Ashutosh1975270's picture
Fix: Resolve 0-entity extraction error by adding NVIDIA LLM integration and robust error handling
feca495
Raw
History Blame Contribute Delete
7.56 kB
import os
from pathlib import Path
from datetime import timedelta
import dotenv
# Build paths inside the project like this: BASE_DIR / 'subdir'.
BASE_DIR = Path(__file__).resolve().parent.parent
# Load environment variables from parent directory .env
ENV_PATH = BASE_DIR.parent / '.env'
if ENV_PATH.exists():
dotenv.load_dotenv(ENV_PATH)
# Security settings
SECRET_KEY = os.getenv('SECRET_KEY')
if not SECRET_KEY:
raise ValueError(
"SECRET_KEY environment variable is required. "
"Generate one with: python -c \"from django.core.management.utils import get_random_secret_key; print(get_random_secret_key())\""
)
DEBUG = os.getenv('DEBUG', 'False') == 'True'
ALLOWED_HOSTS = [h.strip() for h in os.getenv('ALLOWED_HOSTS', 'localhost,127.0.0.1').split(',') if h.strip()]
# Production security hardening (only when DEBUG=False)
if not DEBUG:
SECURE_BROWSER_XSS_FILTER = True
SECURE_CONTENT_TYPE_NOSNIFF = True
SESSION_COOKIE_SECURE = True
CSRF_COOKIE_SECURE = True
X_FRAME_OPTIONS = 'DENY'
SECURE_SSL_REDIRECT = False # Set True if behind TLS termination proxy
SECURE_HSTS_SECONDS = 0 # Set to 31536000 once HTTPS is confirmed
SECURE_HSTS_INCLUDE_SUBDOMAINS = False
SECURE_HSTS_PRELOAD = False
# Application definition
INSTALLED_APPS = [
'django.contrib.admin',
'django.contrib.auth',
'django.contrib.contenttypes',
'django.contrib.sessions',
'django.contrib.messages',
'django.contrib.staticfiles',
# Third party apps
'rest_framework',
'rest_framework_simplejwt.token_blacklist',
'corsheaders',
# Custom apps
'graphrag',
]
MIDDLEWARE = [
'corsheaders.middleware.CorsMiddleware', # Must be placed high up
'django.middleware.security.SecurityMiddleware',
'django.contrib.sessions.middleware.SessionMiddleware',
'django.middleware.common.CommonMiddleware',
'django.middleware.csrf.CsrfViewMiddleware',
'django.contrib.auth.middleware.AuthenticationMiddleware',
'django.contrib.messages.middleware.MessageMiddleware',
'django.middleware.clickjacking.XFrameOptionsMiddleware',
]
ROOT_URLCONF = 'config.urls'
TEMPLATES = [
{
'BACKEND': 'django.template.backends.django.DjangoTemplates',
'DIRS': [],
'APP_DIRS': True,
'OPTIONS': {
'context_processors': [
'django.template.context_processors.debug',
'django.template.context_processors.request',
'django.contrib.auth.context_processors.auth',
'django.contrib.messages.context_processors.messages',
],
},
},
]
WSGI_APPLICATION = 'config.wsgi.application'
# Database configuration
# Supports: sqlite (default) or postgres
DB_ENGINE = os.getenv('DB_ENGINE', 'sqlite')
if DB_ENGINE == 'postgres':
DATABASES = {
'default': {
'ENGINE': 'django.db.backends.postgresql',
'NAME': os.getenv('DB_NAME', 'graphrag'),
'USER': os.getenv('DB_USER', 'postgres'),
'PASSWORD': os.getenv('DB_PASSWORD', ''),
'HOST': os.getenv('DB_HOST', 'localhost'),
'PORT': os.getenv('DB_PORT', '5432'),
}
}
else:
DATABASES = {
'default': {
'ENGINE': 'django.db.backends.sqlite3',
'NAME': BASE_DIR / 'db' / 'db.sqlite3',
}
}
# Custom User Model
AUTH_USER_MODEL = 'graphrag.User'
AUTHENTICATION_BACKENDS = [
'graphrag.views.EmailOrUsernameModelBackend',
'django.contrib.auth.backends.ModelBackend',
]
