Russell Ballestrini
aab74dff66
new file: Dockerfile new file: LICENSE new file: README.md new file: app.py new file: docker-compose.yml new file: pyproject.toml new file: requirements.lock
576 lines
13 KiB
Text
576 lines
13 KiB
Text
# generated by rye
|
|
# use `rye lock` or `rye sync` to update this lockfile
|
|
#
|
|
# last locked with the following flags:
|
|
# pre: false
|
|
# features: []
|
|
# all-features: true
|
|
# with-sources: false
|
|
# generate-hashes: false
|
|
# universal: true
|
|
|
|
-e file:.
|
|
# via megaparse
|
|
aiohappyeyeballs==2.4.3
|
|
# via aiohttp
|
|
aiohttp==3.11.5
|
|
# via langchain
|
|
# via langchain-community
|
|
# via llama-index-core
|
|
aiosignal==1.3.1
|
|
# via aiohttp
|
|
annotated-types==0.7.0
|
|
# via pydantic
|
|
anthropic==0.39.0
|
|
# via langchain-anthropic
|
|
antlr4-python3-runtime==4.9.3
|
|
# via omegaconf
|
|
anyio==4.6.2.post1
|
|
# via anthropic
|
|
# via httpx
|
|
# via openai
|
|
# via starlette
|
|
attrs==24.2.0
|
|
# via aiohttp
|
|
backoff==2.2.1
|
|
# via megaparse
|
|
# via unstructured
|
|
beautifulsoup4==4.12.3
|
|
# via unstructured
|
|
cachetools==5.5.0
|
|
# via google-auth
|
|
certifi==2024.8.30
|
|
# via httpcore
|
|
# via httpx
|
|
# via requests
|
|
cffi==1.17.1 ; platform_python_implementation != 'PyPy'
|
|
# via cryptography
|
|
chardet==5.2.0
|
|
# via unstructured
|
|
charset-normalizer==3.4.0
|
|
# via pdfminer-six
|
|
# via requests
|
|
click==8.1.7
|
|
# via llama-parse
|
|
# via nltk
|
|
# via python-oxmsg
|
|
# via uvicorn
|
|
colorama==0.4.6 ; sys_platform == 'win32' or platform_system == 'Windows'
|
|
# via click
|
|
# via loguru
|
|
# via tqdm
|
|
coloredlogs==15.0.1
|
|
# via onnxruntime
|
|
contourpy==1.3.1
|
|
# via matplotlib
|
|
cryptography==43.0.3
|
|
# via pdfminer-six
|
|
# via unstructured-client
|
|
cycler==0.12.1
|
|
# via matplotlib
|
|
dataclasses-json==0.6.7
|
|
# via langchain-community
|
|
# via llama-index-core
|
|
# via unstructured
|
|
defusedxml==0.7.1
|
|
# via langchain-anthropic
|
|
deprecated==1.2.15
|
|
# via llama-index-core
|
|
# via pikepdf
|
|
dirtyjson==1.0.8
|
|
# via llama-index-core
|
|
distro==1.9.0
|
|
# via anthropic
|
|
# via openai
|
|
effdet==0.4.1
|
|
# via unstructured
|
|
emoji==2.14.0
|
|
# via unstructured
|
|
et-xmlfile==2.0.0
|
|
# via openpyxl
|
|
eval-type-backport==0.2.0
|
|
# via unstructured-client
|
|
fastapi==0.115.5
|
|
# via megaparse
|
|
filelock==3.16.1
|
|
# via huggingface-hub
|
|
# via torch
|
|
# via transformers
|
|
# via triton
|
|
filetype==1.2.0
|
|
# via llama-index-core
|
|
# via unstructured
|
|
flatbuffers==24.3.25
|
|
# via onnxruntime
|
|
fonttools==4.55.0
|
|
# via matplotlib
|
|
frozenlist==1.5.0
|
|
# via aiohttp
|
|
# via aiosignal
|
|
fsspec==2024.10.0
|
|
# via huggingface-hub
|
|
# via llama-index-core
|
