Update app/main.py

app/main.py

@@ -4,25 +4,12 @@ from fastapi import FastAPI, HTTPException, Request, Depends, Header
 from fastapi.responses import StreamingResponse, JSONResponse
 from pydantic import BaseModel
 from gradio_client import Client
-import time
-import json
+import httpx
 
-# Load environment variables from .env file
-load_dotenv()
-
-# Configure your Gradio Space ID and default endpoint
-SPACE_ID = os.getenv("SPACE_ID", "prithivMLmods/SAMBANOVA")
-DEFAULT_API = os.getenv("DEFAULT_API", "/chat")
-# Timeout for Gradio client (seconds)
-GRADIO_TIMEOUT = int(os.getenv("GRADIO_TIMEOUT", "60"))
-
-# Load API key from env
-API_KEY = os.getenv("API_KEY")
-if not API_KEY:
-    raise RuntimeError("Missing API_KEY in environment")
-
-# Initialize Gradio client with custom timeout to avoid read timeouts
-client = Client(SPACE_ID, timeout=GRADIO_TIMEOUT)
+# Initialize Gradio client
+client = Client(SPACE_ID)
+# Override the default HTTPX timeout to avoid read timeouts
+client.client.timeout = httpx.Timeout(timeout=GRADIO_TIMEOUT)
 
 
 def chat_with_gradio(message: str, api_name: str = DEFAULT_API):
@@ -113,4 +100,4 @@ if __name__ == "__main__":
     print(
         f"Starting server on http://0.0.0.0:7860 using Space {SPACE_ID}{DEFAULT_API} and OpenAI-compatible endpoint /v1/chat/completions"
     )
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+    uvicorn.run(app, host="0.0.0.0", port=7860)