requires.txt

numpy<2.0.0
datasets
scipy
tqdm
transformers<4.54.0
math_verify
word2number
accelerate
rapidfuzz
colorlog
appdirs
datasketch
modelscope
addict
pytest
rich
docstring_parser
pydantic
nltk
colorama
gradio>5
json5
tiktoken
func_timeout
sqlglot
pymysql
fasttext-wheel
langkit
openai
sentencepiece
datasketch
presidio_analyzer[transformers]
presidio_anonymizer
vendi-score==0.0.3
google-api-core
google-api-python-client
evaluate
contractions
symspellpy
simhash
chonkie
trafilatura
lxml_html_clean
pymupdf
httpx[socks]
cloudpickle
fastapi
httpx
pandas
psutil
pyfiglet
pyyaml
requests
termcolor
uvicorn
sseclient-py
librosa
soundfile
google-cloud-aiplatform>=1.55
google-cloud-bigquery
google-genai
gcsfs

[audio]
librosa
soundfile

[eval]
vllm<0.9.2,>=0.7.0

[kbc]
vllm==0.6.3
mineru[pipeline]==2.0.6

[litellm]
litellm<2.0.0,>=1.70.0

[mineru]
mineru[all]
numpy<2.0.0,>=1.24
sglang[all]>=0.4.8
pypdf
reportlab

[myscale]
clickhouse-driver

[pdf2model]
llamafactory[metrics,torch]>=0.9.0
vllm<0.9.2,>=0.7.0
numpy<2.0.0,>=1.24
mineru[pipeline]
mineru-vl-utils

[rag]
lightrag-hku
asyncio

[sglang]
sglang[all]

[vectorsql]
sqlite-vec
sqlite-lembed
sentence_transformers

[vllm]
vllm<=0.9.2,>=0.7.0
numpy<2.0.0

[vllm07]
vllm<0.8
numpy<2.0.0

[vllm08]
vllm<0.9