alexsun/compose-anything
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add portkey-gateway/libreoffice/jodconverter/bolt-diy

Browse Source
This commit is contained in:
Sun-ZhenXing
2025-10-28 14:10:10 +08:00
parent af55ba73c0
commit c8b9335e74
23 changed files with 1334 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
src/firecrawl/.env.example
View File

@@ -1,25 +1,72 @@
# Firecrawl version
FIRECRAWL_VERSION="v1.16.0"
FIRECRAWL_VERSION="latest"
# Redis version
REDIS_VERSION="7.4.2-alpine"
REDIS_VERSION="alpine"
# Playwright version
PLAYWRIGHT_VERSION="latest"
# PostgreSQL version (official Firecrawl nuq-postgres image)
NUQ_POSTGRES_VERSION="latest"
# PostgreSQL configuration
POSTGRES_USER="postgres"
POSTGRES_PASSWORD="postgres"
POSTGRES_DB="postgres"
POSTGRES_PORT_OVERRIDE=5432
# Redis configuration
REDIS_PASSWORD="firecrawl"
# REDIS_URL is auto-configured by docker-compose
# REDIS_URL="redis://redis:6379"
# Firecrawl configuration
NUM_WORKERS_PER_QUEUE=8
SCRAPE_RATE_LIMIT_TOKEN_BUCKET_SIZE=20
SCRAPE_RATE_LIMIT_TOKEN_BUCKET_REFILL=1
# Firecrawl API configuration
INTERNAL_PORT=3002
FIRECRAWL_PORT_OVERRIDE=3002
EXTRACT_WORKER_PORT=3004
WORKER_PORT=3005
# Playwright configuration (optional)
# Database authentication
USE_DB_AUTHENTICATION="false"
# AI features (Optional)
# OPENAI_API_KEY=""
# OPENAI_BASE_URL=""
# MODEL_NAME=""
# MODEL_EMBEDDING_NAME=""
# OLLAMA_BASE_URL=""
# Admin and security
BULL_AUTH_KEY="@"
# TEST_API_KEY=""
# Monitoring (Optional)
# SLACK_WEBHOOK_URL=""
# POSTHOG_API_KEY=""
# POSTHOG_HOST=""
# Supabase authentication (Optional)
# SUPABASE_ANON_TOKEN=""
# SUPABASE_URL=""
# SUPABASE_SERVICE_TOKEN=""
# Webhook configuration (Optional)
# SELF_HOSTED_WEBHOOK_URL=""
# Search API keys (Optional)
# SERPER_API_KEY=""
# SEARCHAPI_API_KEY=""
# Logging
LOGGING_LEVEL="info"
# Playwright proxy configuration (Optional)
PROXY_SERVER=""
PROXY_USERNAME=""
PROXY_PASSWORD=""
BLOCK_MEDIA="true"
# Port overrides
FIRECRAWL_PORT_OVERRIDE=3002
# SearXNG configuration (Optional)
# SEARXNG_ENDPOINT=""
# SEARXNG_ENGINES=""
# SEARXNG_CATEGORIES=""

125
src/firecrawl/README.md
View File

@@ -6,39 +6,66 @@ This service deploys Firecrawl, a web scraping and crawling API powered by Playw
## Services
- `firecrawl`: The main Firecrawl API server.
- `redis`: Redis for job queue and caching.
- `playwright`: Playwright service for browser automation.
