diff --git a/README.md b/README.md index 4868735d6e2d..ad5d3870cb14 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@

> :bulb: Get help - [❓FAQ](https://localai.io/faq/) [πŸ’­Discussions](https://github.com/go-skynet/LocalAI/discussions) [:speech_balloon: Discord](https://discord.gg/uJAeKSAGDy) [:book: Documentation website](https://localai.io/) -> +> > [πŸ’» Quickstart](https://localai.io/basics/getting_started/) [πŸ“£ News](https://localai.io/basics/news/) [ πŸ›« Examples ](https://github.com/go-skynet/LocalAI/tree/master/examples/) [ πŸ–ΌοΈ Models ](https://localai.io/models/) [ πŸš€ Roadmap ](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap) [![tests](https://github.com/go-skynet/LocalAI/actions/workflows/test.yml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/test.yml)[![Build and Release](https://github.com/go-skynet/LocalAI/actions/workflows/release.yaml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/release.yaml)[![build container images](https://github.com/go-skynet/LocalAI/actions/workflows/image.yml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/image.yml)[![Bump dependencies](https://github.com/go-skynet/LocalAI/actions/workflows/bump_deps.yaml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/bump_deps.yaml)[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/localai)](https://artifacthub.io/packages/search?repo=localai) @@ -54,7 +54,7 @@

-Follow _LocalAI +Follow _LocalAI Share on Telegram @@ -85,12 +85,12 @@ In a nutshell: - Local, OpenAI drop-in alternative REST API. You own your data. - NO GPU required. NO Internet access is required either - - Optional, GPU Acceleration is available in `llama.cpp`-compatible LLMs. See also the [build section](https://localai.io/basics/build/index.html). + - Optional, GPU Acceleration is available in `llama.cpp`-compatible LLMs. See also the [build section](https://localai.io/basics/build/index.html). - Supports multiple models - πŸƒ Once loaded the first time, it keep models loaded in memory for faster inference - ⚑ Doesn't shell-out, but uses C++ bindings for a faster inference and better performance. -LocalAI was created by [Ettore Di Giacinto](https://github.com/mudler/) and is a community-driven project, focused on making the AI accessible to anyone. Any contribution, feedback and PR is welcome! +LocalAI was created by [Ettore Di Giacinto](https://github.com/mudler/) and is a community-driven project, focused on making the AI accessible to anyone. Any contribution, feedback and PR is welcome! Note that this started just as a [fun weekend project](https://localai.io/#backstory) in order to try to create the necessary pieces for a full AI assistant like `ChatGPT`: the community is growing fast and we are working hard to make it better and more stable. If you want to help, please consider contributing (see below)! @@ -112,6 +112,9 @@ Check out the [Getting started](https://localai.io/basics/getting_started/index. ### πŸ”— Community and integrations +Build and deploy custom containers: +- https://github.com/sozercan/aikit + WebUIs: - https://github.com/Jirubizu/localai-admin - https://github.com/go-skynet/LocalAI-frontend @@ -129,7 +132,7 @@ Other: - [How to install in Kubernetes](https://localai.io/basics/getting_started/index.html#run-localai-in-kubernetes) - [Projects integrating LocalAI](https://localai.io/integrations/) - [How tos section](https://localai.io/howtos/) (curated by our community) - + ## :book: πŸŽ₯ [Media, Blogs, Social](https://localai.io/basics/news/#media-blogs-social) - [Create a slackbot for teams and OSS projects that answer to documentation](https://mudler.pm/posts/smart-slackbot-for-teams/) @@ -159,12 +162,12 @@ Support the project by becoming [a backer or sponsor](https://github.com/sponsor A huge thank you to our generous sponsors who support this project: -| ![Spectro Cloud logo_600x600px_transparent bg](https://github.com/go-skynet/LocalAI/assets/2420543/68a6f3cb-8a65-4a4d-99b5-6417a8905512) | +| ![Spectro Cloud logo_600x600px_transparent bg](https://github.com/go-skynet/LocalAI/assets/2420543/68a6f3cb-8a65-4a4d-99b5-6417a8905512) | |:-----------------------------------------------:| -| [Spectro Cloud](https://www.spectrocloud.com/) | +| [Spectro Cloud](https://www.spectrocloud.com/) | | Spectro Cloud kindly supports LocalAI by providing GPU and computing resources to run tests on lamdalabs! | -And a huge shout-out to individuals sponsoring the project by donating hardware or backing the project. +And a huge shout-out to individuals sponsoring the project by donating hardware or