类库
› IDP-system
DocAILab/IDP-system
IDP-system是基于AI的智能文档处理系统,支持PDF、图片等格式。具备版面分析、OCR文字提取、表格识别、信息抽取、敏感词检测及文档指纹比对等功能,适用于文档分类与防泄漏场景。
技术栈
根目录 python
框架
FastAPI
网络
Requests
查看全部依赖 (177)
依赖
Babel
Cython
Flask
Flask-Babel
Jinja2
MarkupSafe
NumPy
Pandas
Pillow
PyGObject
PyJWT
PyMuPDF
PyWavelets
PyYAML
Pydantic
Pygments
SecretStorage
Werkzeug
aiohttp
aiosignal
annotated-types
anyio
astor
async-timeout
attrdict
attrs
bce-python-sdk
beautifulsoup4
blinker
cachetools
ceph
cephfs
certifi
cffi
chardet
charset-normalizer
click
cloud-init
colorama
colorlog
command-not-found
configobj
contourpy
cryptography
cssselect
cssutils
cycler
datasets
datasketch
dbus-python
decorator
dill
distlib
distro
distro-info
et-xmlfile
exceptiongroup
faiss-cpu
fast-tokenizer-python
filelock
fire
fonttools
frozenlist
fsspec
future
gpg
h11
httplib2
huggingface-hub
idna
imageio
imgaug
importlib-metadata
itsdangerous
jeepney
jieba
joblib
jsonpatch
jsonpointer
jsonschema
keyring
kiwisolver
launchpadlib
lazr.restfulclient
lazr.uri
lazy_loader
lmdb
lxml
markdown-it-py
matplotlib
mdurl
more-itertools
multidict
multiprocess
netifaces
networkx
nltk
oauthlib
olefile
opencv-contrib-python
opencv-python
openpyxl
openslide-python
opt-einsum
packaging
paddle-bfloat
paddle2onnx
paddlefsl
paddlenlp
paddleocr
paddlepaddle-gpu
pbr
pdf2docx
pdfminer.six
pdfplumber
platformdirs
premailer
prettytable
protobuf
psutil
pyOpenSSL
pyarrow
pyclipper
pycparser
pycryptodome
pydantic_core
pyinotify
pyparsing
pypdfium2
pyrsistent
pyserial
python-apt
python-dateutil
python-docx
pytz
rados
rapidfuzz
rarfile
rbd
regex
rich
scikit-image
scikit-learn
scipy
sentencepiece
seqeval
shapely
simplejson
six
sniffio
soupsieve
ssh-import-id
starlette
stevedore
systemd-python
termcolor
threadpoolctl
tifffile
tqdm
typer
typing_extensions
tzdata
ubuntu-advantage-tools
ubuntu-drivers-common
ufw
urllib3
uvicorn
virtualenv
virtualenv-clone
virtualenvwrapper
visualdl
wadllib
wcwidth
xkit
xxhash
yarl
zipp