- `api`: The main Firecrawl API server with integrated workers
- `redis`: Redis for job queue and caching
- `playwright-service`: Playwright service for browser automation
- `nuq-postgres`: PostgreSQL database for queue management and data storage
## Environment Variables
| Variable Name | Description | Default Value |
| ------------------------------------- | ----------------------------------- | -------------- |
| FIRECRAWL_VERSION | Firecrawl image version | `v1.16.0` |
| REDIS_VERSION | Redis image version | `7.4.2-alpine` |
| PLAYWRIGHT_VERSION | Playwright service version | `latest` |
| REDIS_PASSWORD | Redis password | `firecrawl` |
| NUM_WORKERS_PER_QUEUE | Number of workers per queue | `8` |
| SCRAPE_RATE_LIMIT_TOKEN_BUCKET_SIZE | Token bucket size for rate limiting | `20` |
| SCRAPE_RATE_LIMIT_TOKEN_BUCKET_REFILL | Token refill rate per second | `1` |
| PROXY_SERVER | Proxy server URL (optional) | `""` |
| PROXY_USERNAME | Proxy username (optional) | `""` |
| PROXY_PASSWORD | Proxy password (optional) | `""` |
| BLOCK_MEDIA | Block media content | `true` |
| FIRECRAWL_PORT_OVERRIDE | Firecrawl API port | `3002` |
| Variable Name | Description | Default Value |
| ----------------------- | ------------------------------------------ | ------------- |
| FIRECRAWL_VERSION | Firecrawl image version | `latest` |
| REDIS_VERSION | Redis image version | `alpine` |
| PLAYWRIGHT_VERSION | Playwright service version | `latest` |
| NUQ_POSTGRES_VERSION | NUQ PostgreSQL image version | `latest` |
| POSTGRES_USER | PostgreSQL username | `postgres` |
| POSTGRES_PASSWORD | PostgreSQL password | `postgres` |
| POSTGRES_DB | PostgreSQL database name | `postgres` |
| POSTGRES_PORT_OVERRIDE | PostgreSQL port mapping | `5432` |
| INTERNAL_PORT | Internal API port | `3002` |
| FIRECRAWL_PORT_OVERRIDE | External API port mapping | `3002` |
| EXTRACT_WORKER_PORT | Extract worker port | `3004` |
| WORKER_PORT | Worker port | `3005` |
| USE_DB_AUTHENTICATION | Enable database authentication | `false` |
| OPENAI_API_KEY | OpenAI API key for AI features (optional) | `""` |
| OPENAI_BASE_URL | OpenAI API base URL (optional) | `""` |
| MODEL_NAME | AI model name (optional) | `""` |
| MODEL_EMBEDDING_NAME | Embedding model name (optional) | `""` |
| OLLAMA_BASE_URL | Ollama base URL (optional) | `""` |
| BULL_AUTH_KEY | Bull queue admin panel authentication key | `@` |
| TEST_API_KEY | Test API key (optional) | `""` |
| SLACK_WEBHOOK_URL | Slack webhook for notifications (optional) | `""` |
| POSTHOG_API_KEY | PostHog API key (optional) | `""` |
| POSTHOG_HOST | PostHog host (optional) | `""` |
| SUPABASE_ANON_TOKEN | Supabase anonymous token (optional) | `""` |
| SUPABASE_URL | Supabase URL (optional) | `""` |
| SUPABASE_SERVICE_TOKEN | Supabase service token (optional) | `""` |
| SELF_HOSTED_WEBHOOK_URL | Self-hosted webhook URL (optional) | `""` |
| SERPER_API_KEY | Serper API key for search (optional) | `""` |
| SEARCHAPI_API_KEY | SearchAPI key (optional) | `""` |
| LOGGING_LEVEL | Logging level | `info` |
| PROXY_SERVER | Proxy server URL (optional) | `""` |
| PROXY_USERNAME | Proxy username (optional) | `""` |
| PROXY_PASSWORD | Proxy password (optional) | `""` |
| BLOCK_MEDIA | Block media content | `true` |
| SEARXNG_ENDPOINT | SearXNG endpoint (optional) | `""` |
| SEARXNG_ENGINES | SearXNG engines (optional) | `""` |
| SEARXNG_CATEGORIES | SearXNG categories (optional) | `""` |
Please modify the `.env` file as needed for your use case.
