Fireworks AI - 快速推理平台

Fireworks AI 的工作原理

Fireworks AI 是生成式 AI 最快的推理平台，旨在在几秒钟内构建和运行神奇的 AI 应用。该平台提供对流行开源模型（如 DeepSeek、Llama、Qwen 和 Mistral）的无服务器访问，具有优化的速度、高吞吐量和最小延迟。专为需要可靠、极快 AI 基础设施而无需 GPU 管理复杂性的开发者而构建。

模型	定价（100万令牌）	上下文窗口
Llama 4 Maverick `推荐`	$0.22/$ 0.88	~131k 令牌
Llama 4 Scout	$0.15/$ 0.60	~131k 令牌
DeepSeek V3	$0.90	~128k 令牌
Qwen3 235B	$0.22/$ 0.88	~131k 令牌

创建 API 密钥

需要 Fireworks AI 账户才能创建 API 密钥。

直接访问 Fireworks AI 控制台创建新的 API 密钥。或者，按照以下步骤操作：

访问 app.fireworks.ai 并创建账户或登录
登录后，导航到您的账户设置中的 API Keys 页面
点击 “Create API Key” 按钮
为您的密钥提供一个描述性名称（例如，‘Kodus’或您偏好的任何名称）
点击 “Create” 生成密钥
立即复制 API 密钥并将其保存在安全的地方 - 您将无法再次查看它

新账户附带 $1 的免费信用额度，可开始使用您的项目。

如何使用

System Requirements

Recommended Hardware

CPU: 2+ cores - RAM: 8GB+ - Storage: 60GB+ free space

Required Software

Docker (latest stable version) - Node.js (latest LTS version) - Yarn or NPM (latest stable version) - Domain name or fixed IP (for external deployments)

Required Ports

3000: Kodus Web App - 3001: Orchestrator API - 5672, 15672: RabbitMQ - 5432: PostgreSQL - 27017: MongoDB

Internet access is only required if you plan to connect with cloud-based Git services like GitHub, GitLab, or Bitbucket. For self-hosted Git tools within your network, external internet access is optional.

Domain Name Setup (Optional)

If you're planning to integrate Kodus with cloud-based Git providers (GitHub, GitLab, or Bitbucket), you'll need public-facing URLs for both the Kodus Web App and its API. This allows your server to receive webhooks for proper Code Review functionality and ensures correct application behavior. We recommend setting up two subdomains:

One for the Web Application, e.g., kodus-web.yourdomain.com.
One for the API, e.g., kodus-api.yourdomain.com.

Both subdomains should have DNS A records pointing to your server's IP address. Later in this guide, we will configure a reverse proxy (Nginx) to route requests to these subdomains to the correct internal services. This setup is essential for full functionality, including webhooks and authentication.

Note: If you're only connecting to self-hosted Git tools on your network and do not require public access or webhooks, you might be able to use a simpler setup, but this guide focuses on public-facing deployments.

Get the Kodus Installer

Clone our installer repository:

git clone https://github.com/kodustech/kodus-installer.git
cd kodus-installer

Configure Environment Variables

First, copy the example environment file:

cp .env.example .env

Generate secure keys for the required environment variables using:

# For most security keys
openssl rand -base64 32

# Specifically for API_CRYPTO_KEY and CODE_MANAGEMENT_SECRET
openssl rand -hex 32

# Specifically for CODE_MANAGEMENT_WEBHOOK_TOKEN
openssl rand -base64 32 | tr -d '=' | tr '/+' '_-'

You'll need to generate values for these security keys:

WEB_NEXTAUTH_SECRET (use openssl rand -base64 32)
WEB_JWT_SECRET_KEY (use openssl rand -base64 32)
API_CRYPTO_KEY (use openssl rand -hex 32)
API_JWT_SECRET (use openssl rand -base64 32)
API_JWT_REFRESHSECRET (use openssl rand -base64 32)
CODE_MANAGEMENT_SECRET (use openssl rand -hex 32)
CODE_MANAGEMENT_WEBHOOK_TOKEN (use openssl rand -base64 32 | tr -d '=' | tr '/+' '_-')

Never commit your .env file to version control. Keep your API keys and database credentials secure.

