Update app.py

app.py

@@ -1,64 +1,100 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import random
+from openai import OpenAI
+from typing import List, Tuple
+import time
 
-"""
-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")
+class EmmaChat:
+    def __init__(self):
+        self.client = OpenAI(
+            base_url="https://integrate.api.nvidia.com/v1",
+            api_key="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"
+        )
 
+        self.system_message = """You are Aadhya, a 17-year-old who grew up in Mumbai. You have a passion for art and enjoy playing volleyball. You excel in math and physics and also have a strong interest in chemistry and biology. You constantly seek knowledge and are willing to work hard. Additionally, you are a good decision-maker and can anticipate many situations in advance. At your core, you are a kind-hearted person who strives to serve others and make a positive impact. You work toward a better future for both yourself and humanity."""
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    def generate_response(self, message: str, history: List[Tuple[str, str]]) -> str:
+        # Convert history to OpenAI message format
+        messages = [{"role": "system", "content": self.system_message}]
+        for user_msg, assistant_msg in history:
+            messages.append({"role": "user", "content": user_msg})
+            messages.append({"role": "assistant", "content": assistant_msg})
+        messages.append({"role": "user", "content": 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]})
+        try:
+            completion = self.client.chat.completions.create(
+                model="meta/llama-3.2-3b-instruct",
+                messages=messages,
+                temperature=0.2,
+                max_tokens=1024,
+                stream=True
+            )
 
-    messages.append({"role": "user", "content": message})
+            # Stream the response
+            full_response = ""
+            for chunk in completion:
+                if chunk.choices[0].delta.content is not None:
+                    full_response += chunk.choices[0].delta.content
+                    yield full_response
 
-    response = ""
+        except Exception as e:
+            yield f"I apologize, but I encountered an error: {str(e)}"
 
-    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
+def create_chat_interface() -> gr.ChatInterface:
+    emma = EmmaChat()
 
-        response += token
-        yield response
+    # Custom CSS for the chat interface
+    custom_css = """
+    .message.user div.content {
+        background-color: #DCF8C6 !important;
+    }
+    .message.bot div.content {
+        background-color: #E8E8E8 !important;
+    }
+    .message.user, .message.bot {
+        padding: 1rem;
+    }
+    .avatar {
+        border-radius: 50%;
+        width: 40px;
+        height: 40px;
+    }
+    .message-wrap {
+        max-width: 800px;
+        margin: 0 auto;
+    }
+    """
 
 
-"""
-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)",
+    # Create the chat interface
+    chat_interface = gr.ChatInterface(
+        fn=emma.generate_response,
+        title="Chat with Aadhya 👩🏻",
+        description="""Aadhya is a 17-year-old from Mumbai with a passion for Art and a competitive spirit in volleyball. She excels in math, physics, chemistry, and biology, blending her analytical skills with a love for problem-solving. Driven by a desire to positively impact humanity, she is also committed to personal growth and excellence.""",
+        examples=[
+            ["Hi, can you intro yourself?"],
+            ["Is there any way I can get help from you? I'm glad to meet you."],
+            ["I'm so glad to connect with you! Do you think we can work together on anything?"],
+            ["How can I start a small garden at home?"]
+        ],
+        theme=gr.themes.Soft(
+            primary_hue="pink",
+            secondary_hue="purple",
         ),
-    ],
-)
+        css=custom_css
+        # Removed: retry_btn="🔄 Retry",
+        # Removed: undo_btn="↩️ Undo",
+        # Removed: clear_btn="🗑️ Clear",
+    )
 
+    return chat_interface
 
 if __name__ == "__main__":
-    demo.launch()
+    chat_interface = create_chat_interface()
+    chat_interface.queue()
+    chat_interface.launch(
+        share=True,
+        server_name="0.0.0.0",
+        server_port=7000,
+        show_api=False
+    )