From 8f30f941840332ca48128b733921fffc863ee89a Mon Sep 17 00:00:00 2001 From: Sun-ZhenXing <1006925066@qq.com> Date: Tue, 9 Dec 2025 15:19:11 +0800 Subject: [PATCH] feat: add phoenix & trigger.dev --- README.md | 3 + README.zh.md | 3 + builds/nexa-sdk/.env.example | 41 --- builds/nexa-sdk/Dockerfile | 8 - builds/nexa-sdk/Dockerfile.cuda | 8 - builds/nexa-sdk/README.md | 233 ---------------- builds/nexa-sdk/README.zh.md | 233 ---------------- builds/nexa-sdk/docker-compose.yaml | 94 ------- src/nexa-sdk/.env.example | 20 ++ src/nexa-sdk/README.md | 105 ++++++++ src/nexa-sdk/README.zh.md | 105 ++++++++ src/nexa-sdk/docker-compose.yaml | 74 +++++ src/phoenix/.env.example | 31 +++ src/phoenix/README.md | 100 +++++++ src/phoenix/README.zh.md | 100 +++++++ src/phoenix/docker-compose.yaml | 68 +++++ src/trigger-dev/.env.example | 223 ++++++++++++++++ src/trigger-dev/README.md | 247 +++++++++++++++++ src/trigger-dev/README.zh.md | 247 +++++++++++++++++ src/trigger-dev/docker-compose.yaml | 400 ++++++++++++++++++++++++++++ 20 files changed, 1726 insertions(+), 617 deletions(-) delete mode 100644 builds/nexa-sdk/.env.example delete mode 100644 builds/nexa-sdk/Dockerfile delete mode 100644 builds/nexa-sdk/Dockerfile.cuda delete mode 100644 builds/nexa-sdk/README.md delete mode 100644 builds/nexa-sdk/README.zh.md delete mode 100644 builds/nexa-sdk/docker-compose.yaml create mode 100644 src/nexa-sdk/.env.example create mode 100644 src/nexa-sdk/README.md create mode 100644 src/nexa-sdk/README.zh.md create mode 100644 src/nexa-sdk/docker-compose.yaml create mode 100644 src/phoenix/.env.example create mode 100644 src/phoenix/README.md create mode 100644 src/phoenix/README.zh.md create mode 100644 src/phoenix/docker-compose.yaml create mode 100644 src/trigger-dev/.env.example create mode 100644 src/trigger-dev/README.md create mode 100644 src/trigger-dev/README.zh.md create mode 100644 src/trigger-dev/docker-compose.yaml diff --git a/README.md b/README.md index 96d37be..7482f33 100644 --- a/README.md +++ b/README.md @@ -68,6 +68,7 @@ Compose Anything helps users quickly deploy various services by providing a set | [n8n](./src/n8n) | 1.114.0 | | [Nacos](./src/nacos) | v3.1.0 | | [NebulaGraph](./src/nebulagraph) | v3.8.0 | +| [NexaSDK](./src/nexa-sdk) | v0.2.62 | | [Neo4j](./src/neo4j) | 5.27.4 | | [Nginx](./src/nginx) | 1.29.1 | | [Node Exporter](./src/node-exporter) | v1.8.2 | @@ -75,6 +76,7 @@ Compose Anything helps users quickly deploy various services by providing a set | [Odoo](./src/odoo) | 19.0 | | [Ollama](./src/ollama) | 0.12.0 | | [Open WebUI](./src/open-webui) | main | +| [Phoenix (Arize)](./src/phoenix) | 12.19.0 | | [Open WebUI Rust](./src/open-webui-rust) | latest | | [OpenCoze](./src/opencoze) | See Docs | | [OpenCut](./src/opencut) | latest | @@ -100,6 +102,7 @@ Compose Anything helps users quickly deploy various services by providing a set | [Temporal](./src/temporal) | 1.24.2 | | [TiDB](./src/tidb) | v8.5.0 | | [TiKV](./src/tikv) | v8.5.0 | +| [Trigger.dev](./src/trigger-dev) | v4.2.0 | | [Valkey Cluster](./src/valkey-cluster) | 8.0 | | [Valkey](./src/valkey) | 8.0 | | [Verdaccio](./src/verdaccio) | 6.1.2 | diff --git a/README.zh.md b/README.zh.md index 6964e0b..5269df8 100644 --- a/README.zh.md +++ b/README.zh.md @@ -68,6 +68,7 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件， | [n8n](./src/n8n) | 1.114.0 | | [Nacos](./src/nacos) | v3.1.0 | | [NebulaGraph](./src/nebulagraph) | v3.8.0 | +| [NexaSDK](./src/nexa-sdk) | v0.2.62 | | [Neo4j](./src/neo4j) | 5.27.4 | | [Nginx](./src/nginx) | 1.29.1 | | [Node Exporter](./src/node-exporter) | v1.8.2 | @@ -75,6 +76,7 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件， | [Odoo](./src/odoo) | 19.0 | | [Ollama](./src/ollama) | 0.12.0 | | [Open WebUI](./src/open-webui) | main | +| [Phoenix (Arize)](./src/phoenix) | 12.19.0 | | [Open WebUI Rust](./src/open-webui-rust) | latest | | [OpenCoze](./src/opencoze) | See Docs | | [OpenCut](./src/opencut) | latest | @@ -100,6 +102,7 @@ Compose Anything 通过提供一组高质量的 Docker Compose 配置文件， | [Temporal](./src/temporal) | 1.24.2 | | [TiDB](./src/tidb) | v8.5.0 | | [TiKV](./src/tikv) | v8.5.0 | +| [Trigger.dev](./src/trigger-dev) | v4.2.0 | | [Valkey Cluster](./src/valkey-cluster) | 8.0 | | [Valkey](./src/valkey) | 8.0 | | [Verdaccio](./src/verdaccio) | 6.1.2 | diff --git a/builds/nexa-sdk/.env.example b/builds/nexa-sdk/.env.example deleted file mode 100644 index 63e7057..0000000 --- a/builds/nexa-sdk/.env.example +++ /dev/null @@ -1,41 +0,0 @@ -# Global registry for container images (optional) -# GLOBAL_REGISTRY= - -# Nexa SDK version -NEXA_SDK_VERSION=latest - -# Timezone configuration -TZ=UTC - -# Port override for host binding -NEXA_SDK_PORT_OVERRIDE=8080 - -# Server configuration -NEXA_HOST=0.0.0.0:8080 -NEXA_KEEPALIVE=300 -NEXA_ORIGINS=* - -# HuggingFace token for accessing private models (optional) -NEXA_HFTOKEN= - -# Logging level (none, debug, info, warn, error) -NEXA_LOG=none - -# Model to run (can be any Nexa-compatible model) -# Examples: gemma-2-2b-instruct, qwen3-4b, llama-3-8b, mistral-7b -NEXA_MODEL=gemma-2-2b-instruct - -# GPU configuration (for gpu profile only) -# Number of GPU layers to offload (-1 for all layers) -NEXA_GPU_LAYERS=-1 - -# Shared memory size -NEXA_SHM_SIZE=2g - -# Resource limits -NEXA_SDK_CPU_LIMIT=4.0 -NEXA_SDK_MEMORY_LIMIT=8G - -# Resource reservations -NEXA_SDK_CPU_RESERVATION=2.0 -NEXA_SDK_MEMORY_RESERVATION=4G diff --git a/builds/nexa-sdk/Dockerfile b/builds/nexa-sdk/Dockerfile deleted file mode 100644 index 6e2ca15..0000000 --- a/builds/nexa-sdk/Dockerfile +++ /dev/null @@ -1,8 +0,0 @@ -# https://github.com/NexaAI/nexa-sdk/issues/684 -FROM ubuntu:22.04 - -RUN apt update && apt install -y libgomp1 curl ffmpeg sox -RUN curl -fsSL https://github.com/NexaAI/nexa-sdk/releases/latest/download/nexa-cli_linux_x86_64.sh | sh - -EXPOSE 8080 -CMD [ "nexa", "serve", "--host", "0.0.0.0:8080" ] diff --git a/builds/nexa-sdk/Dockerfile.cuda b/builds/nexa-sdk/Dockerfile.cuda deleted file mode 100644 index 8fe5df7..0000000 --- a/builds/nexa-sdk/Dockerfile.cuda +++ /dev/null @@ -1,8 +0,0 @@ -# https://github.com/NexaAI/nexa-sdk/issues/684 -FROM nvidia/cuda:12.8.1-cudnn-runtime-ubuntu22.04 - -RUN apt update && apt install -y libgomp1 curl ffmpeg sox -RUN curl -fsSL https://github.com/NexaAI/nexa-sdk/releases/latest/download/nexa-cli_linux_x86_64.sh | sh - -EXPOSE 8080 -CMD [ "nexa", "serve", "--host", "0.0.0.0:8080" ] diff --git a/builds/nexa-sdk/README.md b/builds/nexa-sdk/README.md deleted file mode 100644 index 687c657..0000000 --- a/builds/nexa-sdk/README.md +++ /dev/null @@ -1,233 +0,0 @@ -# Nexa SDK - -Nexa SDK is a comprehensive toolkit for running AI models locally. It provides inference for various model types including LLM, VLM (Vision Language Models), TTS (Text-to-Speech), ASR (Automatic Speech Recognition), and more. Built with performance in mind, it supports both CPU and GPU acceleration. - -## Features - -- **Multi-Model Support**: Run LLM, VLM, TTS, ASR, embedding, reranking, and image generation models -- **OpenAI-Compatible API**: Provides standard OpenAI API endpoints for easy integration -- **GPU Acceleration**: Optional GPU support via NVIDIA CUDA for faster inference -- **Resource Management**: Configurable CPU/memory limits and GPU layer offloading -- **Model Caching**: Persistent model storage for faster startup -- **Profile Support**: Easy switching between CPU-only and GPU-accelerated modes - -## Quick Start - -### Prerequisites - -- Docker and Docker Compose -- For GPU support: NVIDIA Docker runtime and compatible GPU - -### Basic Usage (CPU) - -```bash -# Copy environment file -cp .env.example .env - -# Edit .env to configure your model and settings -# NEXA_MODEL=gemma-2-2b-instruct - -# Start the service with CPU profile -docker compose --profile cpu up -d -``` - -### GPU-Accelerated Usage - -```bash -# Copy environment file -cp .env.example .env - -# Configure for GPU usage -# NEXA_MODEL=gemma-2-2b-instruct -# NEXA_GPU_LAYERS=-1 # -1 means all layers on GPU - -# Start the service with GPU profile -docker compose --profile gpu up -d -``` - -## Configuration - -### Environment Variables - -| Variable | Default | Description | -| ------------------------ | --------------------- | ------------------------------------------------------ | -| `NEXA_SDK_VERSION` | `latest` | Nexa SDK Docker image version | -| `NEXA_SDK_PORT_OVERRIDE` | `8080` | Host port for API access | -| `NEXA_MODEL` | `gemma-2-2b-instruct` | Model to load (e.g., qwen3-4b, llama-3-8b, mistral-7b) | -| `NEXA_HOST` | `0.0.0.0:8080` | Server bind address | -| `NEXA_KEEPALIVE` | `300` | Model keepalive timeout in seconds | -| `NEXA_ORIGINS` | `*` | CORS allowed origins | -| `NEXA_HFTOKEN` | - | HuggingFace token for private models | -| `NEXA_LOG` | `none` | Logging level (none, debug, info, warn, error) | -| `NEXA_GPU_LAYERS` | `-1` | GPU layers to offload (-1 = all, 0 = CPU only) | -| `NEXA_SHM_SIZE` | `2g` | Shared memory size | -| `TZ` | `UTC` | Container timezone | - -### Resource Limits - -| Variable | Default | Description | -| ----------------------------- | ------- | ------------------ | -| `NEXA_SDK_CPU_LIMIT` | `4.0` | Maximum CPU cores | -| `NEXA_SDK_MEMORY_LIMIT` | `8G` | Maximum memory | -| `NEXA_SDK_CPU_RESERVATION` | `2.0` | Reserved CPU cores | -| `NEXA_SDK_MEMORY_RESERVATION` | `4G` | Reserved memory | - -### Profiles - -- `cpu`: Run with CPU-only inference (default profile needed) -- `gpu`: Run with GPU acceleration (requires NVIDIA GPU) - -## Usage Examples - -### Test the API - -```bash -# Check available models -curl http://localhost:8080/v1/models - -# Chat completion -curl http://localhost:8080/v1/chat/completions \ - -H "Content-Type: application/json" \ - -d '{ - "model": "gemma-2-2b-instruct", - "messages": [ - {"role": "user", "content": "Hello!"