## Volumes
- `redis_data`: Redis data storage for job queues and caching.
- `redis_data`: Redis data storage for job queues and caching
- `postgres_data`: PostgreSQL data storage for queue management and metadata
## Usage
### Start the Services
```bash
docker-compose up -d
docker compose up -d
```
### Access the API
@@ -49,12 +76,22 @@ The Firecrawl API will be available at:
http://localhost:3002
```
### Admin Panel
Access the Bull queue admin panel at:
```text
http://localhost:3002/admin/@/queues
```
Replace `@` with your `BULL_AUTH_KEY` value if changed.
### Example API Calls
**Scrape a Single Page:**
```bash
curl -X POST http://localhost:3002/v0/scrape \
curl -X POST http://localhost:3002/v1/scrape \
-H "Content-Type: application/json" \
-d '{
"url": "https://example.com"
@@ -64,12 +101,27 @@ curl -X POST http://localhost:3002/v0/scrape \
**Crawl a Website:**
```bash
curl -X POST http://localhost:3002/v0/crawl \
curl -X POST http://localhost:3002/v1/crawl \
-H "Content-Type: application/json" \
-d '{
"url": "https://example.com",
"crawlerOptions": {
"limit": 100
"limit": 100
}'
```
**Extract Structured Data:**
```bash
curl -X POST http://localhost:3002/v1/extract \
-H "Content-Type: application/json" \
-d '{
"urls": ["https://example.com"],
"schema": {
"type": "object",
"properties": {
"title": {"type": "string"},
"description": {"type": "string"}
}
}
}'
```
@@ -80,16 +132,31 @@ curl -X POST http://localhost:3002/v0/crawl \
- **Web Crawling**: Recursively crawl entire websites
- **JavaScript Rendering**: Full support for dynamic JavaScript-rendered pages
- **Markdown Output**: Clean markdown conversion of web content
- **Rate Limiting**: Built-in rate limiting to prevent abuse
- **Structured Data Extraction**: Extract data using JSON schemas
- **Queue Management**: Built-in job queue with Bull
- **Rate Limiting**: Configurable rate limiting
- **Proxy Support**: Optional proxy configuration for all requests
- **AI-Powered Features**: Optional OpenAI integration for advanced extraction
## Architecture
This deployment uses the official Firecrawl architecture:
- **API Server**: Handles HTTP requests and manages the job queue
- **Workers**: Built into the main container, processes scraping jobs
- **PostgreSQL**: Stores queue metadata and job information
- **Redis**: Handles job queue and caching
- **Playwright Service**: Provides browser automation capabilities
## Notes
- The service uses Playwright for browser automation, supporting complex web pages
- Redis is used for job queuing and caching
- Rate limiting is configurable via environment variables
