data_text_search / requirements.txt
seanpedrickcase's picture
Changed embedding model to MiniLM-L6 as faster. Compressed embeddings are now int8. General improvements to API mode
ea0dd40
raw
history blame
No virus
319 Bytes
pandas==2.2.2
polars==0.20.3
pyarrow==14.0.2
openpyxl==3.1.3
torch==2.3.1 --index-url https://download.pytorch.org/whl/cpu
spacy
en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1.tar.gz
gradio
sentence_transformers==3.0.1
lxml==5.2.2
boto3==1.34.103