your request. Please try again later."
-
-# Define the Gradio interface
-iface = gr.Interface(
-    fn=generate_response,
-    inputs=gr.Textbox(lines=2, placeholder="Ask a medical question..."),
-    outputs=gr.Textbox(),
-    title="AI Patient Interaction Chatbot",
-    description="Ask any health-related questions and get real-time answers.",
-    examples=[
-        ["What are the symptoms of diabetes?"],
-        ["How can I manage my hypertension?"],
-        ["What should I do if I have a headache?"],
+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("meta-llama/Llama-3.2-1B")
+
+
+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]})
+
+    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,
+    ):
+        token = message.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
+"""
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=2048, 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)",
+        ),
     ],
-    theme="compact"
 )
 
-# Launch the interface
-iface.launch()
+
+if __name__ == "__main__":
+    demo.launch()