Files
crawl4ai/deploy/docker/config.yml
UncleCode a58c8000aa refactor(server): migrate to pool-based crawler management
Replace crawler_manager.py with simpler crawler_pool.py implementation:
- Add global page semaphore for hard concurrency cap
- Implement browser pool with idle cleanup
- Add playground UI for testing and stress testing
- Update API handlers to use pooled crawlers
- Enhance logging levels and symbols

BREAKING CHANGE: Removes CrawlerManager class in favor of simpler pool-based approach
2025-04-20 20:14:26 +08:00

91 lines
2.1 KiB
YAML
Raw Permalink Blame History

This file contains invisible Unicode characters
This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Application Configuration
app:
title: "Crawl4AI API"
version: "1.0.0"
host: "0.0.0.0"
port: 8020
reload: False
workers: 4
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:
base_config:
simulate_user: true
memory_threshold_percent: 95.0
rate_limiter:
enabled: true
base_delay: [1.0, 2.0]
timeouts:
stream_init: 30.0 # Timeout for stream initialization
batch_process: 300.0 # Timeout for batch processing
pool:
max_pages: 40 # ← GLOBAL_SEM permits
idle_ttl_sec: 1800 # ← 30 min janitor cutoff
browser:
kwargs:
headless: true
text_mode: true
extra_args:
# - "--single-process"
- "--no-sandbox"
- "--disable-dev-shm-usage"
- "--disable-gpu"
- "--disable-software-rasterizer"
- "--disable-web-security"
- "--allow-insecure-localhost"
- "--ignore-certificate-errors"
# 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"