Eino pronunciation: US / ‘aino /, approximate sound: i know, with the hope that the application can achieve the vision of “i know”
💡 Eino:An AI Application Development Framework Built with Go
Eino aims to provide an AI application development framework built with Go. Eino refers to many excellent AI application development frameworks in the open-source community, such as LangChain, LangGraph, LlamaIndex, etc., and provides an AI application development framework that is more in line with the programming habits of Golang.
Eino provides rich capabilities such as atomic components, integrated components, component orchestration, and aspect extension that assist in AI application development, which can help developers more simply and conveniently develop AI applications with a clear architecture, easy maintenance, and high availability.
Take ReactAgent as an example:
One of Eino’s goals is: to collect and improve the component system in the context of AI applications, so that the business can easily find some common AI components, facilitating the iteration of the business.
Eino will provide components with a relatively good abstraction around the scenarios of AI applications, and provide some common implementations around this abstraction.
Thanks to the lightweight and in-field affinity properties of Eino, users can introduce powerful large model capabilities to their existing microservices with just a few lines of code, allowing traditional microservices to evolve with AI genes.
When people hear the term “Graph Orchestration”, their first reaction might be to segment and layer the implementation logic of the entire application interface, and convert it into an orchestratable Node. The biggest problem encountered in this process is the issue of long-distance context passing (variable passing across Node nodes), whether using the State of Graph/Chain or using Options for transparent passing, the entire orchestration process is extremely complex, far from being as simple as directly making function calls.
Based on the current Graph orchestration capabilities, the scenarios suitable for orchestration have the following characteristics:
What is the significance of orchestration: To aggregate, control, and present the context of long-distance orchestration elements in a fixed paradigm.
Overall, the scenarios where “Graph Orchestration” is applicable are: business-customized AI integration components. That is, to flexibly orchestrate AI-related atomic capabilities and provide simple and easy-to-use scenario-based AI components. Moreover, in this AI component, there is a unified and complete horizontal governance capability.