767eb5e6f2
Added document image extraction capability for PDF and DOCX files, including page/index metadata and storage integration. Extended `process_files` with `document_image_recognition` flag to conditionally enable vision-based image processing when model supports it. Updated knowledge repository and workflow node logic to enforce status=1 checks. Added PyMuPDF dependency.
161 lines
3.9 KiB
TOML
161 lines
3.9 KiB
TOML
[project]
|
|
name = "redbear-mem"
|
|
version = "0.1.0"
|
|
description = "Add your description here"
|
|
readme = "README.md"
|
|
requires-python = ">=3.12,<3.13"
|
|
dependencies = [
|
|
"alembic==1.17.0",
|
|
"amqp==5.3.1",
|
|
"annotated-types==0.7.0",
|
|
"anyio==4.11.0",
|
|
"async-timeout==5.0.1",
|
|
"bcrypt==5.0.0",
|
|
"billiard==4.2.2",
|
|
"celery==5.5.3",
|
|
"cffi==2.0.0",
|
|
"click==8.3.0",
|
|
"click-didyoumean==0.3.1",
|
|
"click-plugins==1.1.1.2",
|
|
"click-repl==0.3.0",
|
|
"cryptography==46.0.3",
|
|
"ecdsa==0.19.1",
|
|
"email-validator>=2.3.0",
|
|
"exceptiongroup==1.3.0",
|
|
"fastapi==0.119.0",
|
|
"greenlet==3.2.4",
|
|
"h11==0.16.0",
|
|
"httptools==0.7.1",
|
|
"idna==3.11",
|
|
"kombu==5.5.4",
|
|
"mako==1.3.10",
|
|
"markupsafe==3.0.3",
|
|
"packaging==25.0",
|
|
"passlib==1.7.4",
|
|
"prompt-toolkit==3.0.52",
|
|
"psycopg2-binary==2.9.11",
|
|
"pyasn1==0.6.1",
|
|
"pycparser==2.23",
|
|
"pydantic==2.12.2",
|
|
"pydantic-core==2.41.4",
|
|
"python-dateutil==2.9.0.post0",
|
|
"python-dotenv==1.1.1",
|
|
"python-jose==3.5.0",
|
|
"python-multipart>=0.0.20",
|
|
"pyyaml==6.0.3",
|
|
"redis==6.4.0",
|
|
"rsa==4.9.1",
|
|
"six==1.17.0",
|
|
"sniffio==1.3.1",
|
|
"sqlalchemy==2.0.44",
|
|
"starlette==0.48.0",
|
|
"tomli==2.3.0",
|
|
"typing-extensions==4.15.0",
|
|
"typing-inspection==0.4.2",
|
|
"tzdata==2025.2",
|
|
"uvicorn==0.37.0",
|
|
"uvloop==0.22.1; sys_platform != 'win32'",
|
|
"vine==5.1.0",
|
|
"watchfiles==1.1.1",
|
|
"wcwidth==0.2.14",
|
|
"websockets==15.0.1",
|
|
"requests==2.32.5",
|
|
"elastic-transport==8.17.0",
|
|
"elasticsearch==8.17.0",
|
|
"elasticsearch-dsl==8.17.0",
|
|
"xinference-client==1.11.0",
|
|
"langchain-ollama",
|
|
"chardet==5.2.0",
|
|
"tiktoken==0.12.0",
|
|
"markdown==3.8",
|
|
"langchain>=1.0.3",
|
|
"langchain-openai>=1.0.2",
|
|
"langchain-community>=0.3.31",
|
|
"dashscope>=1.25.0",
|
|
"neo4j>=6.0.3",
|
|
"chonkie>=1.1.2",
|
|
"pandas>=2.3.3",
|
|
"jinja2>=3.1.6",
|
|
"mcp>=1.21.1",
|
|
"concurrent-log-handler>=0.9.28",
|
|
"langchain-mcp-adapters>=0.1.13",
|
|
"pytest>=9.0.1",
|
|
"matplotlib>=3.10.7",
|
|
"langfuse>=3.10.0",
|
|
"beartype==0.22.5",
|
|
"pdfplumber==0.11.7",
|
|
"olefile==0.47",
|
|
"cachetools==6.2.1",
|
|
"ruamel.yaml==0.18.10",
|
|
"strenum==0.4.15",
|
|
"opencv-python==4.10.0.84",
|
|
"numpy>=1.26.0,<2.0.0",
|
|
"huggingface-hub==0.25.2",
|
|
"torch==2.2.2",
|
|
"onnxruntime==1.20.1",
|
|
"shapely==2.1.2",
|
|
"pyclipper==1.3.0.post6",
|
|
"trio==0.32.0",
|
|
"pillow==12.0.0",
|
|
"roman-numbers==1.0.2",
|
|
"word2number==1.1",
|
|
"cn2an==0.5.23",
|
|
"scikit-learn==1.7.2",
|
|
"datrie==0.8.3",
|
|
"hanziconv==0.3.2",
|
|
"nltk==3.9.2",
|
|
"python-pptx==1.0.2",
|
|
"xgboost==3.0.0",
|
|
"pypdf==6.1.3",
|
|
"beautifulsoup4==4.14.2",
|
|
"pandas==2.3.3",
|
|
"openpyxl==3.1.5",
|
|
"python-docx==1.2.0",
|
|
"demjson3==3.0.6",
|
|
"xpinyin==0.7.7",
|
|
"json-repair==0.53.0",
|
|
"jinja2==3.1.6",
|
|
"xxhash==3.6.0",
|
|
"tika==3.1.0",
|
|
"PyPDF2==3.0.1",
|
|
"mammoth==1.11.0",
|
|
"markdownify==1.2.0",
|
|
"flask==3.1.2",
|
|
"html5lib==1.1",
|
|
"jieba>=0.42.1",
|
|
"fastmcp>=2.13.1",
|
|
"pytest-asyncio>=1.3.0",
|
|
"uvicorn>=0.34.0",
|
|
"celery>=5.5.2",
|
|
"simpleeval>=1.0.3",
|
|
"langchain-aws>=1.0.0a1",
|
|
"networkx>=3.4.2",
|
|
"editdistance==0.8.1",
|
|
"graspologic==3.4.5.dev2",
|
|
"markdown-to-json==2.1.1",
|
|
"valkey==6.0.2",
|
|
"python-calamine>=0.4.0",
|
|
"xlrd==2.0.2",
|
|
"deprecated>=1.3.1",
|
|
"oss2>=2.19.1",
|
|
"flower>=2.0.1",
|
|
"aiofiles>=23.0.0",
|
|
"owlready2>=0.46",
|
|
"rdflib>=7.0.0",
|
|
"lxml>=4.9.0",
|
|
"httpx>=0.28.0",
|
|
"modelscope>=1.34.0",
|
|
"python-magic>=0.4.14; sys_platform == 'linux' or sys_platform == 'darwin'",
|
|
"python-magic-bin>=0.4.14; sys_platform=='win32'",
|
|
"volcengine-python-sdk[ark]==5.0.19",
|
|
"pymupdf>=1.27.2.2",
|
|
]
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
python_files = ["test_*.py"]
|
|
python_classes = ["Test*"]
|
|
python_functions = ["test_*"]
|
|
# 使用 anyio 作为异步测试后端
|
|
anyio_backends = ["asyncio"]
|