- For production use, consider scaling the number of workers
- BLOCK_MEDIA can reduce memory usage by blocking images/videos
- The service uses the official `ghcr.io/firecrawl/firecrawl` image
- PostgreSQL uses the official `ghcr.io/firecrawl/nuq-postgres` image for queue management (NUQ - Not Quite Bull)
- Redis is used for job queuing without password by default (runs on private network)
- For production use, enable `USE_DB_AUTHENTICATION` and configure Supabase
- The `BULL_AUTH_KEY` should be changed in production deployments
- AI features require an `OPENAI_API_KEY` or `OLLAMA_BASE_URL`
- All workers run within the single API container using the harness mode
## License

125
src/firecrawl/README.zh.md
View File

@@ -6,39 +6,66 @@
## 服务
- `firecrawl`: Firecrawl API 主服务器。
- `redis`: 用于作业队列和缓存的 Redis。
- `playwright`: 用于浏览器自动化的 Playwright 服务。
- `api`: Firecrawl API 主服务器,集成了工作进程
- `redis`: 用于作业队列和缓存的 Redis
- `playwright-service`: 用于浏览器自动化的 Playwright 服务
- `nuq-postgres`: 用于队列管理和数据存储的 PostgreSQL 数据库
## 环境变量
| 变量名 | 说明 | 默认值 |
| ------------------------------------- | ---------------------- | -------------- |
| FIRECRAWL_VERSION | Firecrawl 镜像版本 | `v1.16.0` |
| REDIS_VERSION | Redis 镜像版本 | `7.4.2-alpine` |
| PLAYWRIGHT_VERSION | Playwright 服务版本 | `latest` |
| REDIS_PASSWORD | Redis 密码 | `firecrawl` |
| NUM_WORKERS_PER_QUEUE | 每个队列的工作进程数 | `8` |
| SCRAPE_RATE_LIMIT_TOKEN_BUCKET_SIZE | 速率限制的令牌桶大小 | `20` |
| SCRAPE_RATE_LIMIT_TOKEN_BUCKET_REFILL | 每秒令牌填充速率 | `1` |
| PROXY_SERVER | 代理服务器 URL（可选） | `""` |
| PROXY_USERNAME | 代理用户名（可选） | `""` |
| PROXY_PASSWORD | 代理密码（可选） | `""` |
| BLOCK_MEDIA | 阻止媒体内容 | `true` |
| FIRECRAWL_PORT_OVERRIDE | Firecrawl API 端口 | `3002` |
| 变量名 | 说明 | 默认值 |
| ----------------------- | ----------------------------- | ---------- |
| FIRECRAWL_VERSION | Firecrawl 镜像版本 | `latest` |
| REDIS_VERSION | Redis 镜像版本 | `alpine` |
| PLAYWRIGHT_VERSION | Playwright 服务版本 | `latest` |
| NUQ_POSTGRES_VERSION | NUQ PostgreSQL 镜像版本 | `latest` |
| POSTGRES_USER | PostgreSQL 用户名 | `postgres` |
| POSTGRES_PASSWORD | PostgreSQL 密码 | `postgres` |
| POSTGRES_DB | PostgreSQL 数据库名称 | `postgres` |
| POSTGRES_PORT_OVERRIDE | PostgreSQL 端口映射 | `5432` |
| INTERNAL_PORT | 内部 API 端口 | `3002` |
| FIRECRAWL_PORT_OVERRIDE | 外部 API 端口映射 | `3002` |
| EXTRACT_WORKER_PORT | 提取工作进程端口 | `3004` |
| WORKER_PORT | 工作进程端口 | `3005` |
| USE_DB_AUTHENTICATION | 启用数据库身份验证 | `false` |
| OPENAI_API_KEY | OpenAI API 密钥（可选） | `""` |
| OPENAI_BASE_URL | OpenAI API 基础 URL（可选） | `""` |
| MODEL_NAME | AI 模型名称（可选） | `""` |
| MODEL_EMBEDDING_NAME | 嵌入模型名称（可选） | `""` |
