OpenAI API aggregation/management platform
Top 57.7% on sourcepulse
This project provides a unified API management gateway for various AI models, primarily targeting developers and businesses looking to integrate advanced AI capabilities into their products. It offers a user-friendly interface, flexible billing options, and robust administrative features for managing API channels and user access, simplifying the integration of services like OpenAI and Claude.
How It Works
The system acts as a proxy, aggregating multiple AI model APIs under a single interface. It supports various models including GPT-4V and Claude variants, with features like custom request headers, retry mechanisms for empty responses, and token suffix customization. The architecture allows for flexible database configurations (SQLite, MySQL, PostgreSQL) and optional Redis caching for performance.
Quick Start & Requirements
# SQLite
docker run --name chat-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai ai365/chat-api:latest
# MySQL
docker run --name chat-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai ai365/chat-api:latest
docker-compose up -d
http://localhost:3000/admin
, User: http://localhost:3000/
. Initial login: root
/123456
.Highlighted Details
Maintenance & Community
The project is a fork of One API and New API. It is presented as a personal learning project, with no explicit mention of active maintenance, community channels (like Discord/Slack), or a roadmap.
Licensing & Compatibility
The project's README does not explicitly state a license. It warns against illegal use and compliance with OpenAI's terms of service and relevant regulations.
Limitations & Caveats
The project is explicitly stated to be for personal learning use only and does not guarantee stability or provide technical support. Users are responsible for adhering to OpenAI's terms and local regulations, particularly regarding AI service provision in China.
2 weeks ago
1 week