Then update your .env file with the following required variables:

# Core System Settings
WEB_NODE_ENV="self-hosted"                     # Keep as "self-hosted" for self-hosted setup
WEB_HOSTNAME_API="kodus-api.yourdomain.com"    # Public API hostname (e.g., kodus-api.yourdomain.com)
WEB_PORT_API=443                               # Public API port (usually 443 for HTTPS, or 80 if not using SSL yet)
WEB_PORT=3000                                  # Internal Web application port (reverse proxy will handle public port)
GLOBAL_API_CONTAINER_NAME="kodus-orchestrator" # API container name

# Authentication Settings
NEXTAUTH_URL="https://kodus-web.yourdomain.com" # Full public base URL for the Web App (e.g., https://kodus-web.yourdomain.com)
WEB_NEXTAUTH_SECRET=""                        # NextAuth secret key (generate with: openssl rand -base64 32)
WEB_JWT_SECRET_KEY=""                         # JWT secret key (generate with: openssl rand -base64 32)

# API Configuration
API_NODE_ENV="development"                    # Keep as "development" for local setup
API_LOG_LEVEL=error                           # Error logging level
API_LOG_PRETTY=true                           # Pretty print logs
API_HOST=0.0.0.0                              # API host
API_PORT=3001                                 # API port
API_RATE_MAX_REQUEST=100                      # Rate limiting: max requests
API_RATE_INTERVAL=1000                        # Rate limiting: time window (ms)
API_CRYPTO_KEY=                               # Crypto key (generate with: openssl rand -hex 32)
API_JWT_EXPIRES_IN=365d                       # JWT token expiration time
API_JWT_SECRET=                               # JWT secret key
API_JWT_REFRESHSECRET=                        # JWT refresh token secret key
API_JWT_REFRESH_EXPIRES_IN=7d                 # JWT refresh token expiration time

# Database Configuration
API_DATABASE_ENV="development"                # Database environment
API_PG_DB_HOST=db_kodus_postgres              # PostgreSQL host
API_PG_DB_PORT=5432                          # PostgreSQL port
API_PG_DB_USERNAME=kodusdev                  # Database username
API_PG_DB_PASSWORD=                          # Database password
API_PG_DB_DATABASE=kodus_db                  # Database name

# MongoDB Configuration
API_MG_DB_HOST=db_kodus_mongodb              # MongoDB host
API_MG_DB_PORT=27017                         # MongoDB port
API_MG_DB_USERNAME=kodusdev                  # Database username
API_MG_DB_PASSWORD=                          # Database password
API_MG_DB_DATABASE=kodus_db                  # Database name

在环境文件中配置 Fireworks AI

编辑您的 .env 文件并配置核心设置。对于 LLM 集成，在固定模式下使用 Fireworks AI：

# 核心系统设置（使用您的域名更新）
WEB_HOSTNAME_API="kodus-api.yourdomain.com"
WEB_PORT_API=443
NEXTAUTH_URL="https://kodus-web.yourdomain.com"

# 安全密钥（使用上面的 openssl 命令生成）
WEB_NEXTAUTH_SECRET="your-generated-secret"
WEB_JWT_SECRET_KEY="your-generated-secret"
API_CRYPTO_KEY="your-generated-hex-key"
API_JWT_SECRET="your-generated-secret"
API_JWT_REFRESHSECRET="your-generated-secret"

# 数据库配置
API_PG_DB_PASSWORD="your-secure-db-password"
API_MG_DB_PASSWORD="your-secure-db-password"

# Fireworks AI 配置（固定模式）
API_LLM_PROVIDER_MODEL="accounts/fireworks/models/llama4-maverick-instruct-basic"  # 选择您偏好的模型
API_OPENAI_FORCE_BASE_URL="https://api.fireworks.ai/inference/v1"                  # Fireworks AI API URL
API_OPEN_AI_API_KEY="your-fireworks-api-key"                                       # 您的 Fireworks AI API 密钥

# Git 提供商 Webhook（选择您的提供商）
API_GITHUB_CODE_MANAGEMENT_WEBHOOK="https://kodus-api.yourdomain.com/github/webhook"
# 或 API_GITLAB_CODE_MANAGEMENT_WEBHOOK="https://kodus-api.yourdomain.com/gitlab/webhook"
# 或 GLOBAL_BITBUCKET_CODE_MANAGEMENT_WEBHOOK="https://kodus-api.yourdomain.com/bitbucket/webhook"

固定模式非常适合 Fireworks AI，因为它提供兼容 OpenAI 的 API，具有极快的推理速度，并可访问尖端的开源模型，设置时间为零。

Run the Installation Script

Looking for more control? Check out our docker-compose file for manual deployment options.

