changed model and specified device in model.encode to make use of gpu properly

app.py

@@ -6,14 +6,15 @@ import torch # For gpu
 # Make the app device agnostic
 device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
 
-# Load a pretrained Sentence Transformer model
-model = SentenceTransformer("all-MiniLM-L6-v2").to(device)
+# Load a pretrained Sentence Transformer model and move it to the appropriate device
+model = SentenceTransformer('Alibaba-NLP/gte-large-en-v1.5', trust_remote_code=True)
+model = model.to(device)
 
 # Function that does the embedding
 def predict(input_text):
     
-    # Calculate embeddings by calling model.encode()
-    embeddings = model.encode(input_text)
+    # Calculate embeddings by calling model.encode(), specifying the device
+    embeddings = model.encode(input_text, device=device)
 
     return embeddings