} - ] - }' -``` - -### Using Different Models - -Edit `.env` to change the model: - -```bash -# Small models for limited resources -NEXA_MODEL=gemma-2-2b-instruct -# or -NEXA_MODEL=qwen3-4b - -# Larger models for better quality -NEXA_MODEL=llama-3-8b -# or -NEXA_MODEL=mistral-7b -``` - -### GPU Configuration - -For GPU acceleration, adjust the number of layers: - -```bash -# Offload all layers to GPU (fastest) -NEXA_GPU_LAYERS=-1 - -# Offload 30 layers (hybrid mode) -NEXA_GPU_LAYERS=30 - -# CPU only -NEXA_GPU_LAYERS=0 -``` - -## Model Management - -Models are automatically downloaded on first run and cached in the `nexa_models` volume. The default cache location inside the container is `/root/.cache/nexa`. - -To use a different model: - -1. Update `NEXA_MODEL` in `.env` -2. Restart the service: `docker compose --profile restart` - -## API Endpoints - -Nexa SDK provides OpenAI-compatible API endpoints: - -- `GET /v1/models` - List available models -- `POST /v1/chat/completions` - Chat completions -- `POST /v1/completions` - Text completions -- `POST /v1/embeddings` - Text embeddings -- `GET /health` - Health check -- `GET /docs` - API documentation (Swagger UI) - -## Troubleshooting - -### Out of Memory - -Increase memory limits or use a smaller model: - -```bash -NEXA_SDK_MEMORY_LIMIT=16G -NEXA_SDK_MEMORY_RESERVATION=8G -# Or switch to a smaller model -NEXA_MODEL=gemma-2-2b-instruct -``` - -### GPU Not Detected - -Ensure NVIDIA Docker runtime is installed: - -```bash -# Check GPU availability -docker run --rm --gpus all nvidia/cuda:12.8.1-base-ubuntu22.04 nvidia-smi -``` - -### Model Download Issues - -Set HuggingFace token if accessing private models: - -```bash -NEXA_HFTOKEN=your_hf_token_here -``` - -### Slow Performance - -- Use GPU profile for better performance -- Increase `NEXA_GPU_LAYERS` to offload more computation to GPU -- Allocate more resources or use a smaller model - -## Advanced Configuration - -### Custom Model Path - -If you want to use local model files, mount them as a volume: - -```yaml -volumes: - - ./models:/models - - nexa_models:/root/.cache/nexa -``` - -Then reference the model by its path in the command. - -### HTTPS Configuration - -Set environment variables for HTTPS: - -```bash -NEXA_ENABLEHTTPS=true -``` - -Mount certificate files: - -```yaml -volumes: - - ./certs/cert.pem:/app/cert.pem:ro - - ./certs/key.pem:/app/key.pem:ro -``` - -## Health Check - -The service includes a health check that verifies the API is responding: - -```bash -curl http://localhost:8080/v1/models -``` - -## License - -Nexa SDK is developed by Nexa AI. Please refer to the [official repository](https://github.com/NexaAI/nexa-sdk) for license information. - -## Links - -- [Official Repository](https://github.com/NexaAI/nexa-sdk) -- [Nexa AI Website](https://nexa.ai) -- [Documentation](https://docs.nexa.ai) -- [Model Hub](https://sdk.nexa.ai) diff --git a/builds/nexa-sdk/README.zh.md b/builds/nexa-sdk/README.zh.md deleted file mode 100644 index 18b1bb3..0000000 --- a/builds/nexa-sdk/README.zh.md +++ /dev/null @@ -1,233 +0,0 @@ -# Nexa SDK - -Nexa SDK 是一个功能全面的本地 AI 模型运行工具包。它支持多种模型类型的推理，包括 LLM、VLM（视觉语言模型）、TTS（文本转语音）、ASR（自动语音识别）等。该工具专注于性能优化，支持 CPU 和 GPU 加速。 - -## 特性 - -- **多模型支持**：运行 LLM、VLM、TTS、ASR、嵌入、重排序和图像生成模型 -- **OpenAI 兼容 API**：提供标准的 OpenAI API 端点，便于集成 -- **GPU 加速**：通过 NVIDIA CUDA 提供可选的 GPU 支持，实现更快的推理速度 -- **资源管理**：可配置的 CPU/内存限制和 GPU 层卸载 -- **模型缓存**：持久化模型存储，加快启动速度 -- **配置文件支持**：轻松在 CPU 模式和 GPU 加速模式之间切换 - -## 快速开始 - -### 前置要求 - -- Docker 和 Docker Compose -- GPU 支持需要：NVIDIA Docker runtime 和兼容的 GPU - -### 基本使用（CPU） - -```bash -# 复制环境配置文件 -cp .env.example .env - -# 编辑 .env 配置模型和设置 -# NEXA_MODEL=gemma-2-2b-instruct - -# 使用 CPU 配置文件启动服务 -docker compose --profile cpu up -d -``` - -### GPU 加速使用 - -```bash -# 复制环境配置文件 -cp .env.example .env - -# 配置 GPU 使用 -# NEXA_MODEL=gemma-2-2b-instruct -# NEXA_GPU_LAYERS=-1 # -1 表示所有层都在 GPU 上 - -# 使用 GPU 配置文件启动服务 -docker compose --profile gpu up -d -``` - -## 配置 - -### 环境变量 - -| 变量 | 默认值 | 说明 | -| ------------------------ | --------------------- | --------------------------------------------------- | -| `NEXA_SDK_VERSION` | `latest` | Nexa SDK Docker 镜像版本 | -| `NEXA_SDK_PORT_OVERRIDE` | `8080` | API 访问的主机端口 | -| `NEXA_MODEL` | `gemma-2-2b-instruct` | 要加载的模型（如 qwen3-4b、llama-3-8b、mistral-7b） | -| `NEXA_HOST` | `0.0.0.0:8080` | 服务器绑定地址 | -| `NEXA_KEEPALIVE` | `300` | 模型保活超时时间（秒） | -| `NEXA_ORIGINS` | `*` | CORS 允许的源 | -| `NEXA_HFTOKEN` | - | 用于私有模型的 HuggingFace 令牌 | -| `NEXA_LOG` | `none` | 日志级别（none、debug、info、warn、error） | -| `NEXA_GPU_LAYERS` | `-1` | 卸载到 GPU 的层数（-1 = 全部，0 = 仅 CPU） | -| `NEXA_SHM_SIZE` | `2g` | 共享内存大小 | -| `TZ` | `UTC` | 容器时区 | - -### 资源限制 - -| 变量 | 默认值 | 说明 | -| ----------------------------- | ------ | --------------- | -| `NEXA_SDK_CPU_LIMIT` | `4.0` | 最大 CPU 核心数 | -| `NEXA_SDK_MEMORY_LIMIT` | `8G` | 最大内存 | -| `NEXA_SDK_CPU_RESERVATION` | `2.0` | 预留 CPU 核心数 | -| `NEXA_SDK_MEMORY_RESERVATION` | `4G` | 预留内存 | - -### 配置文件 - -- `cpu`：使用 CPU 推理运行（需要指定默认配置文件） -- `gpu`：使用 GPU 加速运行（需要 NVIDIA GPU） - -## 使用示例 - -### 测试 API - -```bash -# 检查可用模型 -curl http://localhost:8080/v1/models - -# 聊天完成 -curl http://localhost:8080/v1/chat/completions \ - -H "Content-Type: application/json" \ - -d '{ - "model": "gemma-2-2b-instruct", - "messages": [ - {"role": "user", "content": "你好！"} - ] - }' -``` - -### 使用不同的模型 - -编辑 `.env` 更改模型： - -```bash -# 资源受限时使用小模型 -NEXA_MODEL=gemma-2-2b-instruct -# 或 -NEXA_MODEL=qwen3-4b - -# 追求更好质量时使用大模型 -NEXA_MODEL=llama-3-8b -# 或 -NEXA_MODEL=mistral-7b -``` - -### GPU 配置 - -对于 GPU 加速，调整层数： - -```bash -# 将所有层卸载到 GPU（最快） -NEXA_GPU_LAYERS=-1 - -# 卸载 30 层（混合模式） -NEXA_GPU_LAYERS=30 - -# 仅 CPU -NEXA_GPU_LAYERS=0 -``` - -## 模型管理 - -模型会在首次运行时自动下载，并缓存在 `nexa_models` 卷中。容器内的默认缓存位置是 `/root/.cache/nexa`。 - -要使用不同的模型： - -1. 在 `.env` 中更新 `NEXA_MODEL` -2. 重启服务：`docker compose --profile restart` - -## API 端点 - -Nexa SDK 提供 OpenAI 兼容的 API 端点： - -- `GET /v1/models` - 列出可用模型 -- `POST /v1/chat/completions` - 聊天完成 -- `POST /v1/completions` - 文本完成 -- `POST /v1/embeddings` - 文本嵌入 -- `GET /health` - 健康检查 -- `GET /docs` - API 文档（Swagger UI） - -## 故障排除 - -### 内存不足 - -增加内存限制或使用更小的模型： - -```bash -NEXA_SDK_MEMORY_LIMIT=16G -NEXA_SDK_MEMORY_RESERVATION=8G -# 或切换到更小的模型 -NEXA_MODEL=gemma-2-2b-instruct -``` - -### GPU 未检测到 - -确保已安装 NVIDIA Docker runtime： - -```bash -# 检查 GPU 可用性 -docker run --rm --gpus all nvidia/cuda:12.8.1-base-ubuntu22.04 nvidia-smi -``` - -### 模型下载问题 - -如果访问私有模型，设置 HuggingFace 令牌： - -```bash -NEXA_HFTOKEN=your_hf_token_here -``` - -### 性能缓慢 - -- 使用 GPU 配置文件以获得更好的性能 -- 增加 `NEXA_GPU_LAYERS` 以将更多计算卸载到 GPU -- 分配更多资源或使用更小的模型 - -## 高级配置 - -### 自定义模型路径 - -如果要使用本地模型文件，将它们挂载为卷： - -```yaml -volumes: - - ./models:/models - - nexa_models:/root/.cache/nexa -``` - -然后在命令中通过路径引用模型。 - -### HTTPS 配置 - -设置 HTTPS 的环境变量： - -```bash -NEXA_ENABLEHTTPS=true -``` - -挂载证书文件： - -```yaml -volumes: - - ./certs/cert.pem:/app/cert.pem:ro - - ./certs/key.pem:/app/key.pem:ro -``` - -## 健康检查 - -服务包含验证 API 是否响应的健康检查： - -```bash -curl http://localhost:8080/v1/models -``` - -## 许可证 - -Nexa SDK 由 Nexa AI 开发。许可证信息请参考[官方仓库](https://github.com/NexaAI/nexa-sdk)。 - -## 链接 - -- [官方仓库](https://github.com/NexaAI/nexa-sdk) -- [Nexa AI 网站](https://nexa.ai) -- [文档](https://docs.nexa.ai) -- [模型中心](https://sdk.nexa.ai) diff --git a/builds/nexa-sdk/docker-compose.yaml b/builds/nexa-sdk/docker-compose.yaml deleted file mode 100644 index a9ad3f1..0000000 --- a/builds/nexa-sdk/docker-compose.yaml +++ /dev/null @@ -1,94 +0,0 @@ -x-defaults: &defaults - restart: unless-stopped - logging: - driver: json-file - options: - max-size: 100m - max-file: "3" - -services: - nexa-sdk: - <<: *defaults - build: - context: . - dockerfile: Dockerfile - image: ${GLOBAL_REGISTRY:-}alexsuntop/nexa-sdk:${NEXA_SDK_CPU_VERSION:-0.2.57} - ports: - - "${NEXA_SDK_PORT_OVERRIDE:-8080}:8080" - volumes: - - nexa_models:/root/.cache/nexa - environment: - - TZ=${TZ:-UTC} - - NEXA_HOST=${NEXA_HOST:-0.0.0.0:8080} - - NEXA_KEEPALIVE=${NEXA_KEEPALIVE:-300} - - NEXA_ORIGINS=${NEXA_ORIGINS:-*} - - NEXA_HFTOKEN=${NEXA_HFTOKEN:-} - - NEXA_LOG=${NEXA_LOG:-none} - command: > - nexa server - ${NEXA_MODEL:-gemma-2-2b-instruct} - ipc: host - shm_size: ${NEXA_SHM_SIZE:-2g} - healthcheck: - test: ["CMD", "curl", "-f", "http://localhost:8080/v1/models"] - interval: 30s - timeout: 10s - retries: 3 - start_period: 60s - deploy: - resources: - limits: - cpus: ${NEXA_SDK_CPU_LIMIT:-4.0} - memory: ${NEXA_SDK_MEMORY_LIMIT:-8G} - reservations: - cpus: ${NEXA_SDK_CPU_RESERVATION:-2.0} - memory: ${NEXA_SDK_MEMORY_RESERVATION:-4G} - profiles: - - cpu - - nexa-sdk-cuda: - <<: *defaults - build: - context: . - dockerfile: Dockerfile.cuda - image: ${GLOBAL_REGISTRY:-}alexsuntop/nexa-sdk:${NEXA_SDK_CUDA_VERSION:-0.2.57-cuda} - ports: - - "${NEXA_SDK_PORT_OVERRIDE:-8080}:8080" - volumes: - - nexa_models:/root/.cache/nexa - environment: - - TZ=${TZ:-UTC} - - NEXA_HOST=${NEXA_HOST:-0.0.0.0:8080} - - NEXA_KEEPALIVE=${NEXA_KEEPALIVE:-300} - - NEXA_ORIGINS=${NEXA_ORIGINS:-*} - - NEXA_HFTOKEN=${NEXA_HFTOKEN:-} - - NEXA_LOG=${NEXA_LOG:-none} - command: > - nexa server - ${NEXA_MODEL:-gemma-2-2b-instruct} - -ngl ${NEXA_GPU_LAYERS:--1} - ipc: host - shm_size: ${NEXA_SHM_SIZE:-2g} - healthcheck: - test: ["CMD", "curl", "-f", "http://localhost:8080/v1/models"] - interval: 30s - timeout: 10s - retries: 3 - start_period: 60s - deploy: - resources: - limits: - cpus: ${NEXA_SDK_CPU_LIMIT:-4.0} - memory: ${NEXA_SDK_MEMORY_LIMIT:-8G} - reservations: - cpus: ${NEXA_SDK_CPU_RESERVATION:-2.0} - memory: ${NEXA_SDK_MEMORY_RESERVATION:-4G} - devices: - - driver: nvidia - device_ids: ['0'] - capabilities: [gpu] - profiles: - - cuda - -volumes: - nexa_models: diff --git a/src/nexa-sdk/.env.example b/src/nexa-sdk/.env.example new file mode 100644 index 0000000..5de9563 --- /dev/null +++ b/src/nexa-sdk/.env.example @@ -0,0 +1,20 @@ +# NexaSDK Docker Configuration + +# Image version (e.g., v0.2.62, v0.2.62-cuda, latest, latest-cuda) +NEXA_SDK_VERSION=v0.2.62 + +# Host port for NexaSDK REST API +NEXA_SDK_PORT_OVERRIDE=18181 + +# Nexa API token (required for model access) +# Obtain from https://sdk.nexa.ai -> Deployment -> Create Token +NEXA_TOKEN= + +# Timezone +TZ=UTC + +# Resource limits +NEXA_SDK_CPU_LIMIT=4.0 +NEXA_SDK_MEMORY_LIMIT=8G +NEXA_SDK_CPU_RESERVATION=1.0 +NEXA_SDK_MEMORY_RESERVATION=2G diff --git a/src/nexa-sdk/README.md b/src/nexa-sdk/README.md new file mode 100644 index 0000000..6f06fe6 --- /dev/null +++ b/src/nexa-sdk/README.md @@ -0,0 +1,105 @@ +# NexaSDK + +[English](./README.md) | [中文](./README.zh.md) + +This service deploys NexaSDK Docker for running AI models with OpenAI-compatible REST API. Supports LLM, Embeddings, Reranking, Computer Vision, and ASR models. + +## Features + +- **OpenAI-compatible API**: Drop-in replacement for OpenAI API endpoints +- **Multiple Model Types**: LLM, VLM, Embeddings, Reranking, CV, ASR +- **GPU Acceleration**: CUDA support for NVIDIA GPUs +- **NPU Support**: Optimized for Qualcomm NPU on ARM64 + +## Supported Models + +| Modality | Models | +| ------------- | ------------------------------------------------------- | +| **LLM** | `NexaAI/LFM2-1.2B-npu`, `NexaAI/Granite-4.0-h-350M-NPU` | +| **VLM** | `NexaAI/OmniNeural-4B` | +| **Embedding** | `NexaAI/embeddinggemma-300m-npu`, `NexaAI/EmbedNeural` | +| **Rerank** | `NexaAI/jina-v2-rerank-npu` | +| **CV** | `NexaAI/yolov12-npu`, `NexaAI/convnext-tiny-npu-IoT` | +| **ASR** | `NexaAI/parakeet-tdt-0.6b-v3-npu` | + +## Usage + +### CPU Mode + +```bash +docker compose up -d +``` + +### GPU Mode (CUDA) + +```bash +docker compose --profile gpu up -d nexa-sdk-cuda +``` + +### Pull a Model + +```bash +docker exec -it nexa-sdk nexa pull NexaAI/Granite-4.0-h-350M-NPU +``` + +### Interactive CLI + +```bash +docker exec -it nexa-sdk nexa infer NexaAI/Granite-4.0-h-350M-NPU +``` + +### API Examples + +- Chat completions: + + ```bash + curl -X POST http://localhost:18181/v1/chat/completions \ + -H "Content-Type: application/json" \ + -d '{ + "model": "NexaAI/Granite-4.0-h-350M-NPU", + "messages": [{"role": "user", "content": "Hello!"}] + }' + ``` + +- Embeddings: + + ```bash + curl -X POST http://localhost:18181/v1/embeddings \ + -H "Content-Type: application/json" \ + -d '{ + "model": "NexaAI/EmbedNeural", + "input": "Hello, world!" + }' + ``` + +- Swagger UI: Visit `http://localhost:18181/docs/ui` + +## Services + +- `nexa-sdk`: CPU-based NexaSDK service (default) +- `nexa-sdk-cuda`: GPU-accelerated service with CUDA support (profile: `gpu`) + +## Configuration + +| Variable | Description | Default | +| ------------------------ | ------------------------- | --------- | +| `NEXA_SDK_VERSION` | NexaSDK image version | `v0.2.62` | +| `NEXA_SDK_PORT_OVERRIDE` | Host port for REST API | `18181` | +| `NEXA_TOKEN` | Nexa API token (required) | - | +| `TZ` | Timezone | `UTC` | + +## Volumes + +- `nexa_data`: Volume for storing downloaded models and data + +## Getting a Token + +1. Create an account at [sdk.nexa.ai](https://sdk.nexa.ai) +2. Go to **Deployment → Create Token** +3. Copy the token to your `.env` file + +## References + +- [NexaSDK Documentation](https://docs.nexa.ai/nexa-sdk-docker/overview) +- [Docker Hub](https://hub.docker.com/r/nexa4ai/nexasdk) +- [Supported Models](https://docs.nexa.ai/nexa-sdk-docker/overview#supported-models) diff --git a/src/nexa-sdk/README.zh.md b/src/nexa-sdk/README.zh.md new file mode 100644 index 0000000..c62f76d --- /dev/null +++ b/src/nexa-sdk/README.zh.md @@ -0,0 +1,105 @@ +# NexaSDK + +[English](./README.md) | [中文](./README.zh.md) + +此服务用于部署 NexaSDK Docker，运行兼容 OpenAI 的 REST API 的 AI 模型。支持 LLM、Embeddings、Reranking、计算机视觉和 ASR 模型。 + +## 特性 + +- **OpenAI 兼容 API**：可直接替换 OpenAI API 端点 +- **多种模型类型**：LLM、VLM、Embeddings、Reranking、CV、ASR +- **GPU 加速**：支持 NVIDIA GPU 的 CUDA 加速 +- **NPU 支持**：针对 ARM64 上的 Qualcomm NPU 优化 + +## 支持的模型 + +| 类型 | 模型 | +| ------------- | ------------------------------------------------------- | +| **LLM** | `NexaAI/LFM2-1.2B-npu`、`NexaAI/Granite-4.0-h-350M-NPU` | +| **VLM** | `NexaAI/OmniNeural-4B` | +| **Embedding** | `NexaAI/embeddinggemma-300m-npu`、`NexaAI/EmbedNeural` | +| **Rerank** | `NexaAI/jina-v2-rerank-npu` | +| **CV** | `NexaAI/yolov12-npu`、`NexaAI/convnext-tiny-npu-IoT` | +| **ASR** | `NexaAI/parakeet-tdt-0.6b-v3-npu` | + +## 用法 + +### CPU 模式 + +```bash +docker compose up -d +``` + +### GPU 模式（CUDA） + +```bash +docker compose --profile gpu up -d nexa-sdk-cuda +``` + +### 拉取模型 + +```bash +docker exec -it nexa-sdk nexa pull NexaAI/Granite-4.0-h-350M-NPU +``` + +### 交互式 CLI + +```bash +docker exec -it nexa-sdk nexa infer NexaAI/Granite-4.0-h-350M-NPU +``` + +### API 示例 + +- 聊天补全： + + ```bash + curl -X POST http://localhost:18181/v1/chat/completions \ + -H "Content-Type: application/json" \ + -d '{ + "model": "NexaAI/Granite-4.0-h-350M-NPU", + "messages": [{"role": "user", "content": "Hello!"}] + }' + ``` + +- Embeddings： + + ```bash + curl -X POST http://localhost:18181/v1/embeddings \ + -H "Content-Type: application/json" \ + -d '{ + "model": "NexaAI/EmbedNeural", + "input": "Hello, world!" + }' + ``` + +- Swagger UI：访问 `http://localhost:18181/docs/ui` + +## 服务 + +- `nexa-sdk`：基于 CPU 的 NexaSDK 服务（默认） +- `nexa-sdk-cuda`：支持 CUDA 的 GPU 加速服务（profile：`gpu`） + +## 配置 + +| 变量 | 描述 | 默认值 | +| ------------------------ | --------------------- | --------- | +| `NEXA_SDK_VERSION` | NexaSDK 镜像版本 | `v0.2.62` | +| `NEXA_SDK_PORT_OVERRIDE` | REST API 的主机端口 | `18181` | +| `NEXA_TOKEN` | Nexa API 令牌（必需） | - | +| `TZ` | 时区 | `UTC` | + +## 卷 + +- `nexa_data`：用于存储下载的模型和数据的卷 + +## 获取令牌 + +1. 在 [sdk.nexa.ai](https://sdk.nexa.ai) 创建账户 +2. 进入 **Deployment → Create Token** +3. 