mirror of
https://github.com/mudler/LocalAI.git
synced 2025-06-17 16:25:00 +00:00

* feat: Add backend gallery This PR add support to manage backends as similar to models. There is now available a backend gallery which can be used to install and remove extra backends. The backend gallery can be configured similarly as a model gallery, and API calls allows to install and remove new backends in runtime, and as well during the startup phase of LocalAI. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add backends docs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * wip: Backend Dockerfile for python backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: drop extras images, build python backends separately Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixup on all backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * test CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tweaks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Drop old backends leftovers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixup CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move dockerfile upper Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fix proto Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Feature dropped for consistency - we prefer model galleries Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add missing packages in the build image Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * exllama is ponly available on cublas Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * pin torch on chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Fixups to index Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Debug CI * Install accellerators deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add target arch * Add cuda minor version Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use self-hosted runners Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: use quay for test images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups for vllm and chatterbox Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Small fixups on CI Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chatterbox is only available for nvidia Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Simplify CI builds Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Adapt test, use qwen3 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(model gallery): add jina-reranker-v1-tiny-en-gguf Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(gguf-parser): recover from potential panics that can happen while reading ggufs with gguf-parser Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use reranker from llama.cpp in AIO images Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Limit concurrent jobs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
198 lines
No EOL
6.7 KiB
YAML
198 lines
No EOL
6.7 KiB
YAML
---
|
|
name: 'build python backend container images (reusable)'
|
|
|
|
on:
|
|
workflow_call:
|
|
inputs:
|
|
base-image:
|
|
description: 'Base image'
|
|
required: true
|
|
type: string
|
|
build-type:
|
|
description: 'Build type'
|
|
default: ''
|
|
type: string
|
|
cuda-major-version:
|
|
description: 'CUDA major version'
|
|
default: "12"
|
|
type: string
|
|
cuda-minor-version:
|
|
description: 'CUDA minor version'
|
|
default: "1"
|
|
type: string
|
|
platforms:
|
|
description: 'Platforms'
|
|
default: ''
|
|
type: string
|
|
tag-latest:
|
|
description: 'Tag latest'
|
|
default: ''
|
|
type: string
|
|
latest-image:
|
|
description: 'Tag latest'
|
|
default: ''
|
|
type: string
|
|
tag-suffix:
|
|
description: 'Tag suffix'
|
|
default: ''
|
|
type: string
|
|
runs-on:
|
|
description: 'Runs on'
|
|
required: true
|
|
default: ''
|
|
type: string
|
|
backend:
|
|
description: 'Backend to build'
|
|
required: true
|
|
type: string
|
|
secrets:
|
|
dockerUsername:
|
|
required: true
|
|
dockerPassword:
|
|
required: true
|
|
quayUsername:
|
|
required: true
|
|
quayPassword:
|
|
required: true
|
|
|
|
jobs:
|
|
reusable_python_backend-build:
|
|
runs-on: ${{ inputs.runs-on }}
|
|
steps:
|
|
- name: Force Install GIT latest
|
|
run: |
|
|
sudo apt-get update \
|
|
&& sudo apt-get install -y software-properties-common \
|
|
&& sudo apt-get update \
|
|
&& sudo add-apt-repository -y ppa:git-core/ppa \
|
|
&& sudo apt-get update \
|
|
&& sudo apt-get install -y git
|
|
|
|
- name: Checkout
