Changed embedding model to MiniLM-L6 as faster. Compressed embeddings are now int8. General improvements to API mode
ea0dd40
| pandas==2.2.2 | |
| polars==0.20.3 | |
| pyarrow==14.0.2 | |
| openpyxl==3.1.3 | |
| torch==2.4.0 --index-url https://download.pytorch.org/whl/nightly/cu121 | |
| 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 |