这是indexloc提供的服务，不要输入任何密码
Skip to content

📖 [docs] 英語READMEの自動更新 #26

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 21, 2024
Merged

📖 [docs] 英語READMEの自動更新 #26

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
120 changes: 68 additions & 52 deletions docs/README.en.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
<p align="center">
<img src="https://raw.githubusercontent.com/Sunwood-ai-labs/AMATERASU/refs/heads/main/docs/amaterasu_main.png" width="100%">
<h1 align="center">AMATERASU v0.6.1</h1>
<h1 align="center">AMATERASU v1.0.0</h1>
</p>

<p align="center">
Expand All @@ -20,33 +20,34 @@
</h2>

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

[Image Placeholder - The link provided points to a user attachment and cannot be displayed here.]

https://github.com/user-attachments/assets/90f382c2-6b4a-42c4-9543-887ecc67b6eb

## 🔒 Security-Focused Design Philosophy
## 🔒 Security-Focused Design

AMATERASU is a private AI platform foundation developed specifically for Japanese enterprises with stringent security requirements. It enables the secure use of LLMs based on AWS Bedrock:
AMATERASU is a private AI platform infrastructure specifically developed for Japanese enterprises with stringent security requirements. It enables the secure use of LLMs based on AWS Bedrock:

- **Secure LLM Foundation with AWS Bedrock**:
- **Secure LLM Infrastructure with AWS Bedrock**:
- Supports the Claude-3 model, optimized for enterprise use.
- Leverages AWS's enterprise-grade security.
- Granular access control using IAM roles.
- Granular access control based on IAM roles.

- **Operation in a Completely Closed Environment**:
- **Operation in a Fully Closed Environment**:
- Operates only within the internal network.
- Supports private cloud/on-premises deployments.

- **Enterprise-Grade Security**:
- IP whitelist access control.
- IP whitelisting for access control (directly specified in security group settings).
- HTTPS/TLS encrypted communication.
- Network segmentation using AWS Security Groups.
- IAM role management based on the principle of least privilege.


## ✨ Key Features

### 1. Secure ChatGPT-like Interface (Open WebUI)
Expand All @@ -60,14 +61,15 @@ AMATERASU is a private AI platform foundation developed specifically for Japanes
- Load balancing and rate limiting of requests.
- Centralized API key management.

### 3. Cost Management and Monitoring Foundation (Langfuse)
### 3. Cost Management and Monitoring Infrastructure (Langfuse)
- Visualizes token usage.
- Aggregates costs by department.
- Analyzes usage patterns.


## 🏗️ System Architecture

### Secure 3-Tier Architecture based on AWS Bedrock
### Secure 3-Tier Architecture Based on AWS Bedrock

```mermaid
%%{init:{'theme':'base'}}%%
Expand Down Expand Up @@ -118,46 +120,52 @@ Recommended Configuration:
- Network: Public/Private subnet


## 💼 Use Cases in Enterprises
## 💼 Enterprise Use Cases

1. **Development Department**
- Code review assistance
- Improved bug analysis efficiency
- Bug analysis efficiency improvement
- Document generation

2. **Business Departments**
- Report creation assistance
- Report generation assistance
- Data analysis support
- Meeting minutes creation
- Meeting minute creation

3. **Customer Support**
- Improved efficiency of inquiry response
- Improved efficiency in handling inquiries
- Automatic FAQ generation
- Improved quality of reply text


## 🔧 Installation and Operation
## 🔧 Deployment and Operation

### Setup Procedure
### Setup Instructions
```bash
# 1. Clone the repository
git clone https://github.com/Sunwood-ai-labs/AMATERASU.git
cd AMATERASU

# 2. Set environment variables
cp .env.example .env
# Edit the .env file and set credentials
# Edit the .env file and set your credentials