Set the proper permissions for the installation script:

chmod +x scripts/install.sh

Run the script:

./scripts/install.sh

What the Installer Does

Our installer automates several important steps:

Verifies Docker installation
Creates networks for Kodus services
Clones repositories and configures environment files
Runs docker-compose to start all services
Executes database migrations
Seeds initial data

🎉 Success! When complete, Kodus Orchestrator API and Web Application should be running on your machine. You can verify your installation by visiting http://localhost:3000 - you should see the Kodus Web Application interface.

Code Review features will not work yet unless you complete the reverse proxy setup. Without this configuration, external Git providers cannot send webhooks to your instance.

设置反向代理（用于生产环境）

对于 Webhook 和外部访问，配置 Nginx：

# Web 应用（端口 3000）
server {
    listen 80;
    server_name kodus-web.yourdomain.com;
    location / {
        proxy_pass http://localhost:3000;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
    }
}

# API（端口 3001）
server {
    listen 80;
    server_name kodus-api.yourdomain.com;
    location / {
        proxy_pass http://localhost:3001;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
    }
}

验证 Fireworks AI 集成

除了基本的安装验证外，确认 Fireworks AI 正常工作：

# 专门验证 Fireworks AI API 连接
docker logs kodus-orchestrator-prod | grep -i fireworks

有关 SSL 设置、监控和高级配置的详细信息，请参阅我们的完整部署指南。

故障排除

API 密钥问题

在 Fireworks AI 控制台中验证您的 API 密钥是否正确且处于活动状态
检查您的 Fireworks AI 账户中是否有足够的信用额度
确保您的 .env 文件中没有多余的空格
新账户会收到 $1 的免费信用额度以开始使用

模型未找到

检查配置中的模型名称拼写是否正确
验证该模型在 Fireworks AI 当前的模型库中是否可用
尝试使用我们推荐列表中的其他模型
查看 Fireworks AI 模型文档

连接错误

验证您的服务器是否有互联网访问权限以访问 api.fireworks.ai
检查是否有任何防火墙限制
查看编排器日志以获取详细的错误消息
确保您使用的是正确的 API 端点

性能问题

Fireworks AI 提供业界领先的速度和最小延迟
检查您的网络连接以获得最佳性能
考虑将专用部署用于企业工作负载
监控您的使用模式以优化 API 调用

速率限制

Fireworks AI 在无服务器基础设施上提供高速率限制
在 Fireworks AI 控制面板中检查您当前的使用情况
考虑升级到专用部署以获得更高的吞吐量
联系 Fireworks AI 支持以进行企业速率限制调整

自托管 + 开源 LLM 提供商

自定义插件

自定义上下文剧本

Fireworks AI - 快速推理平台

Fireworks AI 的工作原理

推荐模型

创建 API 密钥

如何使用

System Requirements

Domain Name Setup (Optional)

Get the Kodus Installer

Configure Environment Variables

在环境文件中配置 Fireworks AI

Run the Installation Script

What the Installer Does

设置反向代理（用于生产环境）

验证 Fireworks AI 集成

故障排除

自托管 + 开源 LLM 提供商

自定义插件

自定义上下文剧本

​Fireworks AI 的工作原理

​推荐模型

​创建 API 密钥

​如何使用

​System Requirements

​Domain Name Setup (Optional)

​Get the Kodus Installer

​Configure Environment Variables

​在环境文件中配置 Fireworks AI

​Run the Installation Script

​What the Installer Does

​设置反向代理（用于生产环境）

​验证 Fireworks AI 集成

​故障排除

Fireworks AI 的工作原理

推荐模型

创建 API 密钥

如何使用

System Requirements

Domain Name Setup (Optional)

Get the Kodus Installer

Configure Environment Variables

在环境文件中配置 Fireworks AI

Run the Installation Script

What the Installer Does

设置反向代理（用于生产环境）

验证 Fireworks AI 集成

故障排除