using api url

app.py

@@ -7,16 +7,15 @@
 
 # dataset = load_dataset("soulhq-ai/insuranceQA-v2")
 
-import torch
-from transformers import pipeline
+import requests
 
-model_id = "meta-llama/Llama-3.2-3B"
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B"
+headers = {"Authorization": "Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}
 
-pipe = pipeline(
-    "text-generation", 
-    model=model_id, 
-    torch_dtype=torch.bfloat16, 
-    device_map="auto"
-)
-
-pipe("The key to life is")
+def query(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+	
+output = query({
+	"inputs": "Can you please let us know more details about your ",
+})