Update app.py

app.py

@@ -16,6 +16,7 @@ from pydantic import BaseModel
 from typing import List, Optional, AsyncGenerator
 import asyncio
 import gradio as gr
+from gradio import HTML
 
 # ==============================================================================
 # Model Architecture (Same as before)
@@ -446,7 +447,7 @@ async def chat_completions(request: ChatCompletionRequest):
                     "finish_reason": None
                 }]
             }
-            yield f"data: {json.dumps(chunk)}\n\n"
+            yield f" {json.dumps(chunk)}\n\n"
         yield " [DONE]\n\n"
 
     if request.stream:
@@ -471,7 +472,7 @@ async def list_models():
 
 
 # ==============================================================================
-# Simple Gradio API Info Page (Replaces Chat UI)
+# Gradio App (API Info Page)
 # ==============================================================================
 
 def get_api_info():
@@ -501,10 +502,13 @@ Set `"stream": true` in your request to receive real-time token-by-token respons
   "stream": true,
   "temperature": 0.7
 }}
-"""
+```
+    """
+
+# Create the Gradio app
 with gr.Blocks(title="SAM-X-1 API") as demo:
     gr.Markdown(get_api_info())
 
-
-    app = gr.mount_gradio_app(app, demo, path="/")
-
+# Launch Gradio app with FastAPI mounted
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860, show_error=True)