tdpeuter/open-webui
tdpeuter/open-webui
1
Fork 0
forked from open-webui/open-webui
Code Issues Pull requests 1 Projects 1 Releases 2 Packages Activity Actions

Merge pull request #1495 from cheahjs/feat/parallelize-docker-build

Browse source 
feat: parallelize docker build
This commit is contained in:
Timothy Jaeryang Baek 2024-04-10 12:53:37 -07:00 committed by GitHub
commit a85e93f1f9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 352 additions and 55 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

341
.github/workflows/docker-build.yaml vendored
View file

@ -1,6 +1,5 @@
name: Create and publish Docker images with specific build args
# Configures this workflow to run every time a change is pushed to the branch called `release`.
on:
workflow_dispatch:
push:
@ -10,30 +9,39 @@ on:
tags:
- v*
# Defines two custom environment variables for the workflow. These are used for the Container registry domain, and a name for the Docker image that this workflow builds.
env:
REGISTRY: ghcr.io
IMAGE_NAME: ${{ github.repository }}
FULL_IMAGE_NAME: ghcr.io/${{ github.repository }}
# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
jobs:
build-and-push-image:
build-main-image:
runs-on: ubuntu-latest
# Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
permissions:
contents: read
packages: write
strategy:
fail-fast: false
matrix:
platform:
- linux/amd64
- linux/arm64
steps:
- name: Prepare
run: |
platform=${{ matrix.platform }}
echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
- name: Checkout repository
uses: actions/checkout@v4
# Required for multi architecture build
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
# Required for multi architecture build
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
# Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
- name: Log in to the Container registry
uses: docker/login-action@v3
with:
@ -42,10 +50,10 @@ jobs:
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata for Docker images (default latest tag)
id: meta-latest
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
images: ${{ env.FULL_IMAGE_NAME }}
tags: |
type=ref,event=branch
type=ref,event=tag
@ -55,31 +63,320 @@ jobs:
flavor: |
latest=${{ github.ref == 'refs/heads/main' }}
- name: Build and push Docker image (latest)
- name: Build Docker image (latest)
uses: docker/build-push-action@v5
id: build
with:
context: .
push: true
platforms: linux/amd64,linux/arm64
tags: ${{ steps.meta-latest.outputs.tags }}
labels: ${{ steps.meta-latest.outputs.labels }}
platforms: ${{ matrix.platform }}
labels: ${{ steps.meta.outputs.labels }}
outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
cache-from: type=gha
cache-to: type=gha,mode=max
- name: Build and push Docker image with CUDA
- name: Export digest
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
- name: Upload digest
uses: actions/upload-artifact@v4
with:
name: digests-main-${{ env.PLATFORM_PAIR }}
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
build-cuda-image:
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
strategy:
fail-fast: false
matrix:
platform:
- linux/amd64
- linux/arm64
steps:
- name: Prepare
run: |
platform=${{ matrix.platform }}
echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
- name: Checkout repository
uses: actions/checkout@v4
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Log in to the Container registry
uses: docker/login-action@v3
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata for Docker images (default latest tag)
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.FULL_IMAGE_NAME }}
tags: |
type=ref,event=branch
type=ref,event=tag
type=sha,prefix=git-
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=cuda
flavor: |
latest=${{ github.ref == 'refs/heads/main' }}
suffix=-cuda,onlatest=true
- name: Build Docker image (cuda)
uses: docker/build-push-action@v5
if: github.ref == 'refs/heads/main'
id: build
with:
context: .
push: true
platforms: linux/amd64,linux/arm64
tags: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:cuda
platforms: ${{ matrix.platform }}
labels: ${{ steps.meta.outputs.labels }}
outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
cache-from: type=gha
cache-to: type=gha,mode=max
build-args: USE_CUDA=true
- name: Build and push Docker image with Ollama
- name: Export digest
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
- name: Upload digest
uses: actions/upload-artifact@v4
with:
name: digests-cuda-${{ env.PLATFORM_PAIR }}
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
build-ollama-image:
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
strategy:
fail-fast: false
matrix:
platform:
- linux/amd64
- linux/arm64
steps:
- name: Prepare
run: |
platform=${{ matrix.platform }}
echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
- name: Checkout repository
uses: actions/checkout@v4
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Log in to the Container registry
uses: docker/login-action@v3
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata for Docker images (ollama tag)
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.FULL_IMAGE_NAME }}
tags: |
type=ref,event=branch
type=ref,event=tag
type=sha,prefix=git-
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=ollama
flavor: |
latest=${{ github.ref == 'refs/heads/main' }}
suffix=-ollama,onlatest=true
- name: Build Docker image (ollama)
uses: docker/build-push-action@v5
if: github.ref == 'refs/heads/main'
id: build
with:
context: .
push: true
platforms: linux/amd64,linux/arm64
tags: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:ollama
platforms: ${{ matrix.platform }}
labels: ${{ steps.meta.outputs.labels }}
outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
cache-from: type=gha
cache-to: type=gha,mode=max
build-args: USE_OLLAMA=true
- name: Export digest
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
- name: Upload digest
uses: actions/upload-artifact@v4
with:
name: digests-ollama-${{ env.PLATFORM_PAIR }}
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
merge-main-images:
runs-on: ubuntu-latest
needs: [ build-main-image ]
steps:
- name: Download digests
uses: actions/download-artifact@v4
with:
pattern: digests-main-*
path: /tmp/digests
merge-multiple: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Log in to the Container registry
uses: docker/login-action@v3
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata for Docker images (default latest tag)
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.FULL_IMAGE_NAME }}
tags: |
type=ref,event=branch
type=ref,event=tag
type=sha,prefix=git-
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
flavor: |
latest=${{ github.ref == 'refs/heads/main' }}
- name: Create manifest list and push
working-directory: /tmp/digests
run: |
docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
$(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
- name: Inspect image
run: |
docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}
merge-cuda-images:
runs-on: ubuntu-latest
needs: [ build-cuda-image ]
steps:
- name: Download digests
uses: actions/download-artifact@v4
with:
pattern: digests-cuda-*
path: /tmp/digests
merge-multiple: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Log in to the Container registry
uses: docker/login-action@v3
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata for Docker images (default latest tag)
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.FULL_IMAGE_NAME }}
tags: |
type=ref,event=branch
type=ref,event=tag
type=sha,prefix=git-
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
flavor: |
latest=${{ github.ref == 'refs/heads/main' }}
suffix=-cuda,onlatest=true
- name: Create manifest list and push
working-directory: /tmp/digests
run: |
docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
$(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
- name: Inspect image
run: |
docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}
merge-ollama-images:
runs-on: ubuntu-latest
needs: [ build-ollama-image ]
steps:
- name: Download digests
uses: actions/download-artifact@v4
with:
pattern: digests-ollama-*
path: /tmp/digests
merge-multiple: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Log in to the Container registry
uses: docker/login-action@v3
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata for Docker images (default ollama tag)
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.FULL_IMAGE_NAME }}
tags: |
type=ref,event=branch
type=ref,event=tag
type=sha,prefix=git-
type=semver,pattern={{version}}
type=semver,pattern={{major}}.{{minor}}
flavor: |
latest=${{ github.ref == 'refs/heads/main' }}
suffix=-ollama,onlatest=true
- name: Create manifest list and push
working-directory: /tmp/digests
run: |
docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
$(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
- name: Inspect image
run: |
docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}

