Update app.py

app.py

@@ -1,63 +1,51 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
 
-"""
-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("https://huggingface.co/mlabonne/Meta-Llama-3-120B-Instruct")
+# Fetch the API key from environment variables
+api_key = os.getenv('HF_API_KEY')
 
+# Configure the Inference API client
+client = InferenceClient("meta-llama-3-120b-instruct-zoa", token=api_key)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     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]})
-
+    
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
+        
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    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
+    try:
+        responses = client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+        )
+    except Exception as e:
+        yield f"Error: {str(e)}"
+        return
 
-        response += token
+    response = ""
+    for res in responses:
+        response += res.choices[0].delta.content
         yield response
 
-"""
-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="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="You are a friendly assistant.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, label="Top-p (nucleus sampling)"),
     ],
+    title="Meta-Llama Chat",
+    description="A chat interface powered by Meta Llama 3-120B model."
 )
 
-
 if __name__ == "__main__":
     demo.launch()