Update app.py

app.py

@@ -3,7 +3,8 @@ from gradio_client import Client
 import sys
 import io
 import json 
-
+import gradio as gr
+from huggingface_hub import InferenceClient
 mcp = FastMCP("gradio-spaces")
 
 clients = {}
@@ -61,9 +62,67 @@ async def run_dia_tts(prompt: str, space_id: str = "ysharma/Dia-1.6B") -> str:
     return result
 
 
+
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    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]})
+
+    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
+
+        response += token
+        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)",
+        ),
+    ],
+)
+
+
 if __name__ == "__main__":
     import sys
     import io
     sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
     
-    mcp.run(transport='stdio')
+    mcp.run(transport='stdio')
+    demo.launch()