Feat/general-debug

.dockerignore

@@ -1,43 +1,98 @@
-# Escludi file di sistema e cache Python
+# ==============================================================================
+# Docker Build Context Exclusions - LegalAIze
+# ==============================================================================
+# Files and directories excluded from Docker build context to reduce image size
+# and prevent sensitive data from being included in containers.
+# ==============================================================================
+
+# ------------------------------------------------------------------------------
+# Python Runtime & Cache
+# ------------------------------------------------------------------------------
 __pycache__/
 *.py[cod]
 *$py.class
 *.so
 .Python
+
+# Virtual Environments
 env/
 venv/
 ENV/
 .venv
+backend_venv/
+frontend_venv/
 
-# Escludi file IDE
+# ------------------------------------------------------------------------------
+# Development Tools & IDEs
+# ------------------------------------------------------------------------------
 .vscode/
 .idea/
 *.swp
 *.swo
+*.swn
 
-# Escludi file OS
+# ------------------------------------------------------------------------------
+# OS-Specific Files
+# ------------------------------------------------------------------------------
 .DS_Store
 Thumbs.db
+desktop.ini
 
-# SECURITY: EXCLUDE KEYS AND SECRETS
+# ------------------------------------------------------------------------------
+# Security & Credentials (NEVER include in images)
+# ------------------------------------------------------------------------------
 .env
 dagshub_token.txt
-*.log
+*.pem
+*.key
+*.crt
+secrets/
 
-# Exclude data, models, output, DVC, git, etc.
+# ------------------------------------------------------------------------------
+# Data & Model Artifacts (too large for container images)
+# ------------------------------------------------------------------------------
 data/
 models/
 mlruns/
 mlartifacts/
-.dvc/
+metrics/
+output/
+tmp/
+logs/
+
+# ------------------------------------------------------------------------------
+# Version Control & Experiment Tracking
+# ------------------------------------------------------------------------------
 .git/
+.dvc/
 *.dvc
+.gitignore
+.dockerignore
+
+# ------------------------------------------------------------------------------
+# Archives & Large Files
+# ------------------------------------------------------------------------------
 *.gz
 *.zip
 *.tar
 *.tar.gz
+*.rar
+*.7z
+
+# ------------------------------------------------------------------------------
+# Jupyter Notebooks & Documentation
+# ------------------------------------------------------------------------------
 *.ipynb
-output/
-tmp/
-logs/
-notebooks/
+notebooks/
+docs/
+*.md
+!README.md
+
+# ------------------------------------------------------------------------------
+# Test & CI/CD
+# ------------------------------------------------------------------------------
+tests/
+.pytest_cache/
+.coverage
+htmlcov/
+.github/

.env.example

@@ -1,6 +1,6 @@
 # MLflow/DagsHub Configuration Examples
 
-# Use one of the following configurations for MLflow tracking.
+# Use ONLY ONE of the following configurations for MLflow tracking.
 
 # 1. Local MLflow tracking (recommended for most users)
 MLFLOW_TRACKING_URI=http://localhost:5000

.github/scripts/check_and_issue.py

@@ -12,19 +12,15 @@
 # List of actually used metrics in rag_eval.json
 metric_keys = [
     "weighted_mae_score",
-    "mean_groundedness_score",
     "mean_faithfulness_score",
-    "mean_note_similarity",
     "ragas_correctness",
     "ragas_answer_relevancy"
 ]
 
 # Default thresholds (add more if needed)
 default_thresholds = {
     "weighted_mae_score": ("max", float(os.getenv("THRESHOLD_MAE", "1.0"))),
-    "mean_groundedness_score": ("min", float(os.getenv("THRESHOLD_GROUNDEDNESS", "0.5"))),
     "mean_faithfulness_score": ("min", float(os.getenv("THRESHOLD_FAITHFULNESS", "0.5"))),
-    "mean_note_similarity": ("min", float(os.getenv("THRESHOLD_NOTE_SIMILARITY", "0.35"))),
     "ragas_correctness": ("min", 0.5),
     "ragas_answer_relevancy": ("min", 0.5)
     # You can add more custom thresholds here