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Release space from worker
|
|
if: inputs.runs-on == 'ubuntu-latest'
|
|
run: |
|
|
echo "Listing top largest packages"
|
|
pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
|
|
head -n 30 <<< "${pkgs}"
|
|
echo
|
|
df -h
|
|
echo
|
|
sudo apt-get autoremove -y
|
|
sudo apt-get clean
|
|
echo
|
|
df -h
|
|
|
|
- name: Docker meta
|
|
id: meta
|
|
if: github.event_name != 'pull_request'
|
|
uses: docker/metadata-action@v5
|
|
with:
|
|
images: |
|
|
quay.io/go-skynet/local-ai-backends
|
|
localai/localai-backends
|
|
tags: |
|
|
type=ref,event=branch
|
|
type=semver,pattern={{raw}}
|
|
type=sha
|
|
flavor: |
|
|
latest=${{ inputs.tag-latest }}
|
|
suffix=${{ inputs.tag-suffix }}
|
|
|
|
- name: Docker meta for PR
|
|
id: meta_pull_request
|
|
if: github.event_name == 'pull_request'
|
|
uses: docker/metadata-action@v5
|
|
with:
|
|
images: |
|
|
quay.io/go-skynet/ci-tests
|
|
tags: |
|
|
type=ref,event=branch,suffix=${{ github.event.number }}-${{ inputs.backend }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
|
|
type=semver,pattern={{raw}},suffix=${{ github.event.number }}-${{ inputs.backend }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
|
|
type=sha,suffix=${{ github.event.number }}-${{ inputs.backend }}-${{ inputs.build-type }}-${{ inputs.cuda-major-version }}-${{ inputs.cuda-minor-version }}
|
|
flavor: |
|
|
latest=${{ inputs.tag-latest }}
|
|
suffix=${{ inputs.tag-suffix }}
|
|
## End testing image
|
|
- name: Set up QEMU
|
|
uses: docker/setup-qemu-action@master
|
|
with:
|
|
platforms: all
|
|
|
|
- name: Set up Docker Buildx
|
|
id: buildx
|
|
uses: docker/setup-buildx-action@master
|
|
|
|
- name: Login to DockerHub
|
|
if: github.event_name != 'pull_request'
|
|
uses: docker/login-action@v3
|
|
with:
|
|
username: ${{ secrets.dockerUsername }}
|
|
password: ${{ secrets.dockerPassword }}
|
|
|
|
- name: Login to Quay.io
|
|
# if: github.event_name != 'pull_request'
|
|
uses: docker/login-action@v3
|
|
with:
|
|
registry: quay.io
|
|
username: ${{ secrets.quayUsername }}
|
|
password: ${{ secrets.quayPassword }}
|
|
|
|
- name: Build and push
|
|
uses: docker/build-push-action@v6
|
|
if: github.event_name != 'pull_request'
|
|
with:
|
|
builder: ${{ steps.buildx.outputs.name }}
|
|
build-args: |
|
|
BUILD_TYPE=${{ inputs.build-type }}
|
|
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
|
|
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
|
|
BASE_IMAGE=${{ inputs.base-image }}
|
|
BACKEND=${{ inputs.backend }}
|
|
context: ./backend
|
|
file: ./backend/Dockerfile.python
|
|
cache-from: type=gha
|
|
platforms: ${{ inputs.platforms }}
|
|
push: ${{ github.event_name != 'pull_request' }}
|
|
tags: ${{ steps.meta.outputs.tags }}
|
|
labels: ${{ steps.meta.outputs.labels }}
|
|
|
|
- name: Build and push (PR)
|
|
uses: docker/build-push-action@v6
|
|
if: github.event_name == 'pull_request'
|
|
with:
|
|
builder: ${{ steps.buildx.outputs.name }}
|
|
build-args: |
|
|
BUILD_TYPE=${{ inputs.build-type }}
|
|
CUDA_MAJOR_VERSION=${{ inputs.cuda-major-version }}
|
|
CUDA_MINOR_VERSION=${{ inputs.cuda-minor-version }}
|
|
BASE_IMAGE=${{ inputs.base-image }}
|
|
BACKEND=${{ inputs.backend }}
|
|
context: ./backend
|
|
file: ./backend/Dockerfile.python
|
|
cache-from: type=gha
|
|
platforms: ${{ inputs.platforms }}
|
|
push: true
|
|
tags: ${{ steps.meta_pull_request.outputs.tags }}
|
|
labels: ${{ steps.meta_pull_request.outputs.labels }}
|
|
|
|
- name: Cleanup
|
|
run: |
|
|
docker builder prune -f
|
|
docker system prune --force --volumes --all
|
|
|
|
- name: Latest tag
|
|
if: github.event_name != 'pull_request' && inputs.latest-image != '' && github.ref_type == 'tag'
|
|
run: |
|
|
docker pull localai/localai-backends:${{ steps.meta.outputs.version }}
|
|
docker tag localai/localai-backends:${{ steps.meta.outputs.version }} localai/localai-backends:${{ inputs.latest-image }}
|
|
docker push localai/localai-backends:${{ inputs.latest-image }}
|
|
docker pull quay.io/go-skynet/local-ai-backends:${{ steps.meta.outputs.version }}
|
|
docker tag quay.io/go-skynet/local-ai-backends:${{ steps.meta.outputs.version }} quay.io/go-skynet/local-ai-backends:${{ inputs.latest-image }}
|
|
docker push quay.io/go-skynet/local-ai-backends:${{ inputs.latest-image }}
|
|
|
|
- name: job summary
|
|
run: |
|
|
echo "Built image: ${{ steps.meta.outputs.labels }}" >> $GITHUB_STEP_SUMMARY |