| OLLAMA_BASE_URL | Ollama 基础 URL（可选） | `""` |
| BULL_AUTH_KEY | Bull 队列管理面板身份验证密钥 | `@` |
| TEST_API_KEY | 测试 API 密钥（可选） | `""` |
| SLACK_WEBHOOK_URL | Slack Webhook 通知（可选） | `""` |
| POSTHOG_API_KEY | PostHog API 密钥（可选） | `""` |
| POSTHOG_HOST | PostHog 主机（可选） | `""` |
| SUPABASE_ANON_TOKEN | Supabase 匿名令牌（可选） | `""` |
| SUPABASE_URL | Supabase URL（可选） | `""` |
| SUPABASE_SERVICE_TOKEN | Supabase 服务令牌（可选） | `""` |
| SELF_HOSTED_WEBHOOK_URL | 自托管 Webhook URL（可选） | `""` |
| SERPER_API_KEY | Serper 搜索 API 密钥（可选） | `""` |
| SEARCHAPI_API_KEY | SearchAPI 密钥（可选） | `""` |
| LOGGING_LEVEL | 日志级别 | `info` |
| PROXY_SERVER | 代理服务器 URL（可选） | `""` |
| PROXY_USERNAME | 代理用户名（可选） | `""` |
| PROXY_PASSWORD | 代理密码（可选） | `""` |
| BLOCK_MEDIA | 阻止媒体内容 | `true` |
| SEARXNG_ENDPOINT | SearXNG 端点（可选） | `""` |
| SEARXNG_ENGINES | SearXNG 引擎（可选） | `""` |
| SEARXNG_CATEGORIES | SearXNG 分类（可选） | `""` |
请根据实际需求修改 `.env` 文件。
## 卷
- `redis_data`: 用于作业队列和缓存的 Redis 数据存储。
- `redis_data`: 用于作业队列和缓存的 Redis 数据存储
- `postgres_data`: 用于队列管理和元数据的 PostgreSQL 数据存储
## 使用方法
### 启动服务
```bash
docker-compose up -d
docker compose up -d
```
### 访问 API
@@ -49,12 +76,22 @@ Firecrawl API 可在以下地址访问:
http://localhost:3002
```
### 管理面板
访问 Bull 队列管理面板:
```text
http://localhost:3002/admin/@/queues
```
如果修改了 `BULL_AUTH_KEY`,请将 `@` 替换为您的值。
### API 调用示例
**抓取单个页面:**
```bash
curl -X POST http://localhost:3002/v0/scrape \
curl -X POST http://localhost:3002/v1/scrape \
-H "Content-Type: application/json" \
-d '{
"url": "https://example.com"
@@ -64,12 +101,27 @@ curl -X POST http://localhost:3002/v0/scrape \
**爬取网站:**
```bash
curl -X POST http://localhost:3002/v0/crawl \
curl -X POST http://localhost:3002/v1/crawl \
-H "Content-Type: application/json" \
-d '{
"url": "https://example.com",
"crawlerOptions": {
"limit": 100
"limit": 100
}'
```
**提取结构化数据:**
```bash
curl -X POST http://localhost:3002/v1/extract \
-H "Content-Type: application/json" \
-d '{
"urls": ["https://example.com"],
"schema": {
"type": "object",
"properties": {
"title": {"type": "string"},
"description": {"type": "string"}
}
}
}'
```
@@ -80,16 +132,31 @@ curl -X POST http://localhost:3002/v0/crawl \
- **网站爬取**: 递归爬取整个网站
- **JavaScript 渲染**: 完全支持动态 JavaScript 渲染的页面
- **Markdown 输出**: 将网页内容清晰地转换为 markdown
- **速率限制**: 内置速率限制以防止滥用
- **结构化数据提取**: 使用 JSON Schema 提取数据
- **队列管理**: 内置 Bull 作业队列
- **速率限制**: 可配置的速率限制
- **代理支持**: 所有请求的可选代理配置
- **AI 驱动功能**: 可选的 OpenAI 集成以进行高级提取
## 架构
此部署使用官方 Firecrawl 架构:
- **API 服务器**: 处理 HTTP 请求并管理作业队列
- **工作进程**: 内置于主容器中,处理抓取作业
- **PostgreSQL**: 存储队列元数据和作业信息
- **Redis**: 处理作业队列和缓存
- **Playwright 服务**: 提供浏览器自动化功能
