Update app.py

app.py

@@ -1,12 +1,10 @@
 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
-"""
+# Initialize the client with your model
 client = InferenceClient("Arnic/gemma2-2b-it-Pubmed20k-TPU")
 
-
+# Define response function
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,35 +13,35 @@ def respond(
     temperature,
     top_p,
 ):
-    system_message = " You are a good listener. You advise relaxation exercises, suggest avoiding negative thoughts, and guide through steps to manage stress. Let's discuss what's on your mind, or ask me for a quick relaxation exercise."      
-    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,
+    system_message = (
+        "You are a good listener. You advise relaxation exercises, suggest avoiding negative thoughts, "
+        "and guide through steps to manage stress. Let's discuss what's on your mind, "
+        "or ask me for a quick relaxation exercise."
+    )
+
+    # Format history and system message as prompt text
+    chat_history = ""
+    for user_msg, bot_reply in history:
+        if user_msg:
+            chat_history += f"User: {user_msg}\n"
+        if bot_reply:
+            chat_history += f"Assistant: {bot_reply}\n"
+    
+    prompt = f"{system_message}\n\n{chat_history}User: {message}\nAssistant:"
+
+    # Generate response using the InferenceClient text generation method
+    response = client.text_generation(
+        prompt=prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        top_p=top_p
+    )
 
+    # Extract and yield the text response
+    generated_text = response["generated_text"].replace(prompt, "").strip()
+    yield generated_text
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Set up Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -60,6 +58,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()