Skip to content
/ arcadia Public
forked from kubeagi/arcadia

A diverse, simple, and secure one-stop LLMOps platform

License

Notifications You must be signed in to change notification settings

Hoega/arcadia

 
 

Repository files navigation

Arcadia: A diverse, simple, and secure one-stop LLMOps platform

What is Arcadia?

Arcadia comes from Greek mythology(a tranquil and idyllic region, representing harmony, serenity, and natural beauty). We aim to help everyone find a more perfect integration between humans and AI.

To achieve this goal, we provide this one-stop LLMOps solution:

  • Dataset Management: storage/real-time data,multimodal,pre-processing,vectorization
  • Models Management: local/online LLMs(development,training,deployment),inference acceleration
  • Application Management: development,optimization,deployment with visual editor

Furthermore, we can easily host Arcadia at any kubernetes cluster as production ready by integrating kubebb(A kubernetes building blocks).

Architecture

Our design and development in Arcadia design follows operator pattern which extends kubernetes APIs.

Arch

Quick Start

Pre-requisites

  1. helm

  2. Kubernetes

If you don't have a kubernetes cluster, you can schedule a kind cluster. Depends on your choice on CPU or GPU when running LLM worker, you can choose to:

Documentation

Visit our online documents

Read user guide

CLI

We provide a Command Line Tool arctl to interact with arcadia. See here for more details.

  • ✅ datasource management
  • ✅ local dataset management

Pure Go Toolchains

To enhance the AI capability in Golang, we developed some packages.Here are the examples of how to use them.

  • chat_with_document: a chat server which allows you to chat with your document
  • embedding shows how to embedes your document to vector store with embedding service
  • rbac shows how to inquiry the security risks in your RBAC with AI.
  • zhipuai shows how to use this zhipuai client
  • dashscope shows how to use this dashscope client to chat with qwen-7b-chat / qwen-14b-chat / llama2-7b-chat-v2 / llama2-13b-chat-v2 and use embedding with dashscope text-embedding-v1 / text-embedding-async-v1

LLMs

Embeddings

Fully compatible with langchain embeddings

VectorStores

Fully compatible with langchain vectorstores

Contribute to Arcadia

If you want to contribute to Arcadia, refer to contribute guide.

Support

If you need support, start with the troubleshooting guide, or create GitHub issues

About

A diverse, simple, and secure one-stop LLMOps platform

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Go 56.7%
  • Python 21.7%
  • Shell 13.7%
  • Smarty 6.0%
  • Makefile 0.9%
  • Mustache 0.6%
  • Dockerfile 0.4%