mirror of
https://github.com/Tencent/WeKnora.git
synced 2025-11-25 03:15:00 +08:00
2d66abedf0
移除日志设置与冗余代码，优化导入、类型提示及OCR后端管理 统一调整各文件模块导入路径为绝对导入 调整导入路径，移除部分导入，优化日志及注释 升级文档解析器为 Docx2Parser，优化超时与图片处理逻辑
38 lines
904 B
TOML
38 lines
904 B
TOML
[project]
|
|
name = "docreader"
|
|
version = "0.1.0"
|
|
description = "Add your description here"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10.18"
|
|
dependencies = [
|
|
"antiword>=0.1.0",
|
|
"asyncio>=4.0.0",
|
|
"beautifulsoup4>=4.14.2",
|
|
"cos-python-sdk-v5>=1.9.38",
|
|
"goose3[all]>=3.1.20",
|
|
"grpcio>=1.76.0",
|
|
"grpcio-health-checking>=1.76.0",
|
|
"grpcio-tools>=1.76.0",
|
|
"lxml>=6.0.2",
|
|
"markdown>=3.10",
|
|
"markdownify>=1.2.0",
|
|
"markitdown[docx,pdf,xls,xlsx]>=0.1.3",
|
|
"minio>=7.2.18",
|
|
"mistletoe>=1.5.0",
|
|
"ollama>=0.6.0",
|
|
"openai>=2.7.1",
|
|
"paddleocr>=2.10.0,<3.0.0",
|
|
"paddlepaddle>=3.0.0,<4.0.0",
|
|
"pdfplumber>=0.11.7",
|
|
"pillow>=12.0.0",
|
|
"playwright>=1.55.0",
|
|
"protobuf>=6.33.0",
|
|
"pydantic>=2.12.3",
|
|
"pypdf>=6.1.3",
|
|
"pypdf2>=3.0.1",
|
|
"python-docx>=1.2.0",
|
|
"requests>=2.32.5",
|
|
"textract==1.5.0",
|
|
"urllib3>=2.5.0",
|
|
]
|