.gitignore

@@ -1,62 +1,137 @@
-# Python
+# ==============================================================================
+# LegalAIze - Git Ignore Rules
+# ==============================================================================
+# Files and directories excluded from version control to keep the repository
+# clean, secure, and focused on source code.
+# ==============================================================================
+
+# ------------------------------------------------------------------------------
+# Python Runtime & Cache
+# ------------------------------------------------------------------------------
 __pycache__/
 *.py[cod]
 *$py.class
 *.so
+*.pyo
+*.pyd
 .Python
+*.egg
+*.egg-info/
+dist/
+build/
+
+# Virtual Environments
 env/
 venv/
-backend/backend_venv/
-frontend/frontend_venv/
 ENV/
 .venv
+backend/backend_venv/
+frontend/frontend_venv/
+
+# Jupyter Notebooks
+.ipynb_checkpoints/
+*.ipynb
 
-# MLflow
+# ------------------------------------------------------------------------------
+# Machine Learning & Experiment Tracking
+# ------------------------------------------------------------------------------
+# MLflow experiment tracking
 mlruns/
 mlartifacts/
 
-# DVC
-/data/*.csv
-/data/*.pdf
+# Model artifacts (too large for git)
+/models/*.pkl
+/models/*.h5
+/models/*.pth
+/models/*.joblib
+
+# Metrics and evaluation outputs
+metrics/**
+!metrics/.gitkeep
+
+# ------------------------------------------------------------------------------
+# Data Version Control (DVC)
+# ------------------------------------------------------------------------------
 .dvc/config.local
 .dvc/tmp
-
-/models/*.pkl
 .dvc/cache
 
+# DVC-tracked large files (tracked via .dvc files instead)
+/data/*.csv
+/data/*.pdf
+data/qdrant_storage/
+data/processed/*
+data/debug/*
+data/ground_truth/raw_data/**
+data/unused/**
+data/raw_data/*.pdf
+data/raw_data/*.html
+
+# Data mapping (generated, not source)
+data/mapping.json
 
-# IDE
+# ------------------------------------------------------------------------------
+# Development Tools & IDEs
+# ------------------------------------------------------------------------------
 .vscode/
 .idea/
 *.swp
 *.swo
+*.swn
+.project
+.pydevproject
+.settings/
 
-# OS
+# ------------------------------------------------------------------------------
+# Operating System Files
+# ------------------------------------------------------------------------------
 .DS_Store
 Thumbs.db
+desktop.ini
+*.bak
+*~
 
-# Environment variables
+# ------------------------------------------------------------------------------
+# Security & Credentials (NEVER commit!)
+# ------------------------------------------------------------------------------
 .env
+*.key
+*.pem
+*.crt
+dagshub_token.txt
+secrets/
 
-# Docker
+# ------------------------------------------------------------------------------
+# Logs & Temporary Files
+# ------------------------------------------------------------------------------
 *.log
+*.tmp
+tmp/
+logs/
+*.pid
 
-# Token
-dagshub_token.txt
-
-backend/debug_responses/
+# Docker logs
+docker-compose.override.yml
 
-# Data
-data/mapping.json
-data/qdrant_storage/
-data/ground_truth/raw_data/**
-data/unused/**
-data/raw_data/*.pdf
-data/raw_data/*.html
-data/processed/*
-data/debug/*
+# ------------------------------------------------------------------------------
+# Testing & Coverage
+# ------------------------------------------------------------------------------
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+.nox/
 
+# ------------------------------------------------------------------------------
+# Application-Specific
+# ------------------------------------------------------------------------------
+backend/debug_responses/
 
-# Metrics
-metrics/**
-metrics/ragas_records.json
+# ------------------------------------------------------------------------------
+# Archives (typically not source code)
+# ------------------------------------------------------------------------------
+*.zip
+*.tar
+*.tar.gz
+*.rar
+*.7z