rthrth

app.py

@@ -15,7 +15,7 @@ def get_embeddings(text, task):
     task = "Given a question, retrieve passages that answer the question"
     prompt = f"Instruct: {task}\nQuery: {text}"  # Use text here
     query_embeddings = model.encode([prompt], convert_to_tensor=True)  # Ensure it's a list
-    return query_embeddings
+    return query_embeddings.cpu().numpy()
 
 
 # Initialize a persistent Chroma client and retrieve collection