66
Dockerfile
View file

@ -12,7 +12,7 @@ ARG USE_CUDA_VER=cu121
ARG USE_EMBEDDING_MODEL=all-MiniLM-L6-v2
######## WebUI frontend ########
FROM node:21-alpine3.19 as build
FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build
WORKDIR /app
@ -67,43 +67,43 @@ ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
#### Other models ##########################################################
WORKDIR /app/backend
RUN if [ "$USE_OLLAMA" = "true" ]; then \
apt-get update && \
# Install pandoc and netcat
apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
# for RAG OCR
apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
# install helper tools
apt-get install -y --no-install-recommends curl && \
# install ollama
curl -fsSL https://ollama.com/install.sh | sh && \
# cleanup
rm -rf /var/lib/apt/lists/*; \
else \
apt-get update && \
# Install pandoc and netcat
apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
# for RAG OCR
apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
# cleanup
rm -rf /var/lib/apt/lists/*; \
fi
# install python dependencies
COPY ./backend/requirements.txt ./requirements.txt
RUN if [ "$USE_CUDA" = "true" ]; then \
# If you use CUDA the whisper and embedding modell will be downloaded on first use
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
pip3 install -r requirements.txt --no-cache-dir && \
python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
# If you use CUDA the whisper and embedding model will be downloaded on first use
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
pip3 install -r requirements.txt --no-cache-dir && \
python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
else \
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
pip3 install -r requirements.txt --no-cache-dir && \
python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
fi
RUN if [ "$USE_OLLAMA" = "true" ]; then \
apt-get update && \
# Install pandoc and netcat
apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
# for RAG OCR
apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
# install helper tools
apt-get install -y --no-install-recommends curl && \
# install ollama
curl -fsSL https://ollama.com/install.sh | sh && \
# cleanup
rm -rf /var/lib/apt/lists/*; \
else \
apt-get update && \
# Install pandoc and netcat
apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
# for RAG OCR
apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
# cleanup
rm -rf /var/lib/apt/lists/*; \
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
pip3 install -r requirements.txt --no-cache-dir && \
python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
fi