requirements.txt

# basics
setuptools
wheel
# PyTorch
# Temp. disabled the next line as it gets currently resolved to https://download.pytorch.org/whl/rocm3.8/torch-1.7.1%2Brocm3.8-cp38-cp38-linux_x86_64.whl
# --find-links=https://download.pytorch.org/whl/torch_stable.html
torch>1.5,<1.11
# progress bars in model download and training scripts
tqdm
# Used for downloading models over HTTP
requests
# Scipy & sklearn for stats in run_classifier
scipy>=1.3.2
sklearn
# Metrics or logging related
seqeval
mlflow<=1.13.1
# huggingface repository
transformers==4.13.0
# pickle extension for (de-)serialization
dill
# Inference with ONNX models. Install onnxruntime-gpu for Inference on GPUs
# onnxruntime
# onnxruntime_tools
psutil
# haystack
fastapi
uvicorn
gunicorn
pandas
psycopg2-binary; sys_platform != 'win32' and sys_platform != 'cygwin'
elasticsearch>=7.7,<=7.10
elastic-apm
tox
coverage
langdetect # for PDF conversions
# for PDF conversions using OCR
pytesseract==0.3.7 
pillow==8.3.2
pdf2image==1.14.0
sentence-transformers>=0.4.0
python-multipart
python-docx
sqlalchemy>=1.4.2
sqlalchemy_utils
# for using FAISS with GPUs, install faiss-gpu
faiss-cpu>=1.6.3
tika
uvloop==0.14; sys_platform != 'win32' and sys_platform != 'cygwin'
httptools
nltk
more_itertools
networkx
# Refer milvus version support matrix at https://github.com/milvus-io/pymilvus#install-pymilvus
# For milvus 2.x version use this library `pymilvus===2.0.0rc6`
pymilvus
# Optional: For crawling
#selenium
#webdriver-manager
SPARQLWrapper
mmh3
weaviate-client==2.5.0
ray==1.5.0
dataclasses-json
quantulum3
azure-ai-formrecognizer==3.2.0b2