Update app.py

app.py

@@ -1,64 +1,59 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
 
-"""
-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")
+# Load API key securely from Hugging Face secrets or environment
+api_key = os.getenv("NV_API_KEY")
+if not api_key:
+    raise ValueError("Please set the NV_API_KEY environment variable in your Hugging Face Space.")
 
+# NVIDIA-compatible OpenAI client
+client = OpenAI(
+    base_url="https://integrate.api.nvidia.com/v1",
+    api_key=api_key
+)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# System message
+system_prompt = {
+    "role": "system",
+    "content": "You are a helpful assistant to answer user queries."
+}
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Main chat function with memory from Gradio
+def get_text_response(user_message, history):
+    # Convert Gradio history to OpenAI format
+    formatted_history = [{"role": "user" if i % 2 == 0 else "assistant", "content": msg}
+                         for i, msg in enumerate(sum(history, []))]
 
-    messages.append({"role": "user", "content": message})
+    # Combine system prompt, history, and current user input
+    messages = [system_prompt] + formatted_history + [{"role": "user", "content": user_message}]
 
+    # Stream the response
     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
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+    completion = client.chat.completions.create(
+        model="nvidia/llama-3.1-nemotron-70b-instruct",
+        messages=messages,
+        temperature=0.5,
+        top_p=1,
+        max_tokens=100,
+        stream=True
+    )
+
+    for chunk in completion:
+        delta = chunk.choices[0].delta
+        if delta and delta.content:
+            response += delta.content
+
+    return response
+
+# Gradio Chat Interface
 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)",
-        ),
-    ],
+    fn=get_text_response,
+    title="🧠 Nemotron 70B Assistant",
+    theme="soft",
+    textbox=gr.Textbox(placeholder="Ask me anything...", container=False),
+    examples=["How are you doing?", "What are your interests?", "Which places do you like to visit?"]
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.queue().launch()