|
# via torch
|
|
google-api-core==2.23.0
|
|
# via google-cloud-vision
|
|
google-auth==2.36.0
|
|
# via google-api-core
|
|
# via google-cloud-vision
|
|
google-cloud-vision==3.8.1
|
|
# via unstructured
|
|
googleapis-common-protos==1.66.0
|
|
# via google-api-core
|
|
# via grpcio-status
|
|
greenlet==3.1.1
|
|
# via playwright
|
|
# via sqlalchemy
|
|
grpcio==1.68.0
|
|
# via google-api-core
|
|
# via grpcio-status
|
|
grpcio-status==1.68.0
|
|
# via google-api-core
|
|
h11==0.14.0
|
|
# via httpcore
|
|
# via uvicorn
|
|
httpcore==1.0.7
|
|
# via httpx
|
|
httpx==0.27.2
|
|
# via anthropic
|
|
# via langsmith
|
|
# via llama-index-core
|
|
# via megaparse-sdk
|
|
# via openai
|
|
# via unstructured-client
|
|
huggingface-hub==0.26.2
|
|
# via timm
|
|
# via tokenizers
|
|
# via transformers
|
|
# via unstructured-inference
|
|
humanfriendly==10.0
|
|
# via coloredlogs
|
|
idna==3.10
|
|
# via anyio
|
|
# via httpx
|
|
# via requests
|
|
# via yarl
|
|
iopath==0.1.10
|
|
# via layoutparser
|
|
jinja2==3.1.4
|
|
# via torch
|
|
jiter==0.7.1
|
|
# via anthropic
|
|
# via openai
|
|
joblib==1.4.2
|
|
# via nltk
|
|
jsonpatch==1.33
|
|
# via langchain-core
|
|
jsonpath-python==1.0.6
|
|
# via unstructured-client
|
|
jsonpointer==3.0.0
|
|
# via jsonpatch
|
|
kiwisolver==1.4.7
|
|
# via matplotlib
|
|
langchain==0.2.17
|
|
# via langchain-community
|
|
# via megaparse
|
|
langchain-anthropic==0.1.23
|
|
# via megaparse
|
|
langchain-community==0.2.19
|
|
# via megaparse
|
|
langchain-core==0.2.43
|
|
# via langchain
|
|
# via langchain-anthropic
|
|
# via langchain-community
|
|
# via langchain-openai
|
|
# via langchain-text-splitters
|
|
# via megaparse
|
|
langchain-openai==0.1.25
|
|
# via megaparse
|
|
langchain-text-splitters==0.2.4
|
|
# via langchain
|
|
langdetect==1.0.9
|
|
# via unstructured
|
|
langsmith==0.1.143
|
|
# via langchain
|
|
# via langchain-community
|
|
# via langchain-core
|
|
layoutparser==0.3.4
|
|
# via unstructured-inference
|
|
llama-index-core==0.12.0
|
|
# via llama-parse
|
|
llama-parse==0.5.14
|
|
# via megaparse
|
|
loguru==0.7.2
|
|
# via megaparse-sdk
|
|
lxml==5.3.0
|
|
# via pikepdf
|
|
# via python-docx
|
|
# via python-pptx
|
|
# via unstructured
|
|
markdown==3.7
|
|
# via unstructured
|
|
markupsafe==3.0.2
|
|
# via jinja2
|
|
marshmallow==3.23.1
|
|
# via dataclasses-json
|
|
matplotlib==3.9.2
|
|
# via pycocotools
|
|
# via unstructured-inference
|
|
mpmath==1.3.0
|
|
# via sympy
|
|
multidict==6.1.0
|
|
# via aiohttp
|
|
# via yarl
|
|
mypy-extensions==1.0.0
|
|
# via typing-inspect
|
|
nats-py==2.9.0
|
|
# via megaparse
|
|
# via megaparse-sdk
|
|
nest-asyncio==1.6.0
|
|
# via llama-index-core
|
|
# via unstructured-client
|
|
networkx==3.4.2
|
|
# via llama-index-core
|
|
# via torch
|
|
