Update app.py

app.py

@@ -8,6 +8,10 @@ import gradio as gr
 import os
 import spaces
 from dotenv import load_dotenv
+from fastapi import FastAPI, Request
+from fastapi.responses import JSONResponse
+
+app = FastAPI()
 
 load_dotenv()
 
@@ -117,22 +121,23 @@ async def process_message(message):
     for model, response in unique_responses.items():
         formatted_response += f"**{model}:**\n{response}\n\n"
 
-    curl_command = f"""
-    curl -X POST -H "Content-Type: application/json" \\
-         -d '{{"message": "{message}"}}' \\
-         http://localhost:7860/generate
-    """
-    return formatted_response, curl_command
+    return formatted_response
 
+@app.post("/generate_multimodel")
+async def api_generate_multimodel(request: Request):
+    data = await request.json()
+    message = data["message"]
+    formatted_response = await process_message(message)
+    return JSONResponse({"response": formatted_response})
 
 iface = gr.Interface(
     fn=process_message,
     inputs=gr.Textbox(lines=2, placeholder="Enter your message here..."),
-    outputs=[gr.Markdown(), gr.Textbox(label="cURL command")],
+    outputs=gr.Markdown(),
     title="Multi-Model LLM API",
     description="Enter a message and get responses from multiple LLMs.",
 )
 
 if __name__ == "__main__":
-    port = int(os.environ.get("PORT", 7860))
+    port = int(os.environ.get("PORT", 7867))
     iface.launch(server_port=port)