backing the project. - [Sponsor list](https://github.com/sponsors/mudler) - JDAM00 (donating HW for the CI) diff --git a/docs/content/integrations/AIKit.md b/docs/content/integrations/AIKit.md new file mode 100644 index 000000000000..56ea3cecf43e --- /dev/null +++ b/docs/content/integrations/AIKit.md @@ -0,0 +1,178 @@ + ++++ +disableToc = false +title = "AIKit" +description="AI + BuildKit = AIKit: Build and deploy large language models easily" +weight = 2 ++++ + +GitHub Link - https://github.com/sozercan/aikit + +[AIKit](https://github.com/sozercan/aikit) is a quick, easy, and local or cloud-agnostic way to get started to host and deploy large language models (LLMs) for inference. No GPU, internet access or additional tools are needed to get started except for [Docker](https://docs.docker.com/desktop/install/linux-install/)! + +AIKit uses [LocalAI](https://localai.io/) under-the-hood to run inference. LocalAI provides a drop-in replacement REST API that is OpenAI API compatible, so you can use any OpenAI API compatible client, such as [Kubectl AI](https://github.com/sozercan/kubectl-ai), [Chatbot-UI](https://github.com/sozercan/chatbot-ui) and many more, to send requests to open-source LLMs powered by AIKit! + +> At this time, AIKit is tested with LocalAI `llama` backend. Other backends may work but are not tested. Please open an issue if you'd like to see support for other backends. + +## Features + +- 🐳 No GPU, Internet access or additional tools needed except for [Docker](https://docs.docker.com/desktop/install/linux-install/)! +- 🀏 Minimal image size, resulting in less vulnerabilities and smaller attack surface with a custom [distroless](https://github.com/GoogleContainerTools/distroless)-based image +- πŸš€ Easy to use declarative configuration +- ✨ OpenAI API compatible to use with any OpenAI API compatible client +- 🚒 Kubernetes deployment ready +- πŸ“¦ Supports multiple models with a single image +- πŸ–₯️ Supports GPU-accelerated inferencing with NVIDIA GPUs +- πŸ” Signed images for `aikit` and pre-made models + +## Pre-made Models + +AIKit comes with pre-made models that you can use out-of-the-box! + +### CPU +- πŸ¦™ Llama 2 7B Chat: `ghcr.io/sozercan/llama2:7b` +- πŸ¦™ Llama 2 13B Chat: `ghcr.io/sozercan/llama2:13b` +- 🐬 Orca 2 13B: `ghcr.io/sozercan/orca2:13b` + +### NVIDIA CUDA + +- πŸ¦™ Llama 2 7B Chat (CUDA): `ghcr.io/sozercan/llama2:7b-cuda` +- πŸ¦™ Llama 2 13B Chat (CUDA): `ghcr.io/sozercan/llama2:13b-cuda` +- 🐬 Orca 2 13B (CUDA): `ghcr.io/sozercan/orca2:13b-cuda` + +> CUDA models includes CUDA v12. They are used with [NVIDIA GPU acceleration](#gpu-acceleration-support). + +## Quick Start + +### Creating an image + +> This section shows how to create a custom image with models of your choosing. If you want to use one of the pre-made models, skip to [running models](#running-models). +> +> Please see [models folder](./models/) for pre-made model definitions. You can find more model examples at [go-skynet/model-gallery](https://github.com/go-skynet/model-gallery). + +Create an `aikitfile.yaml` with the following structure: + +```yaml +#syntax=ghcr.io/sozercan/aikit:latest +apiVersion: v1alpha1 +models: + - name: llama-2-7b-chat + source: https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q4_K_M.gguf +``` + +> This is the simplest way to get started to build an image. For full `aikitfile` specification, see [specs](docs/specs.md). + +First, create a buildx buildkit instance. Alternatively, if you are using Docker v24 with [containerd image store](https://docs.docker.com/storage/containerd/) enabled, you can skip this step. + +```bash +docker buildx create --use --name aikit-builder +``` + +Then build your image with: + +```bash +docker buildx build . -t my-model -f aikitfile.yaml --load +``` + +This will build a local container image with your model(s). You can see the image with: + +```bash +docker images +REPOSITORY TAG IMAGE ID CREATED SIZE +my-model latest e7b7c5a4a2cb About an hour ago 5.51GB +``` + +### Running models + +You can start the inferencing server for your models with: + +```bash +# for pre-made models, replace "my-model" with the image name +docker run -d --rm -p 8080:8080 my-model +``` + +You can then send requests to `localhost:8080` to run inference from your models. For example: + +```bash +curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{ + "model": "llama-2-7b-chat", + "messages": [{"role": "user", "content": "explain kubernetes in a sentence"}] + }' +{"created":1701236489,"object":"chat.completion","id":"dd1ff40b-31a7-4418-9e32-42151ab6875a","model":"llama-2-7b-chat","choices":[{"index":0,"finish_reason":"stop","message":{"role":"assistant","content":"\nKubernetes is a container orchestration system that automates the deployment, scaling, and management of containerized applications in a microservices architecture."