diff --git a/chains/local_doc_qa.py b/chains/local_doc_qa.py
index 2d696a3..f2e3be6 100644
--- a/chains/local_doc_qa.py
+++ b/chains/local_doc_qa.py
@@ -9,6 +9,7 @@ from typing import List, Tuple
 from langchain.docstore.document import Document
 import numpy as np
 from utils import torch_gc
+from tqdm import tqdm
 
 
 DEVICE_ = EMBEDDING_DEVICE
@@ -136,6 +137,7 @@ class LocalDocQA:
                                     filepath: str or List[str],
                                     vs_path: str or os.PathLike = None):
         loaded_files = []
+        failed_files = []
         if isinstance(filepath, str):
             if not os.path.exists(filepath):
                 print("路径不存在")
@@ -152,15 +154,19 @@ class LocalDocQA:
                     return None
             elif os.path.isdir(filepath):
                 docs = []
-                for file in os.listdir(filepath):
+                for file in tqdm(os.listdir(filepath), desc="加载文件"):
                     fullfilepath = os.path.join(filepath, file)
                     try:
                         docs += load_file(fullfilepath)
-                        print(f"{file} 已成功加载")
                         loaded_files.append(fullfilepath)
                     except Exception as e:
-                        print(e)
-                        print(f"{file} 未能成功加载")
+                        failed_files.append(file)
+
+                if len(failed_files) > 0:
+                    print("以下文件未能成功加载：")
+                    for file in failed_files:
+                        print(file,end="\n")
+
         else:
             docs = []
             for file in filepath:
@@ -172,6 +178,7 @@ class LocalDocQA:
                     print(e)
                     print(f"{file} 未能成功加载")
         if len(docs) > 0:
+            print("文件加载完毕，正在生成向量库")
             if vs_path and os.path.isdir(vs_path):
                 vector_store = FAISS.load_local(vs_path, self.embeddings)
                 vector_store.add_documents(docs)