## 注意事项
- 该服务使用 Playwright 进行浏览器自动化,支持复杂的网页
- Redis 用于作业队列和缓存
- 速率限制可通过环境变量配置
- 对于生产环境,考虑扩展工作进程数量
- BLOCK_MEDIA 可以通过阻止图像/视频来减少内存使用
- 该服务使用官方的 `ghcr.io/firecrawl/firecrawl` 镜像
- PostgreSQL 使用官方的 `ghcr.io/firecrawl/nuq-postgres` 镜像进行队列管理（NUQ - Not Quite Bull）
- Redis 默认不使用密码（运行在私有网络上）
- 对于生产环境,启用 `USE_DB_AUTHENTICATION` 并配置 Supabase
- 在生产部署中应更改 `BULL_AUTH_KEY`
- AI 功能需要 `OPENAI_API_KEY` 或 `OLLAMA_BASE_URL`
- 所有工作进程都在单个 API 容器中使用 harness 模式运行
## 许可证

190
src/firecrawl/docker-compose.yaml
View File

@@ -6,68 +6,41 @@ x-default: &default
max-size: 100m
max-file: "3"
x-common-env: &common-env
REDIS_URL: ${REDIS_URL:-redis://redis:6379}
REDIS_RATE_LIMIT_URL: ${REDIS_URL:-redis://redis:6379}
PLAYWRIGHT_MICROSERVICE_URL: ${PLAYWRIGHT_MICROSERVICE_URL:-http://playwright-service:3000/scrape}
NUQ_DATABASE_URL: ${NUQ_DATABASE_URL:-postgres://postgres:postgres@nuq-postgres:5432/postgres}
USE_DB_AUTHENTICATION: ${USE_DB_AUTHENTICATION:-false}
OPENAI_API_KEY: ${OPENAI_API_KEY:-}
OPENAI_BASE_URL: ${OPENAI_BASE_URL:-}
MODEL_NAME: ${MODEL_NAME:-}
MODEL_EMBEDDING_NAME: ${MODEL_EMBEDDING_NAME:-}
OLLAMA_BASE_URL: ${OLLAMA_BASE_URL:-}
SLACK_WEBHOOK_URL: ${SLACK_WEBHOOK_URL:-}
BULL_AUTH_KEY: ${BULL_AUTH_KEY:-@}
TEST_API_KEY: ${TEST_API_KEY:-}
POSTHOG_API_KEY: ${POSTHOG_API_KEY:-}
POSTHOG_HOST: ${POSTHOG_HOST:-}
SUPABASE_ANON_TOKEN: ${SUPABASE_ANON_TOKEN:-}
SUPABASE_URL: ${SUPABASE_URL:-}
SUPABASE_SERVICE_TOKEN: ${SUPABASE_SERVICE_TOKEN:-}
SELF_HOSTED_WEBHOOK_URL: ${SELF_HOSTED_WEBHOOK_URL:-}
SERPER_API_KEY: ${SERPER_API_KEY:-}
SEARCHAPI_API_KEY: ${SEARCHAPI_API_KEY:-}
LOGGING_LEVEL: ${LOGGING_LEVEL:-info}
PROXY_SERVER: ${PROXY_SERVER:-}
PROXY_USERNAME: ${PROXY_USERNAME:-}
PROXY_PASSWORD: ${PROXY_PASSWORD:-}
SEARXNG_ENDPOINT: ${SEARXNG_ENDPOINT:-}
SEARXNG_ENGINES: ${SEARXNG_ENGINES:-}
SEARXNG_CATEGORIES: ${SEARXNG_CATEGORIES:-}
services:
firecrawl:
playwright-service:
<<: *default
image: mendableai/firecrawl:${FIRECRAWL_VERSION:-v1.16.0}
ports:
- "${FIRECRAWL_PORT_OVERRIDE:-3002}:3002"
image: ghcr.io/firecrawl/playwright-service:${PLAYWRIGHT_VERSION:-latest}
environment:
TZ: ${TZ:-UTC}
REDIS_URL: redis://:${REDIS_PASSWORD:-firecrawl}@redis:6379
PLAYWRIGHT_MICROSERVICE_URL: http://playwright:3000
PORT: 3002
NUM_WORKERS_PER_QUEUE: ${NUM_WORKERS_PER_QUEUE:-8}
SCRAPE_RATE_LIMIT_TOKEN_BUCKET_SIZE: ${SCRAPE_RATE_LIMIT_TOKEN_BUCKET_SIZE:-20}
SCRAPE_RATE_LIMIT_TOKEN_BUCKET_REFILL: ${SCRAPE_RATE_LIMIT_TOKEN_BUCKET_REFILL:-1}
depends_on:
redis:
condition: service_healthy
playwright:
condition: service_started
deploy:
resources:
limits:
cpus: '2.0'
memory: 4G
reservations:
cpus: '1.0'