# via unstructured
|
|
nltk==3.9.1
|
|
# via llama-index-core
|
|
# via unstructured
|
|
numpy==1.26.4
|
|
# via contourpy
|
|
# via langchain
|
|
# via langchain-community
|
|
# via layoutparser
|
|
# via llama-index-core
|
|
# via matplotlib
|
|
# via megaparse
|
|
# via onnx
|
|
# via onnxruntime
|
|
# via opencv-python
|
|
# via pandas
|
|
# via pycocotools
|
|
# via scipy
|
|
# via torchvision
|
|
# via transformers
|
|
# via unstructured
|
|
nvidia-cublas-cu12==12.4.5.8 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via nvidia-cudnn-cu12
|
|
# via nvidia-cusolver-cu12
|
|
# via torch
|
|
nvidia-cuda-cupti-cu12==12.4.127 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
nvidia-cuda-nvrtc-cu12==12.4.127 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
nvidia-cuda-runtime-cu12==12.4.127 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
nvidia-cudnn-cu12==9.1.0.70 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
nvidia-cufft-cu12==11.2.1.3 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
nvidia-curand-cu12==10.3.5.147 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
nvidia-cusolver-cu12==11.6.1.9 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
nvidia-cusparse-cu12==12.3.1.170 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via nvidia-cusolver-cu12
|
|
# via torch
|
|
nvidia-nccl-cu12==2.21.5 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
nvidia-nvjitlink-cu12==12.4.127 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via nvidia-cufft-cu12
|
|
# via nvidia-cusolver-cu12
|
|
# via nvidia-cusparse-cu12
|
|
# via torch
|
|
nvidia-nvtx-cu12==12.4.127 ; platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
olefile==0.47
|
|
# via python-oxmsg
|
|
omegaconf==2.3.0
|
|
# via effdet
|
|
onnx==1.17.0
|
|
# via unstructured
|
|
# via unstructured-inference
|
|
onnxruntime==1.20.0
|
|
# via unstructured-inference
|
|
openai==1.54.5
|
|
# via langchain-openai
|
|
opencv-python==4.10.0.84
|
|
# via layoutparser
|
|
# via unstructured-inference
|
|
openpyxl==3.1.5
|
|
# via unstructured
|
|
orjson==3.10.11
|
|
# via langsmith
|
|
packaging==24.2
|
|
# via huggingface-hub
|
|
# via langchain-core
|
|
# via marshmallow
|
|
# via matplotlib
|
|
# via megaparse-monorepo
|
|
# via onnxruntime
|
|
# via pikepdf
|
|
# via pytesseract
|
|
# via transformers
|
|
# via unstructured-pytesseract
|
|
pandas==2.2.3
|
|
# via layoutparser
|
|
# via unstructured
|
|
pdf2image==1.17.0
|
|
# via layoutparser
|
|
# via unstructured
|
|
pdfminer-six==20231228
|
|
# via pdfplumber
|
|
# via unstructured
|
|
pdfplumber==0.11.4
|
|
# via layoutparser
|
|
# via megaparse
|
|
pikepdf==9.4.2
|
|
# via unstructured
|
|
pillow==11.0.0
|
|
# via layoutparser
|
|
# via llama-index-core
|
|
# via matplotlib
|
|
# via pdf2image
|
|
# via pdfplumber
|
