这是indexloc提供的服务,不要输入任何密码
Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 31 additions & 27 deletions docs/README.en.md
Original file line number Diff line number Diff line change
Expand Up @@ -19,19 +19,23 @@
</p>

<h2 align="center">
Automates the Construction of an LLM Platform on AWS ~
Automated Construction of an LLM Platform on AWS ~
</h2>

>[!IMPORTANT]
>AMATERASU is the successor project to [MOA](https://github.com/Sunwood-ai-labs/MOA). It has evolved to run each AI service on an independent EC2 instance using Docker Compose, enabling easy deployment with Terraform.
>This repository utilizes [SourceSage](https://github.com/Sunwood-ai-labs/SourceSage). Approximately 90% of the release notes, README, and commit messages were generated using [SourceSage](https://github.com/Sunwood-ai-labs/SourceSage) and [claude.ai](https://claude.ai/).

>[!NOTE]
>AMATERASU is the successor project to [MOA](https://github.com/Sunwood-ai-labs/MOA). It has evolved to run each AI service on an independent EC2 instance using Docker Compose, enabling easier deployment with Terraform.


## 🚀 Project Overview

AMATERASU is an automation tool for building an LLM (Large Language Model) platform on AWS. While inheriting the functionality of MOA, it achieves more flexible scaling and management by operating each service on a separate EC2 instance.
AMATERASU is an automation tool for building an LLM (Large Language Model) platform on AWS. While inheriting the functionality of MOA, it offers more flexible scaling and management by running each service on a separate EC2 instance.

Key Features:
- Simple EC2 instance management using Terraform
- Independent EC2 instance and Docker Compose environment for each service
- Independent EC2 instances and Docker Compose environments for each service
- Service-level scaling and operation
- Secure communication and access control

Expand All @@ -42,10 +46,10 @@ Key Features:

## 🔧 Usage

Follow the installation instructions and usage methods described in this README to set up AMATERASU.
Follow the installation instructions and usage guide in this README to set up AMATERASU.


## 📦 Installation Instructions
## 📦 Installation

1. Clone the repository:
```bash
Expand Down Expand Up @@ -74,21 +78,21 @@ terraform apply
ssh -i "C:\Users\makim\.ssh\AMATERASU-terraform-keypair-tokyo-PEM.pem" ubuntu@i-062f3dd7388a5da8a
```

## 🆕 Latest Information
## 🆕 What's New

v0.2.0 has revamped the architecture, changing the execution of each AI service to use Docker Compose on independent EC2 instances. This improves scalability and operation of each service, enhancing flexibility. Additionally, the English README has been updated, and images have been added to improve the appearance of the release notes.
v0.2.0 features a revamped architecture, running each AI service in a separate EC2 instance using Docker Compose. This improves scalability and manageability for each service. The English README has been updated, and images have been added to improve the appearance of the release notes.

Along with the architecture refresh, the README now includes an architecture diagram, system requirements, installation instructions, module composition, deployment methods, operational command examples, detailed directory structures for each module, examples of Docker Compose configuration files (`docker-compose.yml`) and environment variable files (`.env`), SSH connection to each module, and scripts for managing services (start, stop, log display) via Docker Compose. For enhanced security, each EC2 instance is protected by a separate security group, and inter-service communication is controlled within the internal VPC network.
The architecture refresh has added an architecture diagram, system requirements, installation instructions, module structure, deployment methods, operational command examples, detailed directory structures for each module, examples of Docker Compose configuration files (`docker-compose.yml`) and environment variable files (`.env`), SSH connection to each module, and scripts for managing services (start, stop, log display) using Docker Compose. For enhanced security, each EC2 instance is protected by a separate security group, and inter-service communication is controlled within the internal VPC network.


## 🌐 Module Composition
## 🌐 Module Structure

Each module runs using Docker Compose on an independent EC2 instance:
Each module runs using Docker Compose on a separate EC2 instance:

### open-webui Module (EC2 instance)
### open-webui Module (EC2 Instance)
```
📁 open-webui/
├── 📄 docker-compose.yml # Configuration for open-webui and ollama
├── 📄 docker-compose.yml # open-webui and ollama configuration
├── 📄 .env # Environment variable settings
└── 📁 config/ # Configuration files
```
Expand All @@ -112,25 +116,25 @@ services:
- OLLAMA_URL=http://ollama:11434
```

### litellm Module (EC2 instance)
### litellm Module (EC2 Instance)
```
📁 litellm/
├── 📄 docker-compose.yml # Configuration for the litellm service
├── 📄 docker-compose.yml # litellm service configuration
├── 📄 .env # API key and other environment variables
└── 📁 config/ # LLM configuration files
```

### langfuse Module (EC2 instance)
### langfuse Module (EC2 Instance)
```
📁 langfuse/
├── 📄 docker-compose.yml # Configuration for langfuse and the database
├── 📄 docker-compose.yml # langfuse and DB configuration
├── 📄 .env # Environment variable settings
└── 📁 data/ # PostgreSQL data
```

## 🔨 Deployment Command Examples

Deploying only specific modules:
Deploying specific modules only:
```bash
# Deploy only the open-webui module
terraform apply -target=module.ec2_open_webui
Expand All @@ -154,19 +158,19 @@ Connecting to each EC2 instance:

Docker Compose operations:
```bash
# Execute within each instance
# Run within each instance
cd /opt/amaterasu/[module-name]
docker-compose up -d # Start services
docker-compose down # Stop services
docker-compose logs -f # Display logs
docker-compose logs -f # View logs
```

## 🔒 Security Settings
## 🔒 Security Configuration

- Each EC2 instance is protected by a separate security group
- Inter-service communication is controlled within the internal VPC network
- Only the minimum necessary ports are exposed
- Permission management via IAM roles
- Permission management using IAM roles

## 📚 Directory Structure

Expand All @@ -192,21 +196,21 @@ amaterasu/
## 📦 Upgrade Instructions

1. Stop the existing environment.
2. Follow the instructions in this README to build the environment with the new architecture.
2. Build the environment with the new architecture following the instructions in this README.
3. If data migration is necessary, perform the appropriate steps. (Specific steps are not provided.)


## 📄 License

This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

## 👏 Acknowledgements

Thanks to iris-s-coon and Maki.

## 🤝 Contributions
## 🤝 Contributing

Contributions are welcome! Follow these steps to contribute:
Contributions are welcome! Here's how to get involved:

1. Fork this repository
2. Create a new branch (`git checkout -b feature/amazing-feature`)
Expand All @@ -216,7 +220,7 @@ Contributions are welcome! Follow these steps to contribute:

## 📧 Support

For any questions or feedback, please feel free to contact us:
For questions or feedback, please feel free to contact us:
- Create an issue: [GitHub Issues](https://github.com/Sunwood-ai-labs/AMATERASU/issues)
- Email: support@sunwoodai.com

Expand Down