initial commit

app.py

@@ -11,8 +11,12 @@ API_URL = "https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-b
 # retrieval = Client("https://ishaan-mital-ncert-helper-vector-db.hf.space/--replicas/149bg26k5/")
 
 embed_model_id = 'sentence-transformers/all-MiniLM-L6-v2'
+# device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'
+
 embed_model = HuggingFaceEmbeddings(
     model_name=embed_model_id,
+    # model_kwargs={'device': device},
+    # encode_kwargs={'device': device, 'batch_size': 32}
 )