将令牌复制到 `.env` 文件中 + +## 参考资料 + +- [NexaSDK 文档](https://docs.nexa.ai/nexa-sdk-docker/overview) +- [Docker Hub](https://hub.docker.com/r/nexa4ai/nexasdk) +- [支持的模型](https://docs.nexa.ai/nexa-sdk-docker/overview#supported-models) diff --git a/src/nexa-sdk/docker-compose.yaml b/src/nexa-sdk/docker-compose.yaml new file mode 100644 index 0000000..4c4678c --- /dev/null +++ b/src/nexa-sdk/docker-compose.yaml @@ -0,0 +1,74 @@ +# NexaSDK Docker Compose Configuration +# OpenAI-compatible API for LLM, Embeddings, Reranking, and more +# Supports both CPU and GPU (CUDA/NPU) acceleration + +x-defaults: &defaults + restart: unless-stopped + logging: + driver: json-file + options: + max-size: 100m + max-file: "3" + +services: + nexa-sdk: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}nexa4ai/nexasdk:${NEXA_SDK_VERSION:-v0.2.62} + ports: + - "${NEXA_SDK_PORT_OVERRIDE:-18181}:18181" + volumes: + - nexa_data:/data + environment: + - TZ=${TZ:-UTC} + - NEXA_TOKEN=${NEXA_TOKEN:-} + command: serve + healthcheck: + test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:18181/docs/ui"] + interval: 30s + timeout: 10s + retries: 3 + start_period: 30s + deploy: + resources: + limits: + cpus: ${NEXA_SDK_CPU_LIMIT:-4.0} + memory: ${NEXA_SDK_MEMORY_LIMIT:-8G} + reservations: + cpus: ${NEXA_SDK_CPU_RESERVATION:-1.0} + memory: ${NEXA_SDK_MEMORY_RESERVATION:-2G} + + # GPU-accelerated service with CUDA support + nexa-sdk-cuda: + <<: *defaults + profiles: + - gpu + image: ${GLOBAL_REGISTRY:-}nexa4ai/nexasdk:${NEXA_SDK_VERSION:-v0.2.62}-cuda + ports: + - "${NEXA_SDK_PORT_OVERRIDE:-18181}:18181" + volumes: + - nexa_data:/data + environment: + - TZ=${TZ:-UTC} + - NEXA_TOKEN=${NEXA_TOKEN:-} + command: serve + healthcheck: + test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:18181/docs/ui"] + interval: 30s + timeout: 10s + retries: 3 + start_period: 60s + deploy: + resources: + limits: + cpus: ${NEXA_SDK_CPU_LIMIT:-8.0} + memory: ${NEXA_SDK_MEMORY_LIMIT:-16G} + reservations: + cpus: ${NEXA_SDK_CPU_RESERVATION:-2.0} + memory: ${NEXA_SDK_MEMORY_RESERVATION:-4G} + devices: + - driver: nvidia + count: 1 + capabilities: [gpu] + +volumes: + nexa_data: diff --git a/src/phoenix/.env.example b/src/phoenix/.env.example new file mode 100644 index 0000000..077f7ee --- /dev/null +++ b/src/phoenix/.env.example @@ -0,0 +1,31 @@ +# Phoenix version +PHOENIX_VERSION=version-12.19.0 + +# Timezone +TZ=UTC + +# Phoenix ports +PHOENIX_PORT_OVERRIDE=6006 # UI and OTLP HTTP collector +PHOENIX_GRPC_PORT_OVERRIDE=4317 # OTLP gRPC collector + +# Phoenix configuration +PHOENIX_ENABLE_PROMETHEUS=false +PHOENIX_SECRET= # Optional: Set for authentication, generate with: openssl rand -base64 32 + +# PostgreSQL configuration +POSTGRES_VERSION=17.2-alpine3.21 +POSTGRES_USER=postgres +POSTGRES_PASSWORD=postgres +POSTGRES_DB=phoenix + +# Resource limits for Phoenix +PHOENIX_CPU_LIMIT=2.0 +PHOENIX_MEMORY_LIMIT=2G +PHOENIX_CPU_RESERVATION=0.5 +PHOENIX_MEMORY_RESERVATION=512M + +# Resource limits for PostgreSQL +PHOENIX_DB_CPU_LIMIT=1.0 +PHOENIX_DB_MEMORY_LIMIT=1G +PHOENIX_DB_CPU_RESERVATION=0.25 +PHOENIX_DB_MEMORY_RESERVATION=256M diff --git a/src/phoenix/README.md b/src/phoenix/README.md new file mode 100644 index 0000000..838ddb3 --- /dev/null +++ b/src/phoenix/README.md @@ -0,0 +1,100 @@ +# Arize Phoenix + +[English](./README.md) | [中文](./README.zh.md) + +Arize Phoenix is an open-source AI observability platform for LLM applications. It provides tracing, evaluation, datasets, and experiments to help you build and improve AI applications. + +## Services + +- `phoenix`: The main Phoenix application server with UI and OpenTelemetry collectors. +- `phoenix-db`: PostgreSQL database for persistent storage. + +## Ports + +| Port | Protocol | Description | +| ---- | -------- | ----------------------------------------- | +| 6006 | HTTP | UI and OTLP HTTP collector (`/v1/traces`) | +| 4317 | gRPC | OTLP gRPC collector | + +## Environment Variables + +| Variable Name | Description | Default Value | +| -------------------------- | ------------------------------------- | ----------------- | +| PHOENIX_VERSION | Phoenix image version | `version-12.19.0` | +| PHOENIX_PORT_OVERRIDE | Host port for Phoenix UI and HTTP API | `6006` | +| PHOENIX_GRPC_PORT_OVERRIDE | Host port for OTLP gRPC collector | `4317` | +| PHOENIX_ENABLE_PROMETHEUS | Enable Prometheus metrics endpoint | `false` | +| PHOENIX_SECRET | Secret for authentication (optional) | `""` | +| POSTGRES_VERSION | PostgreSQL image version | `17.2-alpine3.21` | +| POSTGRES_USER | PostgreSQL username | `postgres` | +| POSTGRES_PASSWORD | PostgreSQL password | `postgres` | +| POSTGRES_DB | PostgreSQL database name | `phoenix` | + +## Volumes + +- `phoenix_db_data`: PostgreSQL data volume for persistent storage. + +## Getting Started + +1. Copy the example environment file: + + ```bash + cp .env.example .env + ``` + +2. (Optional) For production, set a secure password and secret: + + ```bash + # Generate a secret for authentication + openssl rand -base64 32 + ``` + +3. Start the services: + + ```bash + docker compose up -d + ``` + +4. Access Phoenix UI at `http://localhost:6006` + +## Sending Traces + +Phoenix supports OpenTelemetry-compatible traces. You can send traces using: + +### HTTP (OTLP) + +Send traces to `http://localhost:6006/v1/traces` + +### gRPC (OTLP) + +Send traces to `localhost:4317` + +### Python Example + +```python +from phoenix.otel import register + +tracer_provider = register( + project_name="my-llm-app", + endpoint="http://localhost:6006/v1/traces", +) +``` + +## Features + +- **Tracing**: Capture and visualize LLM application traces with OpenTelemetry support. +- **Evaluation**: Run evaluations using built-in or custom evaluators. +- **Datasets**: Create and manage datasets for testing and evaluation. +- **Experiments**: Run experiments to compare model performance. +- **Playground**: Test prompts with different models interactively. + +## Documentation + +For more information, visit the [official Phoenix documentation](https://docs.arize.com/phoenix). + +## Security Notes + +- Change default PostgreSQL password in production. +- Set `PHOENIX_SECRET` for authentication if exposing Phoenix publicly. +- Consider using a reverse proxy with SSL/TLS in production. +- Regularly backup the PostgreSQL database. diff --git a/src/phoenix/README.zh.md b/src/phoenix/README.zh.md new file mode 100644 index 0000000..d15f2d3 --- /dev/null +++ b/src/phoenix/README.zh.md @@ -0,0 +1,100 @@ +# Arize Phoenix + +[English](./README.md) | [中文](./README.zh.md) + +Arize Phoenix 是一个开源的 AI 可观测性平台，专为 LLM 应用设计。它提供追踪、评估、数据集和实验功能，帮助你构建和改进 AI 应用。 + +## 服务 + +- `phoenix`：Phoenix 主应用服务器，包含 UI 和 OpenTelemetry 采集器。 +- `phoenix-db`：用于持久化存储的 PostgreSQL 数据库。 + +## 端口 + +| 端口 | 协议 | 描述 | +| ---- | ---- | -------------------------------------- | +| 6006 | HTTP | UI 和 OTLP HTTP 采集器（`/v1/traces`） | +| 4317 | gRPC | OTLP gRPC 采集器 | + +## 环境变量 + +| 变量名 | 描述 | 默认值 | +| -------------------------- | --------------------------------- | ----------------- | +| PHOENIX_VERSION | Phoenix 镜像版本 | `version-12.19.0` | +| PHOENIX_PORT_OVERRIDE | Phoenix UI 和 HTTP API 的主机端口 | `6006` | +| PHOENIX_GRPC_PORT_OVERRIDE | OTLP gRPC 采集器的主机端口 | `4317` | +| PHOENIX_ENABLE_PROMETHEUS | 启用 Prometheus 指标端点 | `false` | +| PHOENIX_SECRET | 认证密钥（可选） | `""` | +| POSTGRES_VERSION | PostgreSQL 镜像版本 | `17.2-alpine3.21` | +| POSTGRES_USER | PostgreSQL 用户名 | `postgres` | +| POSTGRES_PASSWORD | PostgreSQL 密码 | `postgres` | +| POSTGRES_DB | PostgreSQL 数据库名 | `phoenix` | + +## 数据卷 + +- `phoenix_db_data`：PostgreSQL 数据卷，用于持久化存储。 + +## 快速开始 + +1. 复制示例环境文件： + + ```bash + cp .env.example .env + ``` + +2. （可选）生产环境下，请设置安全的密码和密钥： + + ```bash + # 生成认证密钥 + openssl rand -base64 32 + ``` + +3. 启动服务： + + ```bash + docker compose up -d + ``` + +4. 访问 Phoenix UI：`http://localhost:6006` + +## 发送追踪数据 + +Phoenix 支持 OpenTelemetry 兼容的追踪数据。你可以通过以下方式发送追踪： + +### HTTP（OTLP） + +发送追踪到 `http://localhost:6006/v1/traces` + +### gRPC（OTLP） + +发送追踪到 `localhost:4317` + +### Python 示例 + +```python +from phoenix.otel import register + +tracer_provider = register( + project_name="my-llm-app", + endpoint="http://localhost:6006/v1/traces", +) +``` + +## 功能特性 + +- **追踪**：捕获和可视化 LLM 应用追踪，支持 OpenTelemetry。 +- **评估**：使用内置或自定义评估器运行评估。 +- **数据集**：创建和管理用于测试和评估的数据集。 +- **实验**：运行实验以比较模型性能。 +- **Playground**：交互式测试不同模型的提示词。 + +## 文档 + +更多信息请访问 [Phoenix 官方文档](https://docs.arize.com/phoenix)。 + +## 安全说明 + +- 生产环境请更改默认的 PostgreSQL 密码。 +- 如果公开暴露 Phoenix，请设置 `PHOENIX_SECRET` 进行认证。 +- 生产环境建议使用反向代理并启用 SSL/TLS。 +- 定期备份 PostgreSQL 数据库。 