}}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}} +``` + +## Kubernetes Deployment + +It is easy to get started to deploy your models to Kubernetes! + +Make sure you have a Kubernetes cluster running and `kubectl` is configured to talk to it, and your model images are accessible from the cluster. + +> You can use [kind](https://kind.sigs.k8s.io/) to create a local Kubernetes cluster for testing purposes. + +```bash +# create a deployment +# for pre-made models, replace "my-model" with the image name +kubectl create deployment my-llm-deployment --image=my-model + +# expose it as a service +kubectl expose deployment my-llm-deployment --port=8080 --target-port=8080 --name=my-llm-service + +# easy to scale up and down as needed +kubectl scale deployment my-llm-deployment --replicas=3 + +# port-forward for testing locally +kubectl port-forward service/my-llm-service 8080:8080 + +# send requests to your model +curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{ + "model": "llama-2-7b-chat", + "messages": [{"role": "user", "content": "explain kubernetes in a sentence"}] + }' +{"created":1701236489,"object":"chat.completion","id":"dd1ff40b-31a7-4418-9e32-42151ab6875a","model":"llama-2-7b-chat","choices":[{"index":0,"finish_reason":"stop","message":{"role":"assistant","content":"\nKubernetes is a container orchestration system that automates the deployment, scaling, and management of containerized applications in a microservices architecture."}}],"usage":{"prompt_tokens":0,"completion_tokens":0,"total_tokens":0}} +``` + +> For an example Kubernetes deployment and service YAML, see [kubernetes folder](./kubernetes/). Please note that these are examples, you may need to customize them (such as properly configured resource requests and limits) based on your needs. + +## GPU Acceleration Support + +> At this time, only NVIDIA GPU acceleration is supported. Please open an issue if you'd like to see support for other GPU vendors. + +### NVIDIA + +AIKit supports GPU accelerated inferencing with [NVIDIA Container Toolkit](https://github.com/NVIDIA/nvidia-container-toolkit). You must also have [NVIDIA Drivers](https://www.nvidia.com/en-us/drivers/unix/) installed on your host machine. + +For Kubernetes, [NVIDIA GPU Operator](https://github.com/NVIDIA/gpu-operator) provides a streamlined way to install the NVIDIA drivers and container toolkit to configure your cluster to use GPUs. + +To get started with GPU-accelerated inferencing, make sure to set the following in your `aikitfile` and build your model. + +```yaml +runtime: cuda # use NVIDIA CUDA runtime +f16: true # use float16 precision +gpu_layers: 35 # number of layers to offload to GPU +low_vram: true # for devices with low VRAM +``` + +> Make sure to customize these values based on your model and GPU specs. + +After building the model, you can run it with [`--gpus all`](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/docker-specialized.html#gpu-enumeration) flag to enable GPU support: + +```bash +# for pre-made models, replace "my-model" with the image name +docker run --rm --gpus all -p 8080:8080 my-model +``` + +If GPU acceleration is working, you'll see output that is similar to following in the debug logs: + +```bash +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr ggml_init_cublas: found 1 CUDA devices: +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr Device 0: Tesla T4, compute capability 7.5 +... +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr llm_load_tensors: using CUDA for GPU acceleration +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr llm_load_tensors: mem required = 70.41 MB (+ 2048.00 MB per state) +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr llm_load_tensors: offloading 32 repeating layers to GPU +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr llm_load_tensors: offloading non-repeating layers to GPU +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr llm_load_tensors: offloading v cache to GPU +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr llm_load_tensors: offloading k cache to GPU +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr llm_load_tensors: offloaded 35/35 layers to GPU +5:32AM DBG GRPC(llama-2-7b-chat.Q4_K_M.gguf-127.0.0.1:43735): stderr llm_load_tensors: VRAM used: 5869 MB +```