# Python-generated files
__pycache__/
*.py[oc]
build/
dist/
wheels/
*.egg-info

# Virtual environments
.venv

# Environment files
.env

# LangGraph
.langgraph_api

# =============================================================================
# ML MODEL ARTIFACTS (Large files - don't push to Git)
# =============================================================================

# Trained model weights (large binary files)
*.h5
*.hdf5
*.joblib
*.pkl
*.pickle
*.pt
*.pth
*.onnx
*.pb

# Model output directories
models/*/artifacts/models/
models/*/output/
models/*/models_cache/
models/*/checkpoints/

# Airflow local state
models/*/.astro/

# MLflow artifacts (tracked separately)
mlruns/
mlartifacts/

# =============================================================================
# DATA FILES (Can be large)
# =============================================================================
data/
datasets/

# Database files
*.db
*.sqlite
*.sqlite3

# ChromaDB persistence (can be large)
chroma_db/

# =============================================================================
# KEEP THESE (source code, configs)
# =============================================================================
# The models/ folders themselves ARE tracked for:
# - main.py, src/, dags/ (pipeline code)
# - requirements.txt, setup.py (dependencies)
# - data_schema/ (validation configs)
# - README.md (documentation)