feat(requirements): update requirements.txt to include snowballstemmer fix(version_manager): correct version parsing to use __version__.__version__ feat(main): introduce chunking strategy and content filter in CrawlRequest model feat(content_filter): enhance BM25 algorithm with priority tag scoring for improved content relevance feat(logger): implement new async logger engine replacing print statements throughout library fix(database): resolve version-related deadlock and circular lock issues in database operations docs(docker): expand Docker deployment documentation with usage instructions for Docker Compose
63 lines
1.4 KiB
YAML
63 lines
1.4 KiB
YAML
services:
|
|
crawl4ai:
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile
|
|
args:
|
|
PYTHON_VERSION: 3.10
|
|
INSTALL_TYPE: all
|
|
ENABLE_GPU: false
|
|
profiles: ["local"]
|
|
ports:
|
|
- "11235:11235"
|
|
- "8000:8000"
|
|
- "9222:9222"
|
|
- "8080:8080"
|
|
environment:
|
|
- CRAWL4AI_API_TOKEN=${CRAWL4AI_API_TOKEN:-}
|
|
- OPENAI_API_KEY=${OPENAI_API_KEY:-}
|
|
- CLAUDE_API_KEY=${CLAUDE_API_KEY:-}
|
|
volumes:
|
|
- /dev/shm:/dev/shm
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 4G
|
|
reservations:
|
|
memory: 1G
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:11235/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 40s
|
|
|
|
crawl4ai-hub:
|
|
image: unclecode/crawl4ai:basic
|
|
profiles: ["hub"]
|
|
ports:
|
|
- "11235:11235"
|
|
- "8000:8000"
|
|
- "9222:9222"
|
|
- "8080:8080"
|
|
environment:
|
|
- CRAWL4AI_API_TOKEN=${CRAWL4AI_API_TOKEN:-}
|
|
- OPENAI_API_KEY=${OPENAI_API_KEY:-}
|
|
- CLAUDE_API_KEY=${CLAUDE_API_KEY:-}
|
|
volumes:
|
|
- /dev/shm:/dev/shm
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 4G
|
|
reservations:
|
|
memory: 1G
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:11235/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 40s
|