Update

app.py

@@ -2,31 +2,31 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 import os
 
-# Load token and create client
-token = os.getenv("huggingface_token")
+"""
+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",
-    token=token,
-    provider="auto"  # <- fixes the issue
+    model="HuggingFaceH4/zephyr-7b-beta",
+    token=os.getenv("huggingface_token"),
+    provider="hf-inference"
 )
 
-# Load system messages from environment
-SYSTEM_MESSAGES = {
-    "LaunchPad": os.getenv("DEFAULT_SYSTEM_MESSAGE_1", "Default LaunchPad message."),
-    "MentorBot": os.getenv("DEFAULT_SYSTEM_MESSAGE_2", "Default MentorBot message."),
-    "CoachAI": os.getenv("DEFAULT_SYSTEM_MESSAGE_3", "Default CoachAI message."),
-}
-
-# Chat function used by Gradio UI
-def respond(message, history, persona, max_tokens, temperature, top_p):
-    system_message = SYSTEM_MESSAGES.get(persona, "Default fallback message.")
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
     messages = [{"role": "system", "content": system_message}]
 
-    for user, assistant in history:
-        if user:
-            messages.append({"role": "user", "content": user})
-        if assistant:
-            messages.append({"role": "assistant", "content": assistant})
+    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 = ""
@@ -37,44 +37,30 @@ def respond(message, history, persona, max_tokens, temperature, top_p):
         temperature=temperature,
         top_p=top_p,
     ):
-        token_piece = message.choices[0].delta.content
-        response += token_piece
+        token = message.choices[0].delta.content
+
+        response += token
         yield response
 
-# API-callable version
-def chat_api(message, persona, max_tokens, temperature, top_p):
-    system_message = SYSTEM_MESSAGES.get(persona, "Default fallback message.")
-    messages = [{"role": "system", "content": system_message}]
-    messages.append({"role": "user", "content": message})
 
-    output = ""
-    for chunk in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        output += chunk.choices[0].delta.content
-    return output
-
-# Gradio UI
+"""
+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.Dropdown(
-            choices=list(SYSTEM_MESSAGES.keys()),
-            value="LaunchPad",
-            label="Select Persona"
-        ),
+        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.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
     ],
 )
 
-# Serve UI and API
-demo.launch(share=True, show_error=True, show_api=True)
-
-# To add an API endpoint, you must use FastAPI + mount if needed.
-# Ask if you'd like that added again.
+if __name__ == "__main__":
+    demo.launch(share=True)