more file format support

crazy_functions/Rag_Interface.py

@@ -5,7 +5,7 @@ from llama_index.core import Document
 from shared_utils.fastapi_server import validate_path_safety
 
 from toolbox import report_exception
-from crazy_functions.rag_fns.rag_file_support import extract_text
+from crazy_functions.rag_fns.rag_file_support import extract_text, supports_format
 from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_lastest_msg
 from crazy_functions.crazy_utils import input_clipping
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
@@ -48,7 +48,7 @@ def handle_document_upload(files: List[str], llm_kwargs, plugin_kwargs, chatbot,
             text = extract_text(file_path)
             if text is None:
                 chatbot.append(
-                    [f"上传文件: {os.path.basename(file_path)}", "文件解析失败，无法提取文本内容，请更换文件。"])
+                    [f"上传文件: {os.path.basename(file_path)}", f"文件解析失败，无法提取文本内容，请更换文件。失败原因可能为：1.文档格式过于复杂；2. 不支持的文件格式，支持的文件格式后缀有:" + ", ".join(supports_format)])
             else:
                 chatbot.append(
                     [f"上传文件: {os.path.basename(file_path)}", f"上传文件前50个字符为:{text[:50]}。"])

crazy_functions/rag_fns/rag_file_support.py

@@ -1,22 +1,16 @@
 import os
 from llama_index.core import SimpleDirectoryReader
 
-# 保留你原有的自定义解析函数
-from PyPDF2 import PdfReader
+supports_format = ['.csv', '.docx', '.epub', '.ipynb',  '.mbox', '.md', '.pdf',  '.txt', '.ppt',
+                   '.pptm', '.pptx']
 
-def extract_text_from_pdf(file_path):
-    reader = PdfReader(file_path)
-    text = ""
-    for page in reader.pages:
-        text += page.extract_text() + "\n"
-    return text
 
 # 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
 def extract_text(file_path):
     _, ext = os.path.splitext(file_path.lower())
 
     # 使用 SimpleDirectoryReader 处理它支持的文件格式
-    if ext in ['.txt', '.md', '.pdf', '.docx', '.html']:
+    if ext in supports_format:
         try:
             reader = SimpleDirectoryReader(input_files=[file_path])
             documents = reader.load_data()
@@ -25,10 +19,4 @@ def extract_text(file_path):
         except Exception as e:
             pass
 
-    # 如果 SimpleDirectoryReader 失败，或文件格式不支持，使用自定义解析逻辑
-    if ext == '.pdf':
-        try:
-            return extract_text_from_pdf(file_path)
-        except Exception as e:
-            pass
     return None