diff --git a/src/phoenix/docker-compose.yaml b/src/phoenix/docker-compose.yaml new file mode 100644 index 0000000..b45c6ba --- /dev/null +++ b/src/phoenix/docker-compose.yaml @@ -0,0 +1,68 @@ +# Arize Phoenix - AI Observability and Evaluation Platform +# https://docs.arize.com/phoenix + +x-defaults: &defaults + restart: unless-stopped + logging: + driver: json-file + options: + max-size: 100m + max-file: "3" + +services: + phoenix: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}arizephoenix/phoenix:${PHOENIX_VERSION:-version-12.19.0} + ports: + - "${PHOENIX_PORT_OVERRIDE:-6006}:6006" # UI and OTLP HTTP collector + - "${PHOENIX_GRPC_PORT_OVERRIDE:-4317}:4317" # OTLP gRPC collector + environment: + - TZ=${TZ:-UTC} + - PHOENIX_SQL_DATABASE_URL=postgresql://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-postgres}@phoenix-db:5432/${POSTGRES_DB:-phoenix} + - PHOENIX_ENABLE_PROMETHEUS=${PHOENIX_ENABLE_PROMETHEUS:-false} + - PHOENIX_SECRET=${PHOENIX_SECRET:-} + depends_on: + phoenix-db: + condition: service_healthy + healthcheck: + test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:6006/healthz"] + interval: 30s + timeout: 10s + retries: 3 + start_period: 30s + deploy: + resources: + limits: + cpus: ${PHOENIX_CPU_LIMIT:-2.0} + memory: ${PHOENIX_MEMORY_LIMIT:-2G} + reservations: + cpus: ${PHOENIX_CPU_RESERVATION:-0.5} + memory: ${PHOENIX_MEMORY_RESERVATION:-512M} + + phoenix-db: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}postgres:${POSTGRES_VERSION:-17.2-alpine3.21} + environment: + - TZ=${TZ:-UTC} + - POSTGRES_USER=${POSTGRES_USER:-postgres} + - POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-postgres} + - POSTGRES_DB=${POSTGRES_DB:-phoenix} + volumes: + - phoenix_db_data:/var/lib/postgresql/data + healthcheck: + test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-postgres}"] + interval: 10s + timeout: 5s + retries: 5 + start_period: 30s + deploy: + resources: + limits: + cpus: ${PHOENIX_DB_CPU_LIMIT:-1.0} + memory: ${PHOENIX_DB_MEMORY_LIMIT:-1G} + reservations: + cpus: ${PHOENIX_DB_CPU_RESERVATION:-0.25} + memory: ${PHOENIX_DB_MEMORY_RESERVATION:-256M} + +volumes: + phoenix_db_data: diff --git a/src/trigger-dev/.env.example b/src/trigger-dev/.env.example new file mode 100644 index 0000000..2218a7b --- /dev/null +++ b/src/trigger-dev/.env.example @@ -0,0 +1,223 @@ +# ============================================================================= +# Trigger.dev Configuration +# ============================================================================= + +# Global settings +TZ=UTC +GLOBAL_REGISTRY= + +# ============================================================================= +# Image Versions +# ============================================================================= + +# Trigger.dev version (webapp and supervisor) +TRIGGER_IMAGE_TAG=v4.2.0 + +# Infrastructure versions +POSTGRES_VERSION=17.2-alpine3.21 +REDIS_VERSION=7.4.3-alpine3.21 +CLICKHOUSE_VERSION=25.3 +MINIO_VERSION=RELEASE.2025-04-22T22-12-26Z +MC_VERSION=RELEASE.2025-04-16T18-13-26Z +ELECTRIC_VERSION=1.0.0 +REGISTRY_IMAGE_VERSION=3 +DOCKER_SOCKET_PROXY_VERSION=0.3.0 + +# ============================================================================= +# Port Configuration +# ============================================================================= + +# Webapp port +TRIGGER_PORT=8030 + +# MinIO ports +MINIO_API_PORT=9000 +MINIO_CONSOLE_PORT=9001 + +# Registry port +REGISTRY_PORT=5000 + +# ============================================================================= +# Required Secrets (MUST be set) +# ============================================================================= + +# Generate with: openssl rand -hex 16 +SESSION_SECRET= +MAGIC_LINK_SECRET= +ENCRYPTION_KEY= + +# Managed worker secret (must match between webapp and supervisor) +MANAGED_WORKER_SECRET=managed-secret + +# PostgreSQL password +POSTGRES_PASSWORD= + +# ============================================================================= +# Domain Configuration +# ============================================================================= + +# Public URLs (change these for production) +APP_ORIGIN=http://localhost:8030 +LOGIN_ORIGIN=http://localhost:8030 +API_ORIGIN=http://localhost:8030 +STREAM_ORIGIN=http://localhost:8030 + +# ============================================================================= +# Database Configuration +# ============================================================================= + +# PostgreSQL +POSTGRES_USER=trigger +POSTGRES_DB=trigger +DATABASE_CONNECTION_LIMIT=10 + +# ============================================================================= +# ClickHouse Configuration +# ============================================================================= + +CLICKHOUSE_DATABASE=default +CLICKHOUSE_USER=default +CLICKHOUSE_PASSWORD=password + +# ============================================================================= +# Object Storage Configuration (MinIO) +# ============================================================================= + +MINIO_ROOT_USER=admin +MINIO_ROOT_PASSWORD=very-safe-password +PACKET_BUCKET_NAME=packets + +# ============================================================================= +# Registry Configuration +# ============================================================================= + +# Registry host (internal) +REGISTRY_HOST=trigger-registry:5000 + +# Registry credentials (generate htpasswd file) +REGISTRY_USER=registry-user +REGISTRY_PASSWORD=very-secure-indeed + +# ============================================================================= +# Authentication Configuration +# ============================================================================= + +# Restrict login to specific email addresses (regex pattern) +# Example: ^(user1@example\.com|user2@example\.com)$ +WHITELISTED_EMAILS= + +# GitHub OAuth (optional) +AUTH_GITHUB_CLIENT_ID= +AUTH_GITHUB_CLIENT_SECRET= + +# ============================================================================= +# Email Configuration (optional) +# ============================================================================= + +# Transport: resend, smtp, or aws-ses +EMAIL_TRANSPORT= + +# Email addresses +FROM_EMAIL= +REPLY_TO_EMAIL= + +# Resend configuration +RESEND_API_KEY= + +# SMTP configuration +SMTP_HOST= +SMTP_PORT=587 +SMTP_SECURE=false +SMTP_USER= +SMTP_PASSWORD= + +# AWS SES (uses AWS_REGION, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY) + +# ============================================================================= +# Telemetry +# ============================================================================= + +# Set to any non-empty value to disable telemetry +TRIGGER_TELEMETRY_DISABLED= + +# ============================================================================= +# Bootstrap Configuration +# ============================================================================= + +# Enable automatic worker group creation +TRIGGER_BOOTSTRAP_ENABLED=true +TRIGGER_BOOTSTRAP_WORKER_GROUP_NAME=bootstrap + +# Worker token (auto-generated on first run, or set manually for remote workers) +# Format: tr_wgt_... (obtained from webapp logs on first run) +TRIGGER_WORKER_TOKEN=file:///home/node/shared/worker_token + +# ============================================================================= +# Supervisor Configuration +# ============================================================================= + +# Worker instance name (unique per supervisor) +TRIGGER_WORKER_INSTANCE_NAME=supervisor-1 +TRIGGER_WORKER_HEARTBEAT_INTERVAL_SECONDS=30 + +# Docker settings +DOCKER_ENFORCE_MACHINE_PRESETS=true +DOCKER_AUTOREMOVE_EXITED_CONTAINERS=true + +# ============================================================================= +# Resource Limits +# ============================================================================= + +# Webapp +WEBAPP_CPU_LIMIT=3.0 +WEBAPP_MEMORY_LIMIT=6G +WEBAPP_CPU_RESERVATION=1.0 +WEBAPP_MEMORY_RESERVATION=2G + +# PostgreSQL +POSTGRES_CPU_LIMIT=2.0 +POSTGRES_MEMORY_LIMIT=4G +POSTGRES_CPU_RESERVATION=0.5 +POSTGRES_MEMORY_RESERVATION=1G + +# Redis +REDIS_CPU_LIMIT=1.0 +REDIS_MEMORY_LIMIT=2G +REDIS_CPU_RESERVATION=0.25 +REDIS_MEMORY_RESERVATION=512M + +# ClickHouse +CLICKHOUSE_CPU_LIMIT=2.0 +CLICKHOUSE_MEMORY_LIMIT=4G +CLICKHOUSE_CPU_RESERVATION=0.5 +CLICKHOUSE_MEMORY_RESERVATION=1G + +# MinIO +MINIO_CPU_LIMIT=1.0 +MINIO_MEMORY_LIMIT=2G +MINIO_CPU_RESERVATION=0.25 +MINIO_MEMORY_RESERVATION=512M + +# Electric +ELECTRIC_CPU_LIMIT=1.0 +ELECTRIC_MEMORY_LIMIT=1G +ELECTRIC_CPU_RESERVATION=0.25 +ELECTRIC_MEMORY_RESERVATION=256M + +# Registry +REGISTRY_CPU_LIMIT=0.5 +REGISTRY_MEMORY_LIMIT=512M +REGISTRY_CPU_RESERVATION=0.1 +REGISTRY_MEMORY_RESERVATION=128M + +# Supervisor +SUPERVISOR_CPU_LIMIT=2.0 +SUPERVISOR_MEMORY_LIMIT=4G +SUPERVISOR_CPU_RESERVATION=0.5 +SUPERVISOR_MEMORY_RESERVATION=1G + +# Docker Socket Proxy +DOCKER_PROXY_CPU_LIMIT=0.5 +DOCKER_PROXY_MEMORY_LIMIT=256M +DOCKER_PROXY_CPU_RESERVATION=0.1 +DOCKER_PROXY_MEMORY_RESERVATION=64M diff --git a/src/trigger-dev/README.md b/src/trigger-dev/README.md new file mode 100644 index 0000000..d89a482 --- /dev/null +++ b/src/trigger-dev/README.md @@ -0,0 +1,247 @@ +# Trigger.dev + +[English](./README.md) | [中文](./README.zh.md) + +Trigger.dev is an open-source platform for building AI workflows and background jobs in TypeScript. It provides long-running tasks with retries, queues, observability, and elastic scaling. + +## Services + +### Core Services (Webapp