feat: add FalkorDB, LMDeploy, and Pogocache with configuration files and documentation

2026-01-20 14:18:28 +08:00
parent 1c528c0e64
commit 2a010843d1
14 changed files with 384 additions and 0 deletions
--- a/src/falkordb/.env.example
+++ b/src/falkordb/.env.example
@@ -0,0 +1,18 @@
+# FalkorDB Version
+# Latest stable version can be found at https://hub.docker.com/r/falkordb/falkordb/tags
+FALKORDB_VERSION=v4.14.11
+
+# Port configuration
+# Port for Redis protocol (Graph Database)
+FALKORDB_PORT_OVERRIDE=6379
+# Port for FalkorDB Browser UI
+FALKORDB_BROWSER_PORT_OVERRIDE=3000
+
+# Resource limits
+FALKORDB_CPU_LIMIT=1.00
+FALKORDB_MEMORY_LIMIT=2G
+FALKORDB_CPU_RESERVATION=0.25
+FALKORDB_MEMORY_RESERVATION=512M
+
+# Timezone
+TZ=UTC
--- a/src/falkordb/README.md
+++ b/src/falkordb/README.md
@@ -0,0 +1,31 @@
+# FalkorDB
+
+[FalkorDB](https://falkordb.com/) is a low-latency property graph database that leverages sparse matrices and linear algebra for high-performance graph queries. It is a community-driven fork of RedisGraph, optimized for large-scale knowledge graphs and AI-powered applications.
+
+## Getting Started
+
+1. Copy `.env.example` to `.env` and adjust the configuration as needed.
+2. Start the service:
+
+   ```bash
+   docker compose up -d
+   ```
+
+3. Access the FalkorDB Browser at `http://localhost:3000`.
+4. Connect to the database using `redis-cli` or any Redis-compatible client on port `6379`.
+
+## Environment Variables
+
+| Variable                         | Description                  | Default    |
+| -------------------------------- | ---------------------------- | ---------- |
+| `FALKORDB_VERSION`               | Version of FalkorDB image    | `v4.14.11` |
+| `FALKORDB_PORT_OVERRIDE`         | Host port for Redis protocol | `6379`     |
+| `FALKORDB_BROWSER_PORT_OVERRIDE` | Host port for Browser UI     | `3000`     |
+| `FALKORDB_CPU_LIMIT`             | Maximum CPU cycles           | `1.00`     |
+| `FALKORDB_MEMORY_LIMIT`          | Maximum memory               | `2G`       |
+
+## Resources
+
+- [Official Documentation](https://docs.falkordb.com/)
+- [GitHub Repository](https://github.com/FalkorDB/FalkorDB)
+- [Docker Hub](https://hub.docker.com/r/falkordb/falkordb)
--- a/src/falkordb/README.zh.md
+++ b/src/falkordb/README.zh.md
@@ -0,0 +1,31 @@
+# FalkorDB
+
+[FalkorDB](https://falkordb.com/) 是一个低延迟的属性图数据库，利用稀疏矩阵和线性代数实现高性能图查询。它是 RedisGraph 的社区驱动分支，针对大规模知识图谱和 AI 驱动的应用进行了优化。
+
+## 快速开始
+
+1. 将 `.env.example` 复制为 `.env` 并根据需要调整配置。
+2. 启动服务：
+
+   ```bash
+   docker compose up -d
+   ```
+
+3. 通过 `http://localhost:3000` 访问 FalkorDB Browser 界面。
+4. 使用 `redis-cli` 或任何兼容 Redis 的客户端连接到 `6379` 端口。
+
+## 环境变量
+
+| 变量名                           | 描述                 | 默认值     |
+| -------------------------------- | -------------------- | ---------- |
+| `FALKORDB_VERSION`               | FalkorDB 镜像版本    | `v4.14.11` |
+| `FALKORDB_PORT_OVERRIDE`         | Redis 协议的主机端口 | `6379`     |
+| `FALKORDB_BROWSER_PORT_OVERRIDE` | 浏览器界面的主机端口 | `3000`     |
+| `FALKORDB_CPU_LIMIT`             | 最大 CPU 使用率      | `1.00`     |
