Update app.py

app.py

@@ -1,70 +1,72 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
 
+# 🔹 Load HF token from Space Secrets (set in Space settings → Secrets)
+HF_TOKEN = os.environ.get('telemedpro')
 
-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="m42-health/Llama3-Med42-70B")
-
-    messages = [{"role": "system", "content": system_message}]
+# 🔹 Default system persona message
+SYSTEM_MESSAGE = (
+    "You are Dr. Alex, a highly knowledgeable yet empathetic doctor. "
+    "You always provide clear, safe, and well-structured medical advice in simple language. "
+    "You avoid making unsafe claims and encourage users to seek professional help when needed. "
+    "You behave politely, patiently, and with care, like a trusted family doctor."
+)
 
-    messages.extend(history)
+# 🔹 Initialize client once
+client = InferenceClient(token=HF_TOKEN, model="m42-health/Llama3-Med42-70B")
 
-    messages.append({"role": "user", "content": message})
+# 🔹 Respond function (non-OAuthToken, stable streaming)
+def respond(message, history, system_message=SYSTEM_MESSAGE, max_tokens=512, temperature=0.7, top_p=0.95):
+    try:
+        # Start with system message
+        messages = [{"role": "system", "content": system_message}]
 
-    response = ""
+        # Append previous conversation (Gradio handles history as list of [user, assistant])
+        if history:
+            for h in history:
+                user_msg = h[0] if h[0] else ""
+                ai_msg = h[1] if h[1] else ""
+                messages.append({"role": "user", "content": user_msg})
+                messages.append({"role": "assistant", "content": ai_msg})
 
-    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
+        # Append current user message
+        messages.append({"role": "user", "content": message})
 
-        response += token
-        yield response
+        # Stream model output
+        response = ""
+        for msg in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            if msg.choices and hasattr(msg.choices[0].delta, "content") and msg.choices[0].delta.content:
+                token = msg.choices[0].delta.content
+                response += token
+                yield response
 
+    except Exception as e:
+        yield f"⚠️ Space error: {e}"
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# 🔹 Gradio Chat Interface
 chatbot = gr.ChatInterface(
-    respond,
+    fn=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)",
-        ),
+        gr.Textbox(value=SYSTEM_MESSAGE, label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, 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"),
     ],
 )
 
+# 🔹 Layout
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
+    gr.Markdown("## 🩺 AI Health Mentor — Dr. Alex")
     chatbot.render()
 
-
+# 🔹 Launch Space
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(show_error=True)