# 3. Deploy infrastructure
# 3. Deploy the infrastructure
cd spellbook/base-infrastructure
terraform init && terraform apply

cd ../open-webui/terraform/main-infrastructure
terraform init && terraform apply

# 4. Start services
# Langfuse (Monitoring foundation)
cd ../../langfuse
cd ../../litellm/terraform/main-infrastructure
terraform init && terraform apply

cd ../../langfuse/terraform/main-infrastructure
terraform init && terraform apply

# 4. Start the services
# Langfuse (Monitoring infrastructure)
cd ../../../langfuse
docker-compose up -d

# LiteLLM (API proxy)
Expand All @@ -167,61 +175,69 @@ docker-compose up -d
# Open WebUI (User interface)
cd ../open-webui
docker-compose up -d

```

## 📚 Detailed Documentation

- [Spellbook Infrastructure Construction Guide](spellbook/README.md)
- [Spellbook Infrastructure Setup Guide](spellbook/README.md)
- [LiteLLM Configuration Guide](spellbook/litellm/README.md)
- [Langfuse Setup Guide](spellbook/langfuse/README.md)

## 🆕 Latest Information

### v0.6.1 Update Notes

- Updated documentation and added important information to the README file.
- Updated English and Japanese READMEs.
- Added information about the development process using SourceSage and claude.ai.
- Simplified descriptions related to security.


### v0.6.0 Update Notes

- Removed unnecessary resources due to the removal of the CloudFront infrastructure.
- Simplified the code to improve maintainability.
- Added application HTTPS and HTTP URLs to the output.
- Enabled easy modification of the environment variable file and setup script paths in `terraform.tfvars`.
- Removed unnecessary variable definitions.
- Simplified the setup script.
## 🆕 What's New

### v1.0.0 Update Contents

- 🎉 Added Langfuse integrated filter pipeline (`langfuse_litellm_filter_pipeline.py`): Integrates with the Langfuse API for conversation tracing and monitoring.
- 🎉 Added conversation turn limit filter (`conversation_turn_limit_filter.py`): Limits the number of conversation turns.
- 🎉 Added convenient Terraform commands: `terraform destroy -auto-approve ; terraform init ; terraform plan ; terraform apply -auto-approve`
- 🚀 README.md updated: Added links and corrected line breaks.
- 🚀 Setup script corrected: Changed the execution order of `docker-compose up`.
- 🚀 Docker Compose configuration corrected: Added `extra_hosts` option.
- 🚀 English README updated.
- 🚀 README updated after release.
- 🚀 Header image updated.
- ⚠️ Removed whitelist CSV file and changed to direct description in security group settings.
- ⚠️ Corrected security group output.
- ⚠️ Removed security group module and changed to direct settings.
- ⚠️ Docker Compose configuration corrected.
- ⚠️ Changed the development environment URL to the production environment URL.
- ⚠️ Whitelist for access restriction to the LitleLLM development environment.
- ⚠️ Terraform variable configuration file for the LitleLLM development environment.
- ⚠️ Creation of a setup script for the LitleLLM development environment.
- ⚠️ Added output value definition for the LitleLLM development environment.
- ⚠️ Terraform module configuration for building the LitleLLM development environment.
- ⚠️ Added definition of Terraform variables for the LitleLLM development environment.


## 💰 Cost Management

Provides detailed cost analysis and management functionality through Langfuse:
- Tracks usage costs for each model.
Provides detailed cost analysis and management capabilities through Langfuse:
- Tracks usage costs per model.
- Allows setting budget alerts.
- Visualizes usage.


## 👏 Acknowledgements

Thanks to iris-s-coon and Maki for their contributions.

## 📄 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.

## 🤝 Contributions

1. Fork this repository
2. Create a new branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push the branch (`git push origin feature/amazing-feature`)
5. Create a pull request
1. Fork this repository.
2. Create a new branch (`git checkout -b feature/amazing-feature`).
3. Commit your changes (`git commit -m 'Add amazing feature'`).
4. Push the branch (`git push origin feature/amazing-feature`).
5. Create a pull request.

## 📧 Support

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

---
Expand Down