Upload app.py

app.py

@@ -72,8 +72,8 @@ llm = CustomInferenceClient(model_name=model_name, hf_token=hf_token, kwargs=kwa
 # 임베딩 객체 생성
 from langchain.embeddings import HuggingFaceInstructEmbeddings
 embeddings = HuggingFaceInstructEmbeddings(
-    # model_name="sentence-transformers/all-MiniLM-L6-v2",  
-    cache_folder="./sentence-transformers/all-MiniLM-L6-v2",
+    model_name="sentence-transformers/all-MiniLM-L6-v2",  
+    # cache_folder="./sentence-transformers/all-MiniLM-L6-v2",
     model_kwargs={"device": "cpu"}
     )