03254f8196
- 新增 app/core/cache_paths.py：HF_HOME / tiktoken 缓存统一指向 <repo>/.cache， 本地与 Docker 路径一致，离线部署打包 .cache 即可 - Dockerfile.backend 的 tiktoken 词表改用官方 SHA 文件名，避免运行时回退重建 - 修复 layout_hybrid 路径不运行 detect_pdf_document_noise 的缺陷： needs_pdf_noise 不再与 needs_layout_raw 互斥，PDF 智能预处理在版面切分下也生效 - 新增 layout_noise.py：识别跨页重复的页眉表格标签组并按行剔除， 解决 docling layout 模型把中文企业 PDF 页眉识别成普通 Table 导致清不掉的问题 - 回收 HybridChunker 丢弃的末尾孤立标题，找回章节标题内容
229 lines
4.7 KiB
Plaintext
229 lines
4.7 KiB
Plaintext
# ---> Python
|
||
# Byte-compiled / optimized / DLL files
|
||
__pycache__/
|
||
*.py[cod]
|
||
*$py.class
|
||
|
||
# C extensions
|
||
*.so
|
||
|
||
# Distribution / packaging
|
||
.Python
|
||
build/
|
||
develop-eggs/
|
||
dist/
|
||
node_modules/
|
||
*.tsbuildinfo
|
||
downloads/
|
||
eggs/
|
||
.eggs/
|
||
lib/
|
||
lib64/
|
||
parts/
|
||
sdist/
|
||
var/
|
||
wheels/
|
||
share/python-wheels/
|
||
*.egg-info/
|
||
.installed.cfg
|
||
*.egg
|
||
MANIFEST
|
||
|
||
# PyInstaller
|
||
# Usually these files are written by a python script from a template
|
||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||
*.manifest
|
||
*.spec
|
||
|
||
# Installer logs
|
||
pip-log.txt
|
||
pip-delete-this-directory.txt
|
||
|
||
# Runtime data and logs
|
||
runtime/
|
||
backend/runtime/
|
||
backend/storage/
|
||
logs/
|
||
backend/logs/
|
||
*.db
|
||
*.sqlite
|
||
*.sqlite3
|
||
|
||
# Unit test / coverage reports
|
||
htmlcov/
|
||
.tox/
|
||
.nox/
|
||
.coverage
|
||
.coverage.*
|
||
nosetests.xml
|
||
coverage.xml
|
||
*.cover
|
||
*.py,cover
|
||
.hypothesis/
|
||
.pytest_cache/
|
||
cover/
|
||
|
||
# Translations
|
||
*.mo
|
||
*.pot
|
||
|
||
# Django stuff:
|
||
*.log
|
||
local_settings.py
|
||
db.sqlite3
|
||
db.sqlite3-journal
|
||
|
||
# Flask stuff:
|
||
instance/
|
||
.webassets-cache
|
||
|
||
# Scrapy stuff:
|
||
.scrapy
|
||
|
||
# Sphinx documentation
|
||
docs/_build/
|
||
|
||
# PyBuilder
|
||
.pybuilder/
|
||
target/
|
||
|
||
# Jupyter Notebook
|
||
.ipynb_checkpoints
|
||
|
||
# IPython
|
||
profile_default/
|
||
ipython_config.py
|
||
|
||
# pyenv
|
||
# For a library or package, you might want to ignore these files since the code is
|
||
# intended to run in multiple environments; otherwise, check them in:
|
||
# .python-version
|
||
|
||
# pipenv
|
||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||
# install all needed dependencies.
|
||
#Pipfile.lock
|
||
|
||
# UV
|
||
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
|
||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||
# commonly ignored for libraries.
|
||
#uv.lock
|
||
|
||
# poetry
|
||
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||
# commonly ignored for libraries.
|
||
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
||
#poetry.lock
|
||
|
||
# pdm
|
||
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
||
#pdm.lock
|
||
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
||
# in version control.
|
||
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
|
||
.pdm.toml
|
||
.pdm-python
|
||
.pdm-build/
|
||
|
||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
||
__pypackages__/
|
||
|
||
# Celery stuff
|
||
celerybeat-schedule
|
||
celerybeat.pid
|
||
|
||
# SageMath parsed files
|
||
*.sage.py
|
||
|
||
# Environments
|
||
.env
|
||
!.env.example
|
||
.venv
|
||
env/
|
||
venv/
|
||
ENV/
|
||
env.bak/
|
||
venv.bak/
|
||
|
||
# Local backend config (含数据库账号密码等敏感信息，勿提交)
|
||
backend/config.yaml
|
||
|
||
# Agent / IDE 工具产物，不应进版本库
|
||
.codex-backups/
|
||
.pnpm-store/
|
||
.zcode/
|
||
.claude/
|
||
CLAUDE.md
|
||
|
||
# Spyder project settings
|
||
.spyderproject
|
||
.spyproject
|
||
|
||
# Rope project settings
|
||
.ropeproject
|
||
|
||
# mkdocs documentation
|
||
/site
|
||
|
||
# mypy
|
||
.mypy_cache/
|
||
.dmypy.json
|
||
dmypy.json
|
||
|
||
# Pyre type checker
|
||
.pyre/
|
||
|
||
# pytype static type analyzer
|
||
.pytype/
|
||
|
||
# Cython debug symbols
|
||
cython_debug/
|
||
|
||
# PyCharm
|
||
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
||
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
||
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||
#.idea/
|
||
|
||
# Ruff stuff:
|
||
.ruff_cache/
|
||
|
||
# PyPI configuration file
|
||
.pypirc
|
||
|
||
docker/llamafactory-latest.tar.gz
|
||
# Compute data - 保留目录结构和 README，忽略子目录内容（日志、模型、数据集等）
|
||
!docker/compute/data/yg-ft/logs/
|
||
docker/compute/data/yg-ft/datasets/*
|
||
docker/compute/data/yg-ft/models/*
|
||
docker/compute/data/yg-ft/outputs/*
|
||
docker/compute/data/yg-ft/trained_models/*
|
||
docker/compute/data/yg-ft/logs/**
|
||
!docker/compute/data/yg-ft/logs/compute/
|
||
!docker/compute/data/yg-ft/logs/training/
|
||
!docker/compute/data/yg-ft/**/.gitkeep
|
||
!docker/compute/data/yg-ft/**/README.md
|
||
|
||
# Offline deployment bundle - 离线部署包（镜像、运行时等大文件，不提交）
|
||
docker/offline/
|
||
|
||
# MinIO object storage data - 对象存储运行时数据，勿提交，保留目录结构
|
||
docker/minio/data/*
|
||
!docker/minio/data/.gitkeep
|
||
|
||
# nlp-eval-demo - 独立演示项目，不进版本库
|
||
nlp-eval-demo/
|
||
nlp-eval-demo.zip
|
||
|
||
# 项目本地缓存（HuggingFace / tiktoken 等大文件），保留目录结构与占位文件
|
||
.cache/*
|
||
!.cache/.gitkeep
|
||
!.cache/tiktoken/
|
||
!.cache/huggingface/
|
||
!.cache/**/.gitkeep
|