numpy<2.0.0 datasets scipy #torch #torchvision #torchaudio 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 # text2sql func_timeout sqlglot pymysql # general text 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 # knowledge base cleaning chonkie trafilatura lxml_html_clean pymupdf httpx[socks] # dataflow agent cloudpickle fastapi httpx pandas psutil pyfiglet pyyaml requests termcolor uvicorn sseclient-py # speech librosa soundfile # map visualize # matplotlib - removed as no longer needed # google vertex ai google-cloud-aiplatform>=1.55 google-cloud-bigquery google-genai gcsfs