memory: 2G
healthcheck:
test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3002/health"]
interval: 30s
timeout: 10s
retries: 3
start_period: 30s
redis:
<<: *default
image: redis:${REDIS_VERSION:-7.4.2-alpine}
command: redis-server --requirepass ${REDIS_PASSWORD:-firecrawl} --appendonly yes
environment:
- TZ=${TZ:-UTC}
volumes:
- redis_data:/data
deploy:
resources:
limits:
cpus: '1.0'
memory: 512M
reservations:
cpus: '0.5'
memory: 256M
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 10s
timeout: 3s
retries: 3
start_period: 5s
playwright:
<<: *default
image: mendableai/firecrawl-playwright:${PLAYWRIGHT_VERSION:-latest}
environment:
TZ: ${TZ:-UTC}
PORT: 3000
PROXY_SERVER: ${PROXY_SERVER:-}
PROXY_USERNAME: ${PROXY_USERNAME:-}
@@ -76,11 +49,102 @@ services:
deploy:
resources:
limits:
cpus: '2.0'
memory: 2G
reservations:
cpus: '1.0'
cpus: "1.0"
memory: 1G
reservations:
cpus: "0.5"
memory: 512M
api:
<<: *default
image: ghcr.io/firecrawl/firecrawl:${FIRECRAWL_VERSION:-latest}
environment:
<<: *common-env
HOST: 0.0.0.0
PORT: ${INTERNAL_PORT:-3002}
EXTRACT_WORKER_PORT: ${EXTRACT_WORKER_PORT:-3004}
WORKER_PORT: ${WORKER_PORT:-3005}
ENV: local
depends_on:
redis:
condition: service_healthy
playwright-service:
condition: service_started
nuq-postgres:
condition: service_started
ports:
- "${FIRECRAWL_PORT_OVERRIDE:-3002}:${INTERNAL_PORT:-3002}"
command: node dist/src/harness.js --start-docker
deploy:
resources:
limits:
cpus: "2.0"
memory: 4G
reservations:
cpus: "1.0"
memory: 2G
healthcheck:
test:
[
"CMD",
"wget",
"--no-verbose",
"--tries=1",
"--spider",
"http://localhost:3002/health",
]
interval: 30s
timeout: 10s
retries: 3
start_period: 30s
redis:
<<: *default
image: redis:${REDIS_VERSION:-alpine}
command: redis-server --bind 0.0.0.0
volumes:
- redis_data:/data
deploy:
resources:
limits:
cpus: "0.5"
memory: 512M
reservations:
cpus: "0.25"
memory: 256M
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 10s
timeout: 3s
retries: 3
start_period: 5s
nuq-postgres:
<<: *default
image: ghcr.io/firecrawl/nuq-postgres:${NUQ_POSTGRES_VERSION:-latest}
environment:
POSTGRES_USER: ${POSTGRES_USER:-postgres}
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-postgres}
POSTGRES_DB: ${POSTGRES_DB:-postgres}
ports:
- "${POSTGRES_PORT_OVERRIDE:-5432}:5432"
volumes:
- postgres_data:/var/lib/postgresql/data
deploy:
resources:
limits:
cpus: "1.0"
memory: 1G
reservations:
cpus: "0.5"
memory: 512M
healthcheck:
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-postgres}"]
interval: 10s
timeout: 5s
retries: 5
start_period: 10s
volumes:
redis_data:
postgres_data: