Update app.py

app.py

@@ -1,25 +1,70 @@
 import gradio as gr
-from huggingface_hub.utils import HfHubHTTPError
+from huggingface_hub import InferenceClient
+import os
+
+# Ensure the required library is installed
+os.system("pip install minijinja")
+
+"""
+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/Meta-Llama-3.1-8B")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [system_message]
+
+    for val in history:
+        if val[0]:
+            messages.append(val[0])
+        if val[1]:
+            messages.append(val[1])
+
+    messages.append(message)
+
+    response = ""
 
-def predict(message, history):
     try:
-        # Load the model interface directly using the load method
-        chat_interface = gr.Interface.load("models/meta-llama/Meta-Llama-3.1-8B")
-
-        # Get the prediction using the correct method call
-        response = chat_interface.predict(message)
-        history.append((message, response))
-        return "", history
-
-    except HfHubHTTPError as e:
-        if e.response.status_code == 504:
-            return "Server overloaded. Please try again later.", history
-        else:
-            raise e
-
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox()
-    clear = gr.ClearButton([msg, chatbot])
-
-    msg.submit(predict, [msg, chatbot], [msg, chatbot])
+        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
+    except Exception as e:
+        yield f"Error: {str(e)}"
+
+
+"""
+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="", 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)",
+        ),
+    ],
+)
+
+if __name__ == "__main__":
+    demo.launch()