Refactor unit mapping in prediction process by replacing UnitMapper with UnitSimilarityMapper for improved similarity calculations and error handling.

Update model to cl-nagoya-sup-simcse-ja-nss-v1_0_8_4, add new standard name mapping functionality in prediction process, and enhance data loading in sentence transformer service.

Update cached embeddings with new sizes, enhance prediction output by adding standard and aggregate unit columns, and refactor loading logic in the sentence transformer service for improved error handling.

Remove outdated anchor name sentence embeddings file, update cached embeddings with new sizes, and refactor sub subject and name mapping in the prediction process.

Refactor prediction process by removing debug print statements and suppressing pandas warnings globally in the sentence transformer service.

Enhance prediction process by adding missing columns with defaults, ensuring correct data types, and improving error handling. Update cached embeddings with new size.

Update Dockerfile to clone from the 'develop' branch, update cached embeddings with new sizes, and ensure required columns in prediction output are handled correctly.

Update model to cl-nagoya-sup-simcse-ja-nss-v1_0_8_3, add new data files, and enhance startup process with directory creation and model loading.

token store

simple authen

update confirm

fix raw predict

upload new model

change model

add similarity score

support 2 new endpoints

remove ファイル名

change service

update run time

change model

add new column to keep

change logic from sentence name to representative name

update project structure