sbt-idp/cope2n-ai-fi/TODO.md

26 lines
1.5 KiB
Markdown
Executable File

## Bring abs path to relative
- [x] save_dir `Kie_Invoice_AP/prediction_sap.py:18`
- [x] detector `Kie_Invoice_AP/AnyKey_Value/ocr-engine/settings.yml` [_fixed_](#refactor)
- [x] rotator_version `Kie_Invoice_AP/AnyKey_Value/ocr-engine/settings.yml` [_fixed_](#refactor)
- [x] cfg `Kie_Invoice_AP/prediction_fi.py`
- [x] weight `Kie_Invoice_AP/prediction_fi.py`
- [x] save_dir `Kie_Invoice_AP/prediction_fi.py:18`
## Bring abs path to .env
- [x] CELERY_BROKER:
- [ ] SAP_KIE_MODEL: `Kie_Invoice_AP/prediction_sap.py:20` [_NEED_REFACTOR_](#refactor)
- [ ] FI_KIE_MODEL: `Kie_Invoice_AP/prediction_fi.py:20` [_NEED_REFACTOR_](#refactor)
## Possible logic confict
### Refactor
- [ ] Each model should be loaded in a docker container and serve as a service
- [ ] Some files (weights, ...) should be mounted in container in a format for endurability
- [ ] `Kie_Invoice_AP/prediction_fi.py` and `Kie_Invoice_AP/prediction_fi.py` should be merged into a single file as it shared resources with different logic
- [ ] `Kie_Invoice_AP/prediction.py` seems to be the base function, this should act as a proxy which import all other `predict_{anything else}` functions
- [ ] There should be a unique folder to keep all models with different versions then mount as /models in container. Currently, `fi` is loading from `/models/Kie_invoice_fi` while `sap` is loading from `Kie_Invoice_AP/AnyKey_Value/experiments/key_value_understanding-20231003-171748`. Another model weight is at `sdsvtd/hub` for unknown reason
- [ ] Env variables should have its description in README