app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+ENDPOINT_URL = "https://x6leavj4hgm2fdyx.us-east-2.aws.endpoints.huggingface.cloud"
 
 def respond(
     message,
@@ -12,37 +13,33 @@ def respond(
     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
+    Uses your Hugging Face Inference Endpoint for chat completion.
     """
-    client = InferenceClient(token=hf_token.token, model="kaizen9/qsft")
+    # Use the endpoint URL here. `token` must be the raw string.
+    client = InferenceClient(model=ENDPOINT_URL, token=hf_token.token)
 
+    # Build messages (system + prior turns + current user)
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
+    # Stream tokens from the endpoint
     response = ""
-
-    for message in client.chat_completion(
-        messages,
+    for chunk in client.chat_completion(
+        messages=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
-
+        if chunk.choices and chunk.choices[0].delta.content:
+            token = chunk.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
-"""
+# ---- Gradio UI ----
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
@@ -50,21 +47,15 @@ chatbot = gr.ChatInterface(
         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)"),
     ],
 )
 
 with gr.Blocks() as demo:
     with gr.Sidebar():
-        gr.LoginButton()
+        gr.LoginButton()  # lets you pass the HF token to the app
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()
+