+| `FALKORDB_MEMORY_LIMIT`          | 最大内存限制         | `2G`       |
+
+## 相关资源
+
+- [官方文档](https://docs.falkordb.com/)
+- [GitHub 仓库](https://github.com/FalkorDB/FalkorDB)
+- [Docker Hub](https://hub.docker.com/r/falkordb/falkordb)
--- a/src/falkordb/docker-compose.yaml
+++ b/src/falkordb/docker-compose.yaml
@@ -0,0 +1,36 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  falkordb:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}falkordb/falkordb:${FALKORDB_VERSION:-v4.14.11}
+    ports:
+      - "${FALKORDB_PORT_OVERRIDE:-6379}:6379"
+      - "${FALKORDB_BROWSER_PORT_OVERRIDE:-3000}:3000"
+    volumes:
+      - falkordb_data:/data
+    environment:
+      - TZ=${TZ:-UTC}
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 10s
+    deploy:
+      resources:
+        limits:
+          cpus: ${FALKORDB_CPU_LIMIT:-1.00}
+          memory: ${FALKORDB_MEMORY_LIMIT:-2G}
+        reservations:
+          cpus: ${FALKORDB_CPU_RESERVATION:-0.25}
+          memory: ${FALKORDB_MEMORY_RESERVATION:-512M}
+
+volumes:
+  falkordb_data:
--- a/src/lmdeploy/.env.example
+++ b/src/lmdeploy/.env.example
@@ -0,0 +1,27 @@
+# LMDeploy Version
+# Find more tags at: https://hub.docker.com/r/openmmlab/lmdeploy/tags
+LMDEPLOY_VERSION=v0.11.1-cu12.8
+
+# Host port override
+LMDEPLOY_PORT_OVERRIDE=23333
+
+# Model path or HuggingFace model ID
+# Examples: 
+# - internlm/internlm2-chat-1_8b
+# - Qwen/Qwen2.5-7B-Instruct
+LMDEPLOY_MODEL=internlm/internlm2-chat-1_8b
+
+# HuggingFace token for private models
+HF_TOKEN=
+
+# Resource limits
+LMDEPLOY_CPU_LIMIT=4.0
+LMDEPLOY_MEMORY_LIMIT=8G
+LMDEPLOY_CPU_RESERVATION=2.0
+LMDEPLOY_MEMORY_RESERVATION=4G
+
+# Shared memory size (required for some models)
+LMDEPLOY_SHM_SIZE=4g
+
+# Timezone
+TZ=UTC
--- a/src/lmdeploy/README.md
+++ b/src/lmdeploy/README.md
@@ -0,0 +1,29 @@
+# LMDeploy Docker Compose
+
+[LMDeploy](https://github.com/InternLM/lmdeploy) is a toolkit for compressing, deploying, and serving LLMs.
+
+## Quick Start
+
+1. (Optional) Configure the model and port in `.env`.
+2. Start the service:
+   ```bash
+   docker compose up -d
+   ```
+3. Access the OpenAI compatible API at `http://localhost:23333/v1`.
+
+## Configuration
+
+| Environment Variable     | Default                        | Description                          |
+| ------------------------ | ------------------------------ | ------------------------------------ |
+| `LMDEPLOY_VERSION`       | `v0.11.1-cu12.8`               | LMDeploy image version               |
+| `LMDEPLOY_PORT_OVERRIDE` | `23333`                        | Host port for the API server         |
+| `LMDEPLOY_MODEL`         | `internlm/internlm2-chat-1_8b` | HuggingFace model ID or local path   |
+| `HF_TOKEN`               |                                | HuggingFace token for private models |
+
+## Monitoring Health
+
+The service includes a health check that verifies if the OpenAI `/v1/models` endpoint is responsive.
+
+## GPU Support
+
+By default, this configuration reserves 1 NVIDIA GPU. Ensure you have the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html) installed on your host.
