mirror of
https://github.com/unclecode/crawl4ai.git
synced 2025-12-31 12:26:16 +00:00
72 lines
1.6 KiB
YAML
72 lines
1.6 KiB
YAML
# Application Configuration
|
|
app:
|
|
title: "Crawl4AI API"
|
|
version: "1.0.0"
|
|
host: "0.0.0.0"
|
|
port: 8000
|
|
reload: True
|
|
timeout_keep_alive: 300
|
|
|
|
# Default LLM Configuration
|
|
llm:
|
|
provider: "openai/gpt-4o-mini"
|
|
api_key_env: "OPENAI_API_KEY"
|
|
# api_key: sk-... # If you pass the API key directly then api_key_env will be ignored
|
|
|
|
# Redis Configuration
|
|
redis:
|
|
host: "localhost"
|
|
port: 6379
|
|
db: 0
|
|
password: ""
|
|
ssl: False
|
|
ssl_cert_reqs: None
|
|
ssl_ca_certs: None
|
|
ssl_certfile: None
|
|
ssl_keyfile: None
|
|
ssl_cert_reqs: None
|
|
ssl_ca_certs: None
|
|
ssl_certfile: None
|
|
ssl_keyfile: None
|
|
|
|
# Rate Limiting Configuration
|
|
rate_limiting:
|
|
enabled: True
|
|
default_limit: "1000/minute"
|
|
trusted_proxies: []
|
|
storage_uri: "memory://" # Use "redis://localhost:6379" for production
|
|
|
|
# Security Configuration
|
|
security:
|
|
enabled: false
|
|
jwt_enabled: false
|
|
https_redirect: false
|
|
trusted_hosts: ["*"]
|
|
headers:
|
|
x_content_type_options: "nosniff"
|
|
x_frame_options: "DENY"
|
|
content_security_policy: "default-src 'self'"
|
|
strict_transport_security: "max-age=63072000; includeSubDomains"
|
|
|
|
# Crawler Configuration
|
|
crawler:
|
|
memory_threshold_percent: 95.0
|
|
rate_limiter:
|
|
base_delay: [1.0, 2.0]
|
|
timeouts:
|
|
stream_init: 30.0 # Timeout for stream initialization
|
|
batch_process: 300.0 # Timeout for batch processing
|
|
|
|
# Logging Configuration
|
|
logging:
|
|
level: "INFO"
|
|
format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
|
|
|
|
# Observability Configuration
|
|
observability:
|
|
prometheus:
|
|
enabled: True
|
|
endpoint: "/metrics"
|
|
health_check:
|
|
endpoint: "/health"
|