Metadata-Version: 2.1
Name: dart-trec-learner
Version: 3.1.0
Summary: T-REC learner libs
Home-page: https://github.sec.samsung.net/SOL/dart-trec-learner
Author: SIDIA
Author-email: sidia@sidia.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Requires-Python: ~=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: accelerate (==1.1.0)
Requires-Dist: apscheduler (==3.10.1)
Requires-Dist: boto3 (==1.34.0)
Requires-Dist: dart-trec-commons (==2.8.3)
Requires-Dist: datasets (==3.1.0)
Requires-Dist: diffusers (==0.31.0)
Requires-Dist: evaluate (==0.4.3)
Requires-Dist: isort (==5.13.2)
Requires-Dist: loguru (==0.7.2)
Requires-Dist: pynvml (==11.5.3)
Requires-Dist: python-dotenv (==1.0.1)
Requires-Dist: scikit-learn (==1.5.2)
Requires-Dist: tabulate (==0.9.0)
Requires-Dist: torch (==2.3.0)
Requires-Dist: torchvision (==0.18.0)
Requires-Dist: tqdm (==4.67.0)
Requires-Dist: transformers (==4.46.3)
Requires-Dist: typer (==0.13.0)
Requires-Dist: tzlocal (==2.1)

# TREC Learner

For production config, set ENV to production

## How to Run

1. Install requeriments
    - `python3 -m venv .venv`
    - `source ./.venv/bin/activate`
    - `pip install -r requirements.txt`
   
2. Config parameters
    - `cp .env.example .env`
    - `cp pytest.ini.example pytest.ini`
    - fill .env and pytest.ini

3. Run learner
    - `./run.sh`

## How to Setup

All application variables are exposed in `src/config.py`. Container variables are exposed in `.env`:

- Learner Options:

    | Option | Description |
    |--------|-------------|
    | LEARNER_DAYS_INTERVAL | Learner interval in days |
    | LEARNER_ROOT_MODEL_DIR | Temporary root dir used during trainning |
    | LEARNER_MODEL_DIR | Temporary dir used store model files |

- Connection Options:

    | Option | Description |
    |--------|-------------|
    | MONGODB_URI | Mongo URI (without database name) |
    | MONGODB_DATABASE | Mongo database with PLM data |
    | MONGODB_COLLECTION | Mongo collection with issue-document data |
    | MINIO_HOST | MinIO host (without http://) |
    | MINIO_ACCESS_KEY | MinIO Key |
    | MINIO_SECRET_KEY | MinIO Secret |
    | MINIO_RECOMMENDER_BUCKET | MinIO recommender bucket |

- Scheduler Options:

    | Option | Description |
    |--------|-------------|
    | JOB_FREQUENCY | Frequency to run job _(seconds interval for dev mode)_ |
    | JOB_FREQUENCY | Frequency to run job _(hour of day for production mode)_ |