Stack) + +| Service | Description | +| ----------------------- | --------------------------------------------------- | +| `webapp` | Main Trigger.dev application with dashboard and API | +| `trigger-postgres` | PostgreSQL database with logical replication | +| `trigger-redis` | Redis for cache and job queue | +| `trigger-clickhouse` | ClickHouse for analytics database | +| `trigger-minio` | S3-compatible object storage | +| `trigger-minio-init` | MinIO bucket initialization | +| `electric` | ElectricSQL for real-time sync | +| `trigger-registry` | Private Docker registry for deployed code | +| `trigger-registry-init` | Registry htpasswd initialization | + +### Worker Services (Supervisor Stack) + +| Service | Description | +| --------------------- | ----------------------------------------- | +| `supervisor` | Worker orchestrator that executes tasks | +| `docker-socket-proxy` | Secure Docker socket proxy for supervisor | + +## Prerequisites + +- Docker 20.10.0+ +- Docker Compose 2.20.0+ +- Minimum 6 vCPU and 12 GB RAM for the complete stack + +## Quick Start + +1. Create a `.env` file with required secrets: + + ```bash + cp .env.example .env + ``` + +2. Generate required secrets: + + ```bash + # Generate secrets + echo "SESSION_SECRET=$(openssl rand -hex 16)" >> .env + echo "MAGIC_LINK_SECRET=$(openssl rand -hex 16)" >> .env + echo "ENCRYPTION_KEY=$(openssl rand -hex 16)" >> .env + echo "POSTGRES_PASSWORD=$(openssl rand -hex 16)" >> .env + ``` + +3. Start all services: + + ```bash + docker compose up -d + ``` + +4. Wait for services to be healthy: + + ```bash + docker compose ps + ``` + +5. Access the webapp at `http://localhost:8030` + +6. Get the magic link from webapp logs for first login: + + ```bash + docker compose logs -f webapp + ``` + +## Environment Variables + +### Required Secrets + +| Variable | Description | +| ------------------- | ---------------------------------------------------------- | +| `SESSION_SECRET` | Session encryption secret (run: `openssl rand -hex 16`) | +| `MAGIC_LINK_SECRET` | Magic link encryption secret (run: `openssl rand -hex 16`) | +| `ENCRYPTION_KEY` | Secret store encryption key (run: `openssl rand -hex 16`) | +| `POSTGRES_PASSWORD` | PostgreSQL password | + +### Domain Configuration + +| Variable | Default | Description | +| -------------- | ----------------------- | -------------------------------------- | +| `APP_ORIGIN` | `http://localhost:8030` | Public webapp URL | +| `LOGIN_ORIGIN` | `http://localhost:8030` | Login URL (usually same as APP_ORIGIN) | +| `API_ORIGIN` | `http://localhost:8030` | API URL | + +### Image Versions + +| Variable | Default | Description | +| -------------------- | ------------------------------ | ----------------------------------------- | +| `TRIGGER_IMAGE_TAG` | `v4.2.0` | Trigger.dev webapp and supervisor version | +| `POSTGRES_VERSION` | `17.2-alpine3.21` | PostgreSQL version | +| `REDIS_VERSION` | `7.4.3-alpine3.21` | Redis version | +| `CLICKHOUSE_VERSION` | `25.3` | ClickHouse version | +| `MINIO_VERSION` | `RELEASE.2025-04-22T22-12-26Z` | MinIO version | + +### Port Configuration + +| Variable | Default | Description | +| -------------------- | ------- | -------------------- | +| `TRIGGER_PORT` | `8030` | Webapp port | +| `MINIO_API_PORT` | `9000` | MinIO API port | +| `MINIO_CONSOLE_PORT` | `9001` | MinIO console port | +| `REGISTRY_PORT` | `5000` | Docker registry port | + +### Authentication + +| Variable | Description | +| --------------------------- | ------------------------------------------------------------- | +| `WHITELISTED_EMAILS` | Regex pattern to restrict login (e.g., `^user@example\.com$`) | +| `AUTH_GITHUB_CLIENT_ID` | GitHub OAuth client ID | +| `AUTH_GITHUB_CLIENT_SECRET` | GitHub OAuth client secret | + +### Email Configuration + +| Variable | Default | Description | +| ----------------- | ------- | ---------------------------------------------- | +| `EMAIL_TRANSPORT` | — | Transport type: `resend`, `smtp`, or `aws-ses` | +| `FROM_EMAIL` | — | From email address | +| `RESEND_API_KEY` | — | Resend API key (if using Resend) | +| `SMTP_HOST` | — | SMTP server host | +| `SMTP_PORT` | `587` | SMTP server port | + +## Volumes + +| Volume | Description | +| ------------------------- | -------------------------------- | +| `trigger_shared` | Shared volume for worker token | +| `trigger_postgres_data` | PostgreSQL data | +| `trigger_redis_data` | Redis data | +| `trigger_clickhouse_data` | ClickHouse data | +| `trigger_clickhouse_logs` | ClickHouse logs | +| `trigger_minio_data` | MinIO object storage | +| `trigger_registry_data` | Docker registry data | +| `trigger_registry_auth` | Registry htpasswd authentication | + +## Worker Token + +On first startup, the webapp generates a worker token and saves it to the shared volume. If you need to run workers on separate machines: + +1. Check webapp logs for the token: + + ```bash + docker compose logs webapp | grep -A15 "Worker Token" + ``` + +2. Set the token in the remote worker's `.env`: + + ```bash + TRIGGER_WORKER_TOKEN=tr_wgt_xxxxx + ``` + +## Registry Setup + +The built-in registry uses htpasswd authentication. The htpasswd file is **automatically generated** on first startup using the credentials from environment variables. + +Default credentials: + +- Username: `registry-user` (set via `REGISTRY_USER`) +- Password: `very-secure-indeed` (set via `REGISTRY_PASSWORD`) + +To use custom credentials, set them in your `.env` file before first run: + +```bash +REGISTRY_USER=my-user +REGISTRY_PASSWORD=my-secure-password +``` + +Before deploying tasks, login to the registry: + +```bash +docker login -u registry-user localhost:5000 +``` + +## CLI Usage + +To initialize a project with self-hosted Trigger.dev: + +```bash +npx trigger.dev@latest login -a http://localhost:8030 +npx trigger.dev@latest init -p -a http://localhost:8030 +``` + +To deploy tasks: + +```bash +npx trigger.dev@latest deploy --self-hosted +``` + +## GitHub OAuth Setup + +1. Create a GitHub OAuth App at `https://github.com/settings/developers` +2. Set callback URL: `http://localhost:8030/auth/github/callback` +3. Configure environment variables: + + ```env + AUTH_GITHUB_CLIENT_ID=your_client_id + AUTH_GITHUB_CLIENT_SECRET=your_client_secret + ``` + +## Production Considerations + +- Use strong, unique passwords for all secrets +- Set up proper TLS/SSL with a reverse proxy +- Configure email transport for magic links +- Use external managed databases for high availability +- Set appropriate resource limits based on your workload +- Enable `WHITELISTED_EMAILS` to restrict access +- Consider disabling telemetry: `TRIGGER_TELEMETRY_DISABLED=1` + +## Scaling Workers + +To add more worker capacity: + +1. Set up additional supervisor instances on different machines +2. Configure each with the same `TRIGGER_WORKER_TOKEN` +3. Use unique `TRIGGER_WORKER_INSTANCE_NAME` for each + +## Troubleshooting + +### Magic links not arriving + +- Check webapp logs: `docker compose logs -f webapp` +- Magic links are logged if no email transport is configured +- Set up email transport for production use + +### Deployment fails at push step + +- Ensure you're logged into the registry: `docker login localhost:5000` +- Check registry is healthy: `docker compose ps trigger-registry` + +### Services not starting + +- Ensure all required secrets are set in `.env` +- Check logs: `docker compose logs -f` + +## References + +- [Trigger.dev Documentation](https://trigger.dev/docs) +- [Self-hosting Guide](https://trigger.dev/docs/self-hosting/docker) +- [GitHub Repository](https://github.com/triggerdotdev/trigger.dev) diff --git a/src/trigger-dev/README.zh.md b/src/trigger-dev/README.zh.md new file mode 100644 index 0000000..62dab14 --- /dev/null +++ b/src/trigger-dev/README.zh.md @@ -0,0 +1,247 @@ +# Trigger.dev + +[English](./README.md) | [中文](./README.zh.md) + +Trigger.dev 是一个开源平台，用于在 TypeScript 中构建 AI 工作流和后台任务。它提供长时间运行的任务、重试机制、队列、可观测性和弹性扩展功能。 + +## 服务组件 + +### 核心服务（Webapp 栈） + +| 服务 | 描述 | +| ----------------------- | ----------------------------------------- | +| `webapp` | 主 Trigger.dev 应用程序，包含仪表板和 API | +| `trigger-postgres` | 带有逻辑复制的 PostgreSQL 数据库 | +| `trigger-redis` | 用于缓存和任务队列的 Redis | +| `trigger-clickhouse` | 用于分析的 ClickHouse 数据库 | +| `trigger-minio` | S3 兼容的对象存储 | +| `trigger-minio-init` | MinIO 存储桶初始化 | +| `electric` | 用于实时同步的 ElectricSQL | +| `trigger-registry` | 用于部署代码的私有 Docker 镜像仓库 | +| `trigger-registry-init` | 镜像仓库 htpasswd 初始化 | + +### Worker 服务（Supervisor 栈） + +| 服务 | 描述 | +| --------------------- | ------------------------------------------- | +| `supervisor` | 执行任务的 Worker 编排器 | +| `docker-socket-proxy` | 为 supervisor 提供安全的 Docker socket 代理 | + +## 前置要求 + +- Docker 20.10.0+ +- Docker Compose 2.20.0+ +- 完整栈至少需要 6 vCPU 和 12 GB RAM + +## 快速开始 + +1. 