Update app.py

app.py

@@ -3,6 +3,13 @@ import numpy as np
 import os
 from sentence_transformers import SentenceTransformer
 from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
+import os
+
+# 设置内存交换参数
+os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:32"
+
+# 设置默认线程数
+torch.set_num_threads(1)  # 减少内存占用
 
 # 使用更轻量的模型 - 添加 token 参数
 model_name = "all-MiniLM-L6-v2"