From fd2990492f4c74a66189d3b9244f5b5a458b8d0c Mon Sep 17 00:00:00 2001 From: nkwangleiGIT Date: Sun, 18 Feb 2024 21:44:09 +0800 Subject: [PATCH] Update npm repo host and README --- .github/workflows/example_test.yaml | 2 +- README.md | 80 ++++++++++++++++------------- 2 files changed, 44 insertions(+), 38 deletions(-) diff --git a/.github/workflows/example_test.yaml b/.github/workflows/example_test.yaml index 2f40f3809..6e4d23baf 100644 --- a/.github/workflows/example_test.yaml +++ b/.github/workflows/example_test.yaml @@ -113,7 +113,7 @@ jobs: - name: setting token to npmrc if: (( github.event_name == 'push' && steps.gql-changes.outputs.gql == 'true') || github.event_name == 'workflow_dispatch') && matrix.no == 1 run: | - echo '//dev-npm.tenxcloud.net/:_authToken="${{ secrets.TENX_NPM_TOKEN }}"' >> ~/.npmrc + echo '//dev-npm.k8s.com.cn/:_authToken="${{ secrets.TENX_NPM_TOKEN }}"' >> ~/.npmrc echo '//registry.npmjs.org/:_authToken="${{ secrets.NPM_TOKEN }}"' >> ~/.npmrc - name: Set variable on Merge pull request if: github.event_name == 'push' && matrix.no == 1 diff --git a/README.md b/README.md index 9b96f22c7..3a474580a 100644 --- a/README.md +++ b/README.md @@ -21,44 +21,60 @@ **Arcadia** comes from [Greek mythology](https://www.greekmythology.com/Myths/Places/Arcadia/arcadia.html)(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: +To achieve this goal, we provide this one-stop LLMOps solution. Furthermore, we can easily host **Arcadia** at any Kubernetes cluster as production ready by integrating [kubebb](https://github.com/kubebb)(Kubernetes building blocks). -- 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](https://github.com/kubebb)(A kubernetes building blocks). +## Features +* Multi-tenant isolation (data, model services), built-in OIDC, RBAC, and auditing, supporting different companies and departments to develop through a unified platform +* Kubernetes native AGI agent orchestration +* Built on langchaingo(golang), has better performance and maintainability +* Support distributed inference using Ray +* Support quality and performance evaluation of AGI agent under different configurations +* A development and operational platform for AI agents, along with an AI agent portal for end-users +* Developed based on micro frontends and low-code approach, allowing for quick scalability and integration ## Architecture -Our design and development in Arcadia design follows operator pattern which extends kubernetes APIs. +Our design and development in Arcadia design follows operator pattern which extends Kubernetes APIs. ![Arch](./docs/images/kubeagi.drawio.png) -## Quick Start +For details, check [Architecture Overview](http://kubeagi.k8s.com.cn/docs/Concepts/architecture-overview) -### Pre-requisites +## Quick Start -1. [helm](https://helm.sh/docs/intro/install/) +### Documentation -2. [Kubernetes](https://kubernetes.io/) +Visit our [online documents](http://kubeagi.k8s.com.cn/docs/intro) -If you don't have a kubernetes cluster, you can schedule a [kind cluster](https://kind.sigs.k8s.io/). Depends on your choice on CPU or GPU when running LLM worker, you can choose to: +Read [user guide](http://kubeagi.k8s.com.cn/docs/UserGuide/intro) -- [Create a kind cluster with/without GPU enabled](http://kubeagi.k8s.com.cn/docs/Quick%20Start/create-cluster-using-kind) +### LLMs -### Documentation +List of supported(tested) LLMs +* baichuan2-7b +* chatglm2-6b +* qwen-7b-chat / qwen-14b-chat / qwen-72b-chat +* llama2-7b +* mistral-7b +* bge-large-zh ***embedding*** +* m3e ***embedding*** +* [ZhiPuAI(智谱 AI)](https://github.com/kubeagi/arcadia/tree/main/pkg/llms/zhipuai) + - [example](https://github.com/kubeagi/arcadia/blob/main/examples/zhipuai/main.go) + - [embedding](https://github.com/kubeagi/arcadia/tree/main/pkg/embeddings/zhipuai) +* [DashScope(灵积模型服务)](https://github.com/kubeagi/arcadia/tree/main/pkg/llms/dashscope) + - [example](https://github.com/kubeagi/arcadia/blob/main/examples/dashscope/main.go) + - [text-embedding-v1(通用文本向量 同步接口)](https://help.aliyun.com/zh/dashscope/developer-reference/text-embedding-api-details) -Visit our [online documents](http://kubeagi.k8s.com.cn/docs/intro) +### Embeddings -Read [user guide](http://kubeagi.k8s.com.cn/docs/UserGuide/intro) +> Fully compatible with [langchain embeddings](https://github.com/tmc/langchaingo/tree/main/embeddings) -## CLI +### VectorStores -We provide a Command Line Tool `arctl` to interact with `arcadia`. See [here](./pkg/arctl/README.md) for more details. +> Fully compatible with [langchain vectorstores](https://github.com/tmc/langchaingo/tree/main/vectorstores) -- ✅ datasource management -- ✅ local dataset management +- ✅ [PG Vector](https://github.com/tmc/langchaingo/tree/main/vectorstores/pgvector), KubeAGI adds the PG vector support to [langchaingo](https://github.com/tmc/langchaingo) project. +- ✅ [ChromaDB](https://docs.trychroma.com/) ## Pure Go Toolchains @@ -70,25 +86,15 @@ To enhance the AI capability in Golang, we developed some packages.Here are the - [zhipuai](https://github.com/kubeagi/arcadia/blob/main/examples/zhipuai/main.go) shows how to use this [zhipuai client](https://github.com/kubeagi/arcadia/tree/main/pkg/llms/zhipuai) - [dashscope](https://github.com/kubeagi/arcadia/blob/main/examples/dashscope/main.go) shows how to use this [dashscope client](https://github.com/kubeagi/arcadia/tree/main/pkg/llms/dashscope) 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 - -- ✅ [ZhiPuAI(智谱 AI)](https://github.com/kubeagi/arcadia/tree/main/pkg/llms/zhipuai) - - [example](https://github.com/kubeagi/arcadia/blob/main/examples/zhipuai/main.go) -- ✅ [DashScope(灵积模型服务)](https://github.com/kubeagi/arcadia/tree/main/pkg/llms/dashscope) - - see [example](https://github.com/kubeagi/arcadia/blob/main/examples/dashscope/main.go) - -### Embeddings - -> Fully compatible with [langchain embeddings](https://github.com/tmc/langchaingo/tree/main/embeddings) - -- ✅ [ZhiPuAI(智谱 AI) Embedding](https://github.com/kubeagi/arcadia/tree/main/pkg/embeddings/zhipuai) -- ✅ [DashScope(灵积模型服务) text-embedding-v1(通用文本向量 同步接口)](https://help.aliyun.com/zh/dashscope/developer-reference/text-embedding-api-details) - -### VectorStores +## CLI -> Fully compatible with [langchain vectorstores](https://github.com/tmc/langchaingo/tree/main/vectorstores) +We provide a Command Line Tool `arctl` to interact with `arcadia`. See [here](http://kubeagi.k8s.com.cn/docs/Tools/arctl-tool) for more details. -- ✅ [ChromaDB](https://docs.trychroma.com/) +- ✅ datasource management +- ✅ local dataset management +- ✅ chat & completion +- ✅ download files from datasource +- ✅ RAG evaluation ## Contribute to Arcadia