创建包含必要密钥的 `.env` 文件： + + ```bash + cp .env.example .env + ``` + +2. 生成必要的密钥： + + ```bash + # 生成密钥 + echo "SESSION_SECRET=$(openssl rand -hex 16)" >> .env + echo "MAGIC_LINK_SECRET=$(openssl rand -hex 16)" >> .env + echo "ENCRYPTION_KEY=$(openssl rand -hex 16)" >> .env + echo "POSTGRES_PASSWORD=$(openssl rand -hex 16)" >> .env + ``` + +3. 启动所有服务： + + ```bash + docker compose up -d + ``` + +4. 等待服务健康运行： + + ```bash + docker compose ps + ``` + +5. 访问 `http://localhost:8030` 打开 webapp + +6. 从 webapp 日志中获取首次登录的 magic link： + + ```bash + docker compose logs -f webapp + ``` + +## 环境变量 + +### 必需的密钥 + +| 变量 | 描述 | +| ------------------- | --------------------------------------------------- | +| `SESSION_SECRET` | 会话加密密钥（运行：`openssl rand -hex 16`） | +| `MAGIC_LINK_SECRET` | Magic link 加密密钥（运行：`openssl rand -hex 16`） | +| `ENCRYPTION_KEY` | 密钥存储加密密钥（运行：`openssl rand -hex 16`） | +| `POSTGRES_PASSWORD` | PostgreSQL 密码 | + +### 域名配置 + +| 变量 | 默认值 | 描述 | +| -------------- | ----------------------- | ---------------------------------- | +| `APP_ORIGIN` | `http://localhost:8030` | 公开的 webapp URL | +| `LOGIN_ORIGIN` | `http://localhost:8030` | 登录 URL（通常与 APP_ORIGIN 相同） | +| `API_ORIGIN` | `http://localhost:8030` | API URL | + +### 镜像版本 + +| 变量 | 默认值 | 描述 | +| -------------------- | ------------------------------ | ------------------------------------- | +| `TRIGGER_IMAGE_TAG` | `v4.2.0` | Trigger.dev webapp 和 supervisor 版本 | +| `POSTGRES_VERSION` | `17.2-alpine3.21` | PostgreSQL 版本 | +| `REDIS_VERSION` | `7.4.3-alpine3.21` | Redis 版本 | +| `CLICKHOUSE_VERSION` | `25.3` | ClickHouse 版本 | +| `MINIO_VERSION` | `RELEASE.2025-04-22T22-12-26Z` | MinIO 版本 | + +### 端口配置 + +| 变量 | 默认值 | 描述 | +| -------------------- | ------ | ------------------- | +| `TRIGGER_PORT` | `8030` | Webapp 端口 | +| `MINIO_API_PORT` | `9000` | MinIO API 端口 | +| `MINIO_CONSOLE_PORT` | `9001` | MinIO 控制台端口 | +| `REGISTRY_PORT` | `5000` | Docker 镜像仓库端口 | + +### 身份认证 + +| 变量 | 描述 | +| --------------------------- | --------------------------------------------------- | +| `WHITELISTED_EMAILS` | 限制登录的正则表达式（例如：`^user@example\.com$`） | +| `AUTH_GITHUB_CLIENT_ID` | GitHub OAuth 客户端 ID | +| `AUTH_GITHUB_CLIENT_SECRET` | GitHub OAuth 客户端密钥 | + +### 邮件配置 + +| 变量 | 默认值 | 描述 | +| ----------------- | ------ | --------------------------------------- | +| `EMAIL_TRANSPORT` | — | 传输类型：`resend`、`smtp` 或 `aws-ses` | +| `FROM_EMAIL` | — | 发件人邮箱地址 | +| `RESEND_API_KEY` | — | Resend API 密钥（如果使用 Resend） | +| `SMTP_HOST` | — | SMTP 服务器主机 | +| `SMTP_PORT` | `587` | SMTP 服务器端口 | + +## 数据卷 + +| 卷 | 描述 | +| ------------------------- | ---------------------- | +| `trigger_shared` | Worker token 共享卷 | +| `trigger_postgres_data` | PostgreSQL 数据 | +| `trigger_redis_data` | Redis 数据 | +| `trigger_clickhouse_data` | ClickHouse 数据 | +| `trigger_clickhouse_logs` | ClickHouse 日志 | +| `trigger_minio_data` | MinIO 对象存储 | +| `trigger_registry_data` | Docker 镜像仓库数据 | +| `trigger_registry_auth` | 镜像仓库 htpasswd 认证 | + +## Worker Token + +首次启动时，webapp 会生成 worker token 并保存到共享卷中。如果需要在单独的机器上运行 worker： + +1. 从 webapp 日志中获取 token： + + ```bash + docker compose logs webapp | grep -A15 "Worker Token" + ``` + +2. 在远程 worker 的 `.env` 中设置 token： + + ```bash + TRIGGER_WORKER_TOKEN=tr_wgt_xxxxx + ``` + +## 镜像仓库设置 + +内置镜像仓库使用 htpasswd 认证。htpasswd 文件在首次启动时会根据环境变量中的凭据**自动生成**。 + +默认凭据： + +- 用户名：`registry-user`（通过 `REGISTRY_USER` 设置） +- 密码：`very-secure-indeed`（通过 `REGISTRY_PASSWORD` 设置） + +要使用自定义凭据，请在首次运行前在 `.env` 文件中设置： + +```bash +REGISTRY_USER=my-user +REGISTRY_PASSWORD=my-secure-password +``` + +部署任务前，登录到镜像仓库： + +```bash +docker login -u registry-user localhost:5000 +``` + +## CLI 使用 + +使用自托管的 Trigger.dev 初始化项目： + +```bash +npx trigger.dev@latest login -a http://localhost:8030 +npx trigger.dev@latest init -p -a http://localhost:8030 +``` + +部署任务： + +```bash +npx trigger.dev@latest deploy --self-hosted +``` + +## GitHub OAuth 设置 + +1. 在 `https://github.com/settings/developers` 创建 GitHub OAuth 应用 +2. 设置回调 URL：`http://localhost:8030/auth/github/callback` +3. 配置环境变量： + + ```env + AUTH_GITHUB_CLIENT_ID=your_client_id + AUTH_GITHUB_CLIENT_SECRET=your_client_secret + ``` + +## 生产环境注意事项 + +- 为所有密钥使用强且唯一的密码 +- 使用反向代理设置正确的 TLS/SSL +- 配置邮件传输以发送 magic link +- 使用外部托管数据库以实现高可用性 +- 根据工作负载设置适当的资源限制 +- 启用 `WHITELISTED_EMAILS` 限制访问 +- 考虑禁用遥测：`TRIGGER_TELEMETRY_DISABLED=1` + +## 扩展 Worker + +添加更多 worker 容量： + +1. 在不同机器上设置额外的 supervisor 实例 +2. 为每个实例配置相同的 `TRIGGER_WORKER_TOKEN` +3. 为每个实例使用唯一的 `TRIGGER_WORKER_INSTANCE_NAME` + +## 故障排除 + +### Magic link 未收到 + +- 检查 webapp 日志：`docker compose logs -f webapp` +- 如果未配置邮件传输，magic link 会记录在日志中 +- 生产环境请设置邮件传输 + +### 部署在 push 步骤失败 + +- 确保已登录镜像仓库：`docker login localhost:5000` +- 检查镜像仓库健康状态：`docker compose ps trigger-registry` + +### 服务无法启动 + +- 确保 `.env` 中设置了所有必需的密钥 +- 检查日志：`docker compose logs -f` + +## 参考链接 + +- [Trigger.dev 文档](https://trigger.dev/docs) +- [自托管指南](https://trigger.dev/docs/self-hosting/docker) +- [GitHub 仓库](https://github.com/triggerdotdev/trigger.dev) diff --git a/src/trigger-dev/docker-compose.yaml b/src/trigger-dev/docker-compose.yaml new file mode 100644 index 0000000..5555560 --- /dev/null +++ b/src/trigger-dev/docker-compose.yaml @@ -0,0 +1,400 @@ +# Trigger.dev - Build and deploy fully-managed AI agents and workflows +# https://trigger.dev/ +# Repository: https://github.com/triggerdotdev/trigger.dev + +x-defaults: &defaults + restart: unless-stopped + logging: + driver: json-file + options: + max-size: 100m + max-file: "3" + +services: + # ============================================================================= + # Core Services (Webapp Stack) + # ============================================================================= + + webapp: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}ghcr.io/triggerdotdev/trigger.dev:${TRIGGER_IMAGE_TAG:-v4.2.0} + ports: + - "${TRIGGER_PORT:-8030}:3030" + environment: + - TZ=${TZ:-UTC} + # Secrets (required) + - SESSION_SECRET=${SESSION_SECRET} + - MAGIC_LINK_SECRET=${MAGIC_LINK_SECRET} + - ENCRYPTION_KEY=${ENCRYPTION_KEY} + - MANAGED_WORKER_SECRET=${MANAGED_WORKER_SECRET:-managed-secret} + # Domains & ports + - REMIX_APP_PORT=3030 + - APP_ORIGIN=${APP_ORIGIN:-http://localhost:8030} + - LOGIN_ORIGIN=${LOGIN_ORIGIN:-http://localhost:8030} + - API_ORIGIN=${API_ORIGIN:-http://localhost:8030} + - STREAM_ORIGIN=${STREAM_ORIGIN:-http://localhost:8030} + - ELECTRIC_ORIGIN=http://electric:3000 + # Database + - DATABASE_URL=postgresql://${POSTGRES_USER:-trigger}:${POSTGRES_PASSWORD}@trigger-postgres:5432/${POSTGRES_DB:-trigger}?schema=public + - DIRECT_URL=postgresql://${POSTGRES_USER:-trigger}:${POSTGRES_PASSWORD}@trigger-postgres:5432/${POSTGRES_DB:-trigger}?schema=public + - DATABASE_CONNECTION_LIMIT=${DATABASE_CONNECTION_LIMIT:-10} + # Redis + - REDIS_HOST=trigger-redis + - REDIS_PORT=6379 + - REDIS_TLS_DISABLED=true + # ClickHouse + - CLICKHOUSE_URL=http://trigger-clickhouse:8123 + - CLICKHOUSE_USER=${CLICKHOUSE_USER:-default} + - CLICKHOUSE_PASSWORD=${CLICKHOUSE_PASSWORD:-password} + - CLICKHOUSE_DATABASE=${CLICKHOUSE_DATABASE:-default} + # Object storage (MinIO) + - OBJECT_STORE_BASE_URL=http://trigger-minio:9000 + - OBJECT_STORE_ACCESS_KEY_ID=${MINIO_ROOT_USER:-admin} + - OBJECT_STORE_SECRET_ACCESS_KEY=${MINIO_ROOT_PASSWORD:-very-safe-password} + - PACKET_BUCKET_NAME=${PACKET_BUCKET_NAME:-packets} + # Registry + - DEPLOY_REGISTRY_HOST=${REGISTRY_HOST:-trigger-registry:5000} + - DEPLOY_REGISTRY_NAMESPACE=trigger + # Authentication + - WHITELISTED_EMAILS=${WHITELISTED_EMAILS:-} + - AUTH_GITHUB_CLIENT_ID=${AUTH_GITHUB_CLIENT_ID:-} + - AUTH_GITHUB_CLIENT_SECRET=${AUTH_GITHUB_CLIENT_SECRET:-} + # Email (optional) + - EMAIL_TRANSPORT=${EMAIL_TRANSPORT:-} + - FROM_EMAIL=${FROM_EMAIL:-} + - REPLY_TO_EMAIL=${REPLY_TO_EMAIL:-} + - RESEND_API_KEY=${RESEND_API_KEY:-} + - SMTP_HOST=${SMTP_HOST:-} + - SMTP_PORT=${SMTP_PORT:-587} + - SMTP_SECURE=${SMTP_SECURE:-false} + - SMTP_USER=${SMTP_USER:-} + - SMTP_PASSWORD=${SMTP_PASSWORD:-} + # Telemetry + - TRIGGER_TELEMETRY_DISABLED=${TRIGGER_TELEMETRY_DISABLED:-} + # Bootstrap + - TRIGGER_BOOTSTRAP_ENABLED=${TRIGGER_BOOTSTRAP_ENABLED:-true} + - TRIGGER_BOOTSTRAP_WORKER_GROUP_NAME=${TRIGGER_BOOTSTRAP_WORKER_GROUP_NAME:-bootstrap} + - TRIGGER_BOOTSTRAP_WORKER_TOKEN_PATH=/home/node/shared/worker_token + volumes: + - trigger_shared:/home/node/shared + depends_on: + trigger-postgres: + condition: service_healthy + trigger-redis: + condition: service_healthy + trigger-clickhouse: + condition: service_healthy + trigger-minio: + condition: service_healthy + electric: + condition: service_healthy + healthcheck: + test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3030/healthcheck"] + interval: 30s + timeout: 10s + retries: 5 + start_period: 60s + deploy: + resources: + limits: + cpus: ${WEBAPP_CPU_LIMIT:-3.0} + memory: ${WEBAPP_MEMORY_LIMIT:-6G} + reservations: + cpus: ${WEBAPP_CPU_RESERVATION:-1.0} + memory: ${WEBAPP_MEMORY_RESERVATION:-2G} + + trigger-postgres: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}postgres:${POSTGRES_VERSION:-17.2-alpine3.21} + command: + - postgres + - -c + - wal_level=logical + - -c + - max_replication_slots=10 + - -c + - max_wal_senders=10 + environment: + - TZ=${TZ:-UTC} + - POSTGRES_USER=${POSTGRES_USER:-trigger} + - POSTGRES_PASSWORD=${POSTGRES_PASSWORD} + - POSTGRES_DB=${POSTGRES_DB:-trigger} + volumes: + - trigger_postgres_data:/var/lib/postgresql/data + healthcheck: + test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-trigger} -d ${POSTGRES_DB:-trigger}"] + interval: 10s + timeout: 5s + retries: 5 + start_period: 30s + deploy: + resources: + limits: + cpus: ${POSTGRES_CPU_LIMIT:-2.0} + memory: ${POSTGRES_MEMORY_LIMIT:-4G} + reservations: + cpus: ${POSTGRES_CPU_RESERVATION:-0.5} + memory: ${POSTGRES_MEMORY_RESERVATION:-1G} + + trigger-redis: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}redis:${REDIS_VERSION:-7.4.3-alpine3.21} + command: redis-server --appendonly yes + volumes: + - trigger_redis_data:/data + healthcheck: + test: ["CMD", "redis-cli", "ping"] + interval: 10s + timeout: 5s + retries: 5 + start_period: 10s + deploy: + resources: + limits: + cpus: ${REDIS_CPU_LIMIT:-1.0} + memory: ${REDIS_MEMORY_LIMIT:-2G} + reservations: + cpus: ${REDIS_CPU_RESERVATION:-0.25} + memory: ${REDIS_MEMORY_RESERVATION:-512M} + + trigger-clickhouse: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}clickhouse/clickhouse-server:${CLICKHOUSE_VERSION:-25.3} + environment: + - TZ=${TZ:-UTC} + - CLICKHOUSE_DB=${CLICKHOUSE_DATABASE:-default} + - CLICKHOUSE_USER=${CLICKHOUSE_USER:-default} + - CLICKHOUSE_PASSWORD=${CLICKHOUSE_PASSWORD:-password} + - CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT=1 + volumes: + - trigger_clickhouse_data:/var/lib/clickhouse + - trigger_clickhouse_logs:/var/log/clickhouse-server + healthcheck: + test: ["CMD", "wget", "--no-verbose", "--tries=1", "-O-", "http://localhost:8123/ping"] + interval: 10s + timeout: 5s + retries: 5 + start_period: 30s + deploy: + resources: + limits: + cpus: ${CLICKHOUSE_CPU_LIMIT:-2.0} + memory: ${CLICKHOUSE_MEMORY_LIMIT:-4G} + reservations: + cpus: ${CLICKHOUSE_CPU_RESERVATION:-0.5} + memory: ${CLICKHOUSE_MEMORY_RESERVATION:-1G} + + trigger-minio: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}minio/minio:${MINIO_VERSION:-RELEASE.2025-04-22T22-12-26Z} + command: server /data --console-address ":9001" + ports: + - "${MINIO_API_PORT:-9000}:9000" + - "${MINIO_CONSOLE_PORT:-9001}:9001" + environment: + - TZ=${TZ:-UTC} + - MINIO_ROOT_USER=${MINIO_ROOT_USER:-admin} + - MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD:-very-safe-password} + volumes: + - trigger_minio_data:/data + healthcheck: + test: ["CMD", "mc", "ready", "local"] + interval: 10s + timeout: 5s + retries: 5 + start_period: 10s + deploy: + resources: + limits: + cpus: ${MINIO_CPU_LIMIT:-1.0} + memory: ${MINIO_MEMORY_LIMIT:-2G} + reservations: + cpus: ${MINIO_CPU_RESERVATION:-0.25} + memory: ${MINIO_MEMORY_RESERVATION:-512M} + + # MinIO bucket initialization + trigger-minio-init: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}minio/mc:${MC_VERSION:-RELEASE.2025-04-16T18-13-26Z} + entrypoint: | + /bin/sh -c ' + sleep 5 + mc alias set myminio http://trigger-minio:9000 ${MINIO_ROOT_USER:-admin} ${MINIO_ROOT_PASSWORD:-very-safe-password} + mc mb myminio/${PACKET_BUCKET_NAME:-packets} --ignore-existing + echo "MinIO bucket initialized" + exit 0 + ' + depends_on: + trigger-minio: + condition: service_healthy + restart: "no" + + electric: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}electricsql/electric:${ELECTRIC_VERSION:-1.0.0} + environment: + - TZ=${TZ:-UTC} + - DATABASE_URL=postgresql://${POSTGRES_USER:-trigger}:${POSTGRES_PASSWORD}@trigger-postgres:5432/${POSTGRES_DB:-trigger} + depends_on: + trigger-postgres: + condition: service_healthy + healthcheck: + test: ["CMD", "curl", "-f", "http://localhost:3000/v1/health"] + interval: 10s + timeout: 5s + retries: 5 + start_period: 30s + deploy: + resources: + limits: + cpus: ${ELECTRIC_CPU_LIMIT:-1.0} + memory: ${ELECTRIC_MEMORY_LIMIT:-1G} + reservations: + cpus: ${ELECTRIC_CPU_RESERVATION:-0.25} + memory: ${ELECTRIC_MEMORY_RESERVATION:-256M} + + # Initialize registry htpasswd file on first run + trigger-registry-init: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}httpd:2-alpine + entrypoint: | + /bin/sh -c ' + if [ ! -f /auth/htpasswd ]; then + echo "Generating htpasswd file..." + htpasswd -nbB "${REGISTRY_USER:-registry-user}" "${REGISTRY_PASSWORD:-very-secure-indeed}" > /auth/htpasswd + echo "htpasswd file created successfully" + else + echo "htpasswd file already exists, skipping..." + fi + ' + environment: + - REGISTRY_USER=${REGISTRY_USER:-registry-user} + - REGISTRY_PASSWORD=${REGISTRY_PASSWORD:-very-secure-indeed} + volumes: + - trigger_registry_auth:/auth + restart: "no" + + trigger-registry: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}registry:${REGISTRY_IMAGE_VERSION:-3} + ports: + - "${REGISTRY_PORT:-5000}:5000" + environment: + - TZ=${TZ:-UTC} + - REGISTRY_AUTH=htpasswd + - REGISTRY_AUTH_HTPASSWD_REALM=Registry + - REGISTRY_AUTH_HTPASSWD_PATH=/auth/htpasswd + - REGISTRY_STORAGE_DELETE_ENABLED=true + volumes: + - trigger_registry_data:/var/lib/registry + - trigger_registry_auth:/auth:ro + depends_on: + trigger-registry-init: + condition: service_completed_successfully + healthcheck: + test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:5000/v2/"] + interval: 30s + timeout: 10s + retries: 3 + start_period: 10s + deploy: + resources: + limits: + cpus: ${REGISTRY_CPU_LIMIT:-0.5} + memory: ${REGISTRY_MEMORY_LIMIT:-512M} + reservations: + cpus: ${REGISTRY_CPU_RESERVATION:-0.1} + memory: ${REGISTRY_MEMORY_RESERVATION:-128M} + + # ============================================================================= + # Worker Services (Supervisor Stack) + # ============================================================================= + + supervisor: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}ghcr.io/triggerdotdev/supervisor:${TRIGGER_IMAGE_TAG:-v4.2.0} + environment: + - TZ=${TZ:-UTC} + # Required settings + - TRIGGER_API_URL=http://webapp:3030 + - TRIGGER_WORKER_TOKEN=${TRIGGER_WORKER_TOKEN:-file:///home/node/shared/worker_token} + - MANAGED_WORKER_SECRET=${MANAGED_WORKER_SECRET:-managed-secret} + - OTEL_EXPORTER_OTLP_ENDPOINT=http://webapp:3030/otel + # Worker instance + - TRIGGER_WORKER_INSTANCE_NAME=${TRIGGER_WORKER_INSTANCE_NAME:-supervisor-1} + - TRIGGER_WORKER_HEARTBEAT_INTERVAL_SECONDS=${TRIGGER_WORKER_HEARTBEAT_INTERVAL_SECONDS:-30} + # Workload API settings + - TRIGGER_WORKLOAD_API_ENABLED=true + - TRIGGER_WORKLOAD_API_PROTOCOL=http + - TRIGGER_WORKLOAD_API_PORT_INTERNAL=8020 + - TRIGGER_WORKLOAD_API_PORT_EXTERNAL=8020 + # Docker settings + - DOCKER_RUNNER_NETWORKS=trigger-dev_default + - DOCKER_ENFORCE_MACHINE_PRESETS=${DOCKER_ENFORCE_MACHINE_PRESETS:-true} + - DOCKER_AUTOREMOVE_EXITED_CONTAINERS=${DOCKER_AUTOREMOVE_EXITED_CONTAINERS:-true} + volumes: + - trigger_shared:/home/node/shared:ro + depends_on: + webapp: + condition: service_healthy + docker-socket-proxy: + condition: service_started + deploy: + resources: + limits: + cpus: ${SUPERVISOR_CPU_LIMIT:-2.0} + memory: ${SUPERVISOR_MEMORY_LIMIT:-4G} + reservations: + cpus: ${SUPERVISOR_CPU_RESERVATION:-0.5} + memory: ${SUPERVISOR_MEMORY_RESERVATION:-1G} + + docker-socket-proxy: + <<: *defaults + image: ${GLOBAL_REGISTRY:-}tecnativa/docker-socket-proxy:${DOCKER_SOCKET_PROXY_VERSION:-0.3.0} + privileged: true + environment: + - TZ=${TZ:-UTC} + # Allowed API endpoints + - CONTAINERS=1 + - IMAGES=1 + - NETWORKS=1 + - VOLUMES=1 + - AUTH=1 + - POST=1 + - BUILD=0 + - COMMIT=0 + - CONFIGS=0 + - DISTRIBUTION=1 + - EXEC=0 + - GRPC=0 + - INFO=1 + - NODES=0 + - PING=1 + - PLUGINS=0 + - SECRETS=0 + - SERVICES=0 + - SESSION=0 + - SWARM=0 + - SYSTEM=0 + - TASKS=0 + - VERSION=1 + volumes: + - /var/run/docker.sock:/var/run/docker.sock:ro + deploy: + resources: + limits: + cpus: ${DOCKER_PROXY_CPU_LIMIT:-0.5} + memory: ${DOCKER_PROXY_MEMORY_LIMIT:-256M} + reservations: + cpus: ${DOCKER_PROXY_CPU_RESERVATION:-0.1} + memory: ${DOCKER_PROXY_MEMORY_RESERVATION:-64M} + +volumes: + trigger_shared: + trigger_postgres_data: + trigger_redis_data: + trigger_clickhouse_data: + trigger_clickhouse_logs: + trigger_minio_data: + trigger_registry_data: + trigger_registry_auth: