CC/gpt_academic
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

up

Browse Source
This commit is contained in:
lbykkkk
2024-12-01 17:35:57 +08:00
parent cf51d4b205
commit b3aef6b393
13 changed files with 398 additions and 234 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
crazy_functions/rag_fns/rag_file_support.py
View File

@@ -1,8 +1,8 @@
import os
from llama_index.core import SimpleDirectoryReader
supports_format = ['.csv', '.docx','.doc', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt',
'.pptm', '.pptx','.py', '.xls', '.xlsx', '.html', '.json', '.xml', '.yaml', '.yml' ,'.m']
supports_format = ['.csv', '.docx', '.doc', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt',
'.pptm', '.pptx', '.py', '.xls', '.xlsx', '.html', '.json', '.xml', '.yaml', '.yml', '.m']
def read_docx_doc(file_path):
if file_path.split(".")[-1] == "docx":
@@ -25,9 +25,11 @@ def read_docx_doc(file_path):
raise RuntimeError('请先将.doc文档转换为.docx文档。')
return file_content
# 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
import os
def extract_text(file_path):
_, ext = os.path.splitext(file_path.lower())