Smart-File-Tagger/.gitignore at main · Models-In-Motion/Smart-File-Tagger · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
# OS / editor
.DS_Store
.claude/

# Local generated manifests
FULL_FILE_MANIFEST.txt

# Python
__pycache__/
*.py[cod]
*.pyc
.pytest_cache/
.venv/
venv/
env/
serving/venv/

# Jupyter
.ipynb_checkpoints/

# App/model artifacts
models/
mlruns/
mlflow.db
mlruns_local/
.env
*.pkl
*.pt

# Data working directories
data/raw/
data/processed/
data/courses/
ocw_downloads/
ocw_courses/

# Large local OCW course dumps
18-06sc-fall-2011/
18.01-fall-2006/
5.111sc-fall-2014/
6.006-spring-2020/
6.034-fall-2010/
6.042j-spring-2015/

# Generated datasets and logs (root-level legacy files only)
dataset.parquet
dataset_all.parquet

# Artifacts — track specific files, ignore large/generated ones
artifacts/demo_logs/
artifacts/production_feedback.jsonl

# data/artifacts — ignore all generated data, keep directory via .gitkeep
data/artifacts/*.parquet
data/artifacts/*.jsonl
data/artifacts/*.json
data/artifacts/versions/*
!data/artifacts/versions/v6/
data/artifacts/versions/v6/*
!data/artifacts/versions/v6/train_llm_merged_ops.parquet
!data/artifacts/versions/v6/eval_llm_merged_ops.parquet
data/artifacts/courses/

# Training outputs (keep dirs via training/artifacts/**/.gitkeep; do not commit bundles)
training/artifacts/**/*.joblib
training/artifacts/**/metrics_summary.json
serving/.venv_host/
serving/.venv/
**/.venv*/

# Bind mount data directories — live runtime data, not for git
data/postgres/
data/grafana/
data/nextcloud/
data/mlflow_artifacts/
data/tagger_backup.sql