update loader.py

chains/local_doc_qa.py

@@ -26,6 +26,9 @@ def load_file(filepath, sentence_size=SENTENCE_SIZE):
     if filepath.lower().endswith(".md"):
         loader = UnstructuredFileLoader(filepath, mode="elements")
         docs = loader.load()
+    elif filepath.lower().endswith(".txt"):
+        loader = UnstructuredFileLoader(filepath, mode="elements")
+        docs = loader.load()
     elif filepath.lower().endswith(".pdf"):
         loader = UnstructuredPaddlePDFLoader(filepath)
         textsplitter = ChineseTextSplitter(pdf=True, sentence_size=sentence_size)
@@ -47,7 +50,7 @@ def write_check_file(filepath, docs):
     if not os.path.exists(folder_path):
         os.makedirs(folder_path)
     fp = os.path.join(folder_path, 'load_file.txt')
-    fout = open(fp, 'a')
+    with open(fp, 'a+', encoding='utf-8') as fout:
         fout.write("filepath=%s,len=%s" % (filepath, len(docs)))
         fout.write('\n')
         for i in docs:

loader/pdf_loader.py

@@ -19,7 +19,7 @@ class UnstructuredPaddlePDFLoader(UnstructuredFileLoader):
             ocr = PaddleOCR(lang="ch", use_gpu=False, show_log=False)
             doc = fitz.open(filepath)
             txt_file_path = os.path.join(full_dir_path, "%s.txt" % (filename))
-            img_name = os.path.join(full_dir_path, '.tmp.png')
+            img_name = os.path.join(full_dir_path, 'tmp.png')
             with open(txt_file_path, 'w', encoding='utf-8') as fout:
 
                 for i in range(doc.page_count):