# Password validation
AUTH_PASSWORD_VALIDATORS = [
{
'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
},
{
'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
'OPTIONS': {
'min_length': 8,
}
},
{
'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
},
{
'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
},
]
# Internationalization
LANGUAGE_CODE = 'en-us'
TIME_ZONE = 'UTC'
USE_I18N = True
USE_TZ = True
# Static files (CSS, JavaScript, Images)
STATIC_URL = 'static/'
# Media files (User uploads)
MEDIA_URL = '/media/'
MEDIA_ROOT = BASE_DIR / 'uploaded_documents'
DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
# CORS configuration
CORS_ALLOW_ALL_ORIGINS = False
CORS_ALLOWED_ORIGINS = [
origin.strip()
for origin in os.getenv(
'CORS_ALLOWED_ORIGINS',
'http://localhost:3000,http://0.0.0.0:3000,http://127.0.0.1:3000'
).split(',')
if origin.strip()
]
# Django REST Framework configuration
REST_FRAMEWORK = {
'DEFAULT_AUTHENTICATION_CLASSES': (
'rest_framework_simplejwt.authentication.JWTAuthentication',
),
'DEFAULT_PERMISSION_CLASSES': (
'rest_framework.permissions.IsAuthenticated',
),
'DEFAULT_THROTTLE_CLASSES': (
'rest_framework.throttling.AnonRateThrottle',
'rest_framework.throttling.UserRateThrottle',
),
'DEFAULT_THROTTLE_RATES': {
'anon': '30/minute',
'user': '100/minute',
},
}
# Simple JWT settings
SIMPLE_JWT = {
'ACCESS_TOKEN_LIFETIME': timedelta(minutes=30),
'REFRESH_TOKEN_LIFETIME': timedelta(days=7),
'ROTATE_REFRESH_TOKENS': True,
'BLACKLIST_AFTER_ROTATION': True,
'ALGORITHM': 'HS256',
'SIGNING_KEY': SECRET_KEY,
'VERIFYING_KEY': None,
'AUDIENCE': None,
'ISSUER': None,
'AUTH_HEADER_TYPES': ('Bearer',),
'USER_ID_FIELD': 'id',
'USER_ID_CLAIM': 'user_id',
'AUTH_TOKEN_CLASSES': ('rest_framework_simplejwt.tokens.AccessToken',),
}
# File Upload Settings
ALLOWED_EXTENSIONS = {'.pdf', '.txt', '.md', '.docx', '.doc', '.csv', '.json', '.html', '.xml'}
MAX_UPLOAD_SIZE_MB = 10
# Ingestion Concurrency
MAX_INGESTION_WORKERS = 3
# Graph Database (Neo4j) settings
NEO4J_URI = os.getenv('NEO4J_URI', 'bolt://localhost:7687')
NEO4J_USERNAME = os.getenv('NEO4J_USERNAME', 'neo4j')
NEO4J_PASSWORD = os.getenv('NEO4J_PASSWORD', 'password')
# ChromaDB settings
# Supports: local (default) or cloud
CHROMADB_MODE = os.getenv('CHROMADB_MODE', 'local')
CHROMADB_HOST = os.getenv('CHROMADB_HOST', '')
CHROMADB_PORT = int(os.getenv('CHROMADB_PORT', '0'))
CHROMADB_DIR = os.path.join(BASE_DIR, os.getenv('CHROMADB_DIR', 'chroma_db'))
# Logging Configuration
LOG_DIR = BASE_DIR / 'logs'
LOG_DIR.mkdir(exist_ok=True)
LOGGING = {
'version': 1,
'disable_existing_loggers': False,
'formatters': {
'detailed': {
'format': '%(asctime)s [%(levelname)s] %(name)s:%(lineno)d - %(message)s'
},
'simple': {
'format': '[%(levelname)s] %(message)s'
},
},
'handlers': {
'console': {
'class': 'logging.StreamHandler',
'formatter': 'detailed',
},
'file': {
'class': 'logging.handlers.RotatingFileHandler',
'filename': LOG_DIR / 'graphrag.log',
'maxBytes': 10 * 1024 * 1024, # 10MB
'backupCount': 5,
'formatter': 'detailed',
},
},
'loggers': {
'': {
'handlers': ['console', 'file'],
'level': 'INFO',
},
'django': {
'handlers': ['console', 'file'],
'level': 'INFO',
'propagate': False,
},
'graphrag': {
'handlers': ['console', 'file'],
'level': 'INFO',
'propagate': False,
},
},
}