--- a/src/lmdeploy/README.zh.md
+++ b/src/lmdeploy/README.zh.md
@@ -0,0 +1,29 @@
+# LMDeploy Docker Compose
+
+[LMDeploy](https://github.com/InternLM/lmdeploy) 是一个用于压缩、部署和服务大语言模型（LLM）的工具包。
+
+## 快速开始
+
+1. （可选）在 `.env` 中配置模型和端口。
+2. 启动服务：
+   ```bash
+   docker compose up -d
+   ```
+3. 通过 `http://localhost:23333/v1` 访问与 OpenAI 兼容的 API。
+
+## 配置项
+
+| 环境变量                 | 默认值                         | 说明                                 |
+| ------------------------ | ------------------------------ | ------------------------------------ |
+| `LMDEPLOY_VERSION`       | `v0.11.1-cu12.8`               | LMDeploy 镜像版本                    |
+| `LMDEPLOY_PORT_OVERRIDE` | `23333`                        | API 服务器的主机端口                 |
+| `LMDEPLOY_MODEL`         | `internlm/internlm2-chat-1_8b` | HuggingFace 模型 ID 或本地路径       |
+| `HF_TOKEN`               |                                | 用于访问私有模型的 HuggingFace Token |
+
+## 健康检查
+
+该配置包含健康检查，用于验证 OpenAI `/v1/models` 接口是否响应。
+
+## GPU 支持
+
+默认情况下，此配置会预留 1 个 NVIDIA GPU。请确保您的主机已安装 [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html)。
--- a/src/lmdeploy/docker-compose.yaml
+++ b/src/lmdeploy/docker-compose.yaml
@@ -0,0 +1,50 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+services:
+  lmdeploy:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}openmmlab/lmdeploy:${LMDEPLOY_VERSION:-v0.11.1-cu12.8}
+    ports:
+      - "${LMDEPLOY_PORT_OVERRIDE:-23333}:23333"
+    volumes:
+      - lmdeploy_data:/root/.cache
+    environment:
+      - TZ=${TZ:-UTC}
+      - HF_TOKEN=${HF_TOKEN:-}
+    command:
+      - lmdeploy
+      - serve
+      - api_server
+      - ${LMDEPLOY_MODEL:-internlm/internlm2-chat-1_8b}
+      - --server-name
+      - "0.0.0.0"
+      - --server-port
+      - "23333"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:23333/v1/models"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+    deploy:
+      resources:
+        limits:
+          cpus: ${LMDEPLOY_CPU_LIMIT:-4.0}
+          memory: ${LMDEPLOY_MEMORY_LIMIT:-8G}
+        reservations:
+          cpus: ${LMDEPLOY_CPU_RESERVATION:-2.0}
+          memory: ${LMDEPLOY_MEMORY_RESERVATION:-4G}
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    shm_size: ${LMDEPLOY_SHM_SIZE:-4g}
+
+volumes:
+  lmdeploy_data:
--- a/src/pogocache/.env.example
+++ b/src/pogocache/.env.example
@@ -0,0 +1,15 @@
+# Pogocache Version
+POGOCACHE_VERSION=1.3.1
+
+# Host port override
+POGOCACHE_PORT_OVERRIDE=9401
+
+# Resource limits
+POGOCACHE_CPU_LIMIT=0.50
+POGOCACHE_MEMORY_LIMIT=512M
+POGOCACHE_CPU_RESERVATION=0.10
+POGOCACHE_MEMORY_RESERVATION=128M
+
+# Extra arguments for pogocache
+# Example: --auth mypassword --threads 4
+POGOCACHE_EXTRA_ARGS=
--- a/src/pogocache/README.md
+++ b/src/pogocache/README.md
@@ -0,0 +1,35 @@
+# Pogocache
+
+[Pogocache](https://github.com/tidwall/pogocache) is fast caching software built from scratch with a focus on low latency and cpu efficiency. It is a high-performance, multi-protocol Redis alternative.
+
+## Features
+
+- **Fast**: Faster than Memcached, Valkey, Redis, Dragonfly, and Garnet.
+- **Multi-protocol**: Supports Redis RESP, Memcached, PostgreSQL wire protocol, and HTTP.
+- **Persistence**: Supports AOF-style persistence.
