feat: switch to OpenAI client for Hugging Face router and update Llama model endpoint

app.py

@@ -1,13 +1,15 @@
 from fastapi import FastAPI
 from pydantic import BaseModel
 from huggingface_hub import InferenceClient
+from openai import OpenAI
 import os
 
+
 app = FastAPI()
 
-client = InferenceClient(
-    provider="hf-inference",
-    api_key=os.environ.get("HF_TOKEN")
+client = OpenAI(
+    base_url="https://router.huggingface.co/v1",
+    api_key=os.environ["HF_TOKEN"],
 )
 
 class ChatRequest(BaseModel):
@@ -20,8 +22,7 @@ def greet_json():
 @app.post("/chat")
 def chat(request: ChatRequest):
     response = client.chat.completions.create(
-        model="meta-llama/Meta-Llama-3-8B-Instruct",
+        model="meta-llama/Llama-3.1-8B-Instruct:novita",
         messages=[{"role": "user", "content": request.message}],
-        max_tokens=1024,
     )
-    return {"response": response.choices[0].message.content}
+    return {"response": response.choices[0].message}