|
# via pikepdf
|
|
# via pillow-heif
|
|
# via pytesseract
|
|
# via python-pptx
|
|
# via torchvision
|
|
# via unstructured-pytesseract
|
|
pillow-heif==0.20.0
|
|
# via unstructured
|
|
playwright==1.48.0
|
|
# via megaparse
|
|
portalocker==3.0.0
|
|
# via iopath
|
|
propcache==0.2.0
|
|
# via aiohttp
|
|
# via yarl
|
|
proto-plus==1.25.0
|
|
# via google-api-core
|
|
# via google-cloud-vision
|
|
protobuf==5.28.3
|
|
# via google-api-core
|
|
# via google-cloud-vision
|
|
# via googleapis-common-protos
|
|
# via grpcio-status
|
|
# via onnx
|
|
# via onnxruntime
|
|
# via proto-plus
|
|
psutil==6.1.0
|
|
# via megaparse
|
|
# via megaparse-sdk
|
|
# via unstructured
|
|
pyasn1==0.6.1
|
|
# via pyasn1-modules
|
|
# via rsa
|
|
pyasn1-modules==0.4.1
|
|
# via google-auth
|
|
pycocotools==2.0.8
|
|
# via effdet
|
|
pycparser==2.22 ; platform_python_implementation != 'PyPy'
|
|
# via cffi
|
|
pycryptodome==3.21.0
|
|
# via megaparse
|
|
# via megaparse-sdk
|
|
pydantic==2.9.2
|
|
# via anthropic
|
|
# via fastapi
|
|
# via langchain
|
|
# via langchain-core
|
|
# via langsmith
|
|
# via llama-index-core
|
|
# via openai
|
|
# via pydantic-settings
|
|
# via unstructured-client
|
|
pydantic-core==2.23.4
|
|
# via pydantic
|
|
pydantic-settings==2.6.1
|
|
# via megaparse
|
|
pyee==12.0.0
|
|
# via playwright
|
|
pypandoc==1.14
|
|
# via unstructured
|
|
pyparsing==3.2.0
|
|
# via matplotlib
|
|
pypdf==5.1.0
|
|
# via megaparse
|
|
# via unstructured
|
|
# via unstructured-client
|
|
pypdfium2==4.30.0
|
|
# via pdfplumber
|
|
pyreadline3==3.5.4 ; sys_platform == 'win32'
|
|
# via humanfriendly
|
|
pytesseract==0.3.13
|
|
# via unstructured
|
|
python-dateutil==2.8.2
|
|
# via matplotlib
|
|
# via pandas
|
|
# via unstructured-client
|
|
python-docx==1.1.2
|
|
# via unstructured
|
|
python-dotenv==1.0.1
|
|
# via megaparse
|
|
# via megaparse-sdk
|
|
# via pydantic-settings
|
|
python-iso639==2024.10.22
|
|
# via unstructured
|
|
python-magic==0.4.27
|
|
# via megaparse
|
|
# via unstructured
|
|
python-multipart==0.0.17
|
|
# via unstructured-inference
|
|
python-oxmsg==0.0.1
|
|
# via unstructured
|
|
python-pptx==0.6.23
|
|
# via unstructured
|
|
pytz==2024.2
|
|
# via pandas
|
|
pywin32==308 ; platform_system == 'Windows'
|
|
# via portalocker
|
|
pyyaml==6.0.2
|
|
# via huggingface-hub
|
|
# via langchain
|
|
# via langchain-community
|
|
# via langchain-core
|
|
# via layoutparser
|
|
# via llama-index-core
|
|
# via omegaconf
|
|
# via timm
|
|
# via transformers
|
|
rapidfuzz==3.10.1
|
|
# via unstructured
|
|
# via unstructured-inference
|
|
ratelimit==2.2.1
|
|
# via megaparse
|
|
regex==2024.11.6
|
|
# via nltk
|
|
# via tiktoken
|
|
# via transformers
|
|
requests==2.32.3
|
|
# via google-api-core
|
|
# via huggingface-hub
|
|
# via langchain
|
|
# via langchain-community
|
|
# via langsmith
|
|
# via llama-index-core
|
|
# via requests-toolbelt
|
|
# via tiktoken
|
|
# via transformers
|
|
# via unstructured
|
|
requests-toolbelt==1.0.0
|
|
# via langsmith
|
|
# via unstructured-client
|
|
rsa==4.9
|
|
# via google-auth
|
|
safetensors==0.4.5
|
|
# via timm
|
|
# via transformers
|
|
scipy==1.14.1
|
|
# via layoutparser
|
|
setuptools==75.5.0
|
|
# via torch
|
|
six==1.16.0
|
|
# via langdetect
|
|
# via python-dateutil
|
|
sniffio==1.3.1
|
|
# via anthropic
|
|
# via anyio
|
|
# via httpx
|
|
# via openai
|
|
soupsieve==2.6
|
|
# via beautifulsoup4
|
|
sqlalchemy==2.0.36
|
|
# via langchain
|
|
# via langchain-community
|
|
# via llama-index-core
|
|
starlette==0.41.3
|
|
# via fastapi
|
|
sympy==1.13.1
|
|
# via onnxruntime
|
|
# via torch
|
|
tabulate==0.9.0
|
|
# via unstructured
|
|
tenacity==8.5.0
|
|
# via langchain
|
|
# via langchain-community
|
|
# via langchain-core
|
|
# via llama-index-core
|
|
tiktoken==0.8.0
|
|
# via langchain-openai
|
|
# via llama-index-core
|
|
timm==1.0.11
|
|
# via effdet
|
|
# via unstructured-inference
|
|
tokenizers==0.20.3
|
|
# via transformers
|
|
torch==2.5.1
|
|
# via effdet
|
|
# via timm
|
|
# via torchvision
|
|
# via unstructured-inference
|
|
torchvision==0.20.1
|
|
# via effdet
|
|
# via timm
|
|
tqdm==4.67.0
|
|
# via huggingface-hub
|
|
# via iopath
|
|
# via llama-index-core
|
|
# via nltk
|
|
# via openai
|
|
# via transformers
|
|
# via unstructured
|
|
transformers==4.46.3
|
|
# via unstructured-inference
|
|
triton==3.1.0 ; python_full_version < '3.13' and platform_machine == 'x86_64' and platform_system == 'Linux'
|
|
# via torch
|
|
typing-extensions==4.12.2
|
|
# via anthropic
|
|
# via fastapi
|
|
# via huggingface-hub
|
|
# via iopath
|
|
# via langchain-core
|
|
# via llama-index-core
|
|
# via openai
|
|
# via pydantic
|
|
# via pydantic-core
|
|
# via pyee
|
|
# via python-docx
|
|
# via python-oxmsg
|
|
# via sqlalchemy
|
|
# via torch
|
|
# via typing-inspect
|
|
# via unstructured
|
|
typing-inspect==0.9.0
|
|
# via dataclasses-json
|
|
# via llama-index-core
|
|
# via unstructured-client
|
|
tzdata==2024.2
|
|
# via pandas
|
|
unstructured==0.15.0
|
|
# via megaparse
|
|
unstructured-client==0.27.0
|
|
# via unstructured
|
|
unstructured-inference==0.7.36
|
|
# via unstructured
|
|
unstructured-pytesseract==0.3.13
|
|
# via unstructured
|
|
urllib3==2.2.3
|
|
# via requests
|
|
uvicorn==0.32.0
|
|
# via megaparse
|
|
uvloop==0.21.0
|
|
# via megaparse
|
|
win32-setctime==1.1.0 ; sys_platform == 'win32'
|
|
# via loguru
|
|
wrapt==1.16.0
|
|
# via deprecated
|
|
# via llama-index-core
|
|
# via unstructured
|
|
xlrd==2.0.1
|
|
# via unstructured
|
|
xlsxwriter==3.2.0
|
|
# via python-pptx
|
|
yarl==1.17.2
|
|
# via aiohttp
|