+- **Resource Efficient**: Low CPU and memory overhead.
+
+## Deployment
+
+```bash
+docker compose up -d
+```
+
+## Configuration
+
+| Variable                  | Default | Description                                   |
+| ------------------------- | ------- | --------------------------------------------- |
+| `POGOCACHE_VERSION`       | `1.3.1` | Pogocache image version                       |
+| `POGOCACHE_PORT_OVERRIDE` | `9401`  | Host port for Pogocache                       |
+| `POGOCACHE_EXTRA_ARGS`    |         | Additional CLI arguments (e.g. `--auth pass`) |
+
+## Accessing Pogocache
+
+- **Redis**: `redis-cli -p 9401`
+- **Postgres**: `psql -h localhost -p 9401`
+- **HTTP**: `curl http://localhost:9401/key`
+- **Memcached**: `telnet localhost 9401`
+
+## Persistence
+
+By default, the data is persisted to a named volume `pogocache_data` at `/data/pogocache.db`.
--- a/src/pogocache/README.zh.md
+++ b/src/pogocache/README.zh.md
@@ -0,0 +1,35 @@
+# Pogocache
+
+[Pogocache](https://github.com/tidwall/pogocache) 是一款从零开始构建的高速缓存软件，专注于低延迟和 CPU 效率。它是一个高性能、多协议的 Redis 替代方案。
+
+## 特性
+
+- **极速**：比 Memcached、Valkey、Redis、Dragonfly 和 Garnet 更快。
+- **多协议支持**：支持 Redis RESP、Memcached、PostgreSQL 线缆协议和 HTTP。
+- **持久化**：支持 AOF 风格的持久化。
+- **资源高效**：极低的 CPU 和内存开销。
+
+## 部署
+
+```bash
+docker compose up -d
+```
+
+## 配置说明
+
+| 变量名                    | 默认值  | 描述                                   |
+| ------------------------- | ------- | -------------------------------------- |
+| `POGOCACHE_VERSION`       | `1.3.1` | Pogocache 镜像版本                     |
+| `POGOCACHE_PORT_OVERRIDE` | `9401`  | 主机端口                               |
+| `POGOCACHE_EXTRA_ARGS`    |         | 额外的命令行参数（例如 `--auth pass`） |
+
+## 访问方式
+
+- **Redis**：`redis-cli -p 9401`
+- **Postgres**：`psql -h localhost -p 9401`
+- **HTTP**：`curl http://localhost:9401/key`
+- **Memcached**：`telnet localhost 9401`
+
+## 持久化
+
+默认情况下，数据持久化到命名卷 `pogocache_data` 中的 `/data/pogocache.db`。
--- a/src/pogocache/docker-compose.yaml
+++ b/src/pogocache/docker-compose.yaml
@@ -0,0 +1,42 @@
+# Docker Compose for Pogocache
+# Pogocache is fast caching software built from scratch with a focus on low latency and cpu efficiency.
+# See: https://github.com/tidwall/pogocache
+
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 10m
+      max-file: "3"
+
+services:
+  pogocache:
+    <<: *defaults
+    image: ${GLOBAL_REGISTRY:-}pogocache/pogocache:${POGOCACHE_VERSION:-1.3.1}
+    ports:
+      - "${POGOCACHE_PORT_OVERRIDE:-9401}:9401"
+    environment:
+      - TZ=${TZ:-UTC}
+    volumes:
+      - pogocache_data:/data
+    command: >
+      ${POGOCACHE_EXTRA_ARGS:-}
+      --persist /data/pogocache.db
+    healthcheck:
+      test: ["CMD-SHELL", "nc -z localhost 9401 || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 5s
+    deploy:
+      resources:
+        limits:
+          cpus: ${POGOCACHE_CPU_LIMIT:-0.50}
+          memory: ${POGOCACHE_MEMORY_LIMIT:-512M}
+        reservations:
+          cpus: ${POGOCACHE_CPU_RESERVATION:-0.10}
+          memory: ${POGOCACHE_MEMORY_RESERVATION:-128M}
+
+volumes:
+  pogocache_data: