.gitignore

# ========================================
# RAG System - Git Ignore Configuration
# ========================================

# 🔐 SECURITY - API Keys and Secrets
# CRITICAL: Never commit these files!
.env
.env.local
.env.development
.env.test
.env.production
.env.staging
*.key
*.pem
*.p12
*.pfx
config/secrets.json
secrets/

# 📊 EXPERIMENT RESULTS AND LOGS
# These are generated outputs that change frequently
regression_test_results/
evaluation_results.json
evaluation_report.md
EVALUATION_COMPARISON.md
RATE_LIMITING_NOTES.md
*.log
*.out
logs/
results/
experiment_logs/
performance_metrics/

# 💾 DATABASE FILES
# ChromaDB and other database files (large and regeneratable)
*.sqlite3
*.db
chroma.sqlite3
data/chroma_db/
embedding_experiment_db/
generation_experiment_db/
retrieval_experiment_db/
system_optimization_db/
test_chroma_db_*/
*.chroma/
vector_db/
database/
db_backups/
chroma_db/

# ChromaDB specific files and directories
**/chroma.sqlite3
**/*chroma_db*/
*.bin
*.index
*.hnsw

# 🐍 PYTHON SPECIFIC
# Standard Python gitignore patterns
__pycache__/
*.py[cod]
*$py.class
*.so
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
pip-wheel-metadata/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST

# 🧪 TESTING AND COVERAGE
# Test outputs and coverage reports
.pytest_cache/
.coverage
htmlcov/
.tox/
.nox/
.coverage.*
coverage.xml
*.cover
*.py,cover
.hypothesis/
test_results/
test_outputs/
pytest_report.html

# 📓 JUPYTER NOTEBOOKS
# Notebook checkpoints and outputs
.ipynb_checkpoints/
*/.ipynb_checkpoints/*
*.ipynb_checkpoints
Untitled*.ipynb

# 🔧 DEVELOPMENT TOOLS
# IDE and editor files
.vscode/settings.json
.vscode/launch.json
.vscode/.ropeproject
.idea/
*.swp
*.swo
*~
.DS_Store
Thumbs.db

# 🐳 CONTAINERS AND DEPLOYMENT
# Docker and deployment artifacts
.dockerignore
Dockerfile.*
docker-compose.override.yml
.docker/
kubernetes/

# 📦 DEPENDENCIES AND VIRTUAL ENVIRONMENTS
# Virtual environments (if locally created)
venv/
env/
ENV/
env.bak/
venv.bak/
.venv/
.conda/
conda-meta/

# 🚀 DEPLOYMENT AND PRODUCTION
# Production configuration and builds
.vercel/
.netlify/
.aws/
terraform.tfstate*
.terraform/

# 📈 MACHINE LEARNING SPECIFIC
# Model files, datasets, and ML artifacts
models/
*.model
*.pkl
*.pickle
*.joblib
*.pt
*.pth
*.onnx
*.h5
*.hdf5
checkpoints/
wandb/
mlruns/
.mlflow/
data/raw/
data/processed/
data/interim/
*.parquet
*.feather

# 🧹 TEMPORARY FILES
# System and application temporary files
*.tmp
*.temp
*.cache
.cache/
.temp/
.tmp/
debug_*.py
temp_*.py
scratch_*.py
# Temporary test files (but not in tests/ directory)
test_*.py
!tests/test_*.py
# Temporary demo files (but not legitimate demos in project directories)
demo_*.py
!regression_testing/demo_*.py

# 📋 DOCUMENTATION BUILDS
# Generated documentation
docs/_build/
docs/build/
site/
.mkdocs.yml.backup

# 🌐 WEB ASSETS
# Frontend build artifacts (if any)
node_modules/
npm-debug.log*
yarn-debug.log*
yarn-error.log*
.npm
.yarn-integrity
static/build/
static/dist/

# ⚙️ CONFIGURATION OVERRIDES
# Local configuration overrides
config/local.py
config/development.json
config/production.json
local_settings.py
instance/

# 📱 MOBILE AND PLATFORM SPECIFIC
# Platform specific files
ehthumbs.db
ehthumbs_vista.db
Desktop.ini
.DS_Store?
._*
.Spotlight-V100
.Trashes
Icon?

# 🔄 BACKUP FILES
# Backup and recovery files
*.bak
*.backup
*.old
*.orig
*~
.#*
#*#

# =======================================
# PROJECT SPECIFIC EXCLUSIONS
# =======================================

# RAG Pipeline Specific
chunking_results/
embedding_results/
generation_results/
retrieval_results/
optimization_results/

# Analysis and Debug Files
analyze_*.py
debug_*.py
cleanup_*.py
limited_evaluation.py
dependency_audit.py

# Experiment Database Backups
experiment_backups/
vector_backups/