Build & Publish AnythingLLM for ARM64 and x86 (#549)

* Update build process to support multi-platform builds Bump @lancedb/vectordb to 0.1.19 for ARM&AMD compatibility Patch puppeteer on ARM builds because of broken chromium resolves #539 resolves #548 --------- Co-authored-by: shatfield4 <[email protected]>
Mintplex-Labs · Jan 9, 2024 · 58971e8 · 58971e8
1 parent cce48c2
commit 58971e8
Show file tree

Hide file tree

Showing 9 changed files with 202 additions and 60 deletions.
diff --git a/.github/workflows/build-and-push-image.yaml b/.github/workflows/build-and-push-image.yaml
@@ -1,8 +1,18 @@
-name: Publish Docker image and Github Registry
+# This Github action is for publishing of the primary image for AnythingLLM
+# It will publish a linux/amd64 and linux/arm64 image at the same time
+# This file should ONLY BY USED FOR `master` BRANCH. 
+# TODO: Update `runs-on` for arm64 when GitHub finally supports
+# native arm environments as QEMU takes around 1 hour to build
+# ref: https://github.com/actions/runner-images/issues/5631 :(
+name: Publish AnythingLLM Primary Docker image (amd64/arm64)
+
+concurrency:
+  group: build-${{ github.ref }}
+  cancel-in-progress: true
 
 on:
   push:
-    branches: ['master']
+    branches: ['master'] # master branch only. Do not modify.
     paths-ignore:
       - '*.md'
       - 'cloud-deployments/*'
@@ -11,15 +21,26 @@ on:
       - '**/.env.example'
 
 jobs:
-  push_to_registries:
-    name: Push Docker image to multiple registries
+  push_multi_platform_to_registries:
+    name: Push Docker multi-platform image to multiple registries
     runs-on: ubuntu-latest
     permissions:
       packages: write
       contents: read
     steps:
       - name: Check out the repo
         uses: actions/checkout@v4
+
+      - name: Parse repository name to lowercase
+        shell: bash
+        run: echo "repo=${GITHUB_REPOSITORY,,}" >> $GITHUB_OUTPUT
+        id: lowercase_repo
+
+      - 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 Docker Hub
         uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a
@@ -42,11 +63,15 @@ jobs:
             mintplexlabs/anythingllm
             ghcr.io/${{ github.repository }}
       
-      - name: Build and push Docker images
-        uses: docker/build-push-action@3b5e8027fcad23fda98b2e3ac259d8d67585f671
+      - name: Build and push multi-platform Docker image
+        uses: docker/build-push-action@v5
         with:
           context: .
           file: ./docker/Dockerfile
           push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
+          platforms: linux/amd64,linux/arm64
+          tags: |
+            ${{ steps.meta.outputs.tags }}
+            ${{ github.ref_name == 'master' && 'mintplexlabs/anythingllm:latest' || '' }}
+            ${{ github.ref_name == 'master' && format('ghcr.io/{0}:{1}', steps.lowercase_repo.outputs.repo, 'latest') || '' }}
+          labels: ${{ steps.meta.outputs.labels }}
diff --git a/clean.sh b/clean.sh
diff --git a/collector/package.json b/collector/package.json
@@ -34,7 +34,7 @@
     "multer": "^1.4.5-lts.1",
     "officeparser": "^4.0.5",
     "pdf-parse": "^1.1.1",
-    "puppeteer": "^21.6.1",
+    "puppeteer": "~21.5.2",
     "slugify": "^1.6.6",
     "url-pattern": "^1.0.3",
     "uuid": "^9.0.0",

diff --git a/collector/yarn.lock b/collector/yarn.lock
@@ -134,10 +134,10 @@
   resolved "https://registry.yarnpkg.com/@protobufjs/utf8/-/utf8-1.1.0.tgz#a777360b5b39a1a2e5106f8e858f2fd2d060c570"
   integrity sha512-Vvn3zZrhQZkkBE8LSuW3em98c0FwgO4nxzv6OdSxPKJIEKY2bGbHn+mhGIPerzI4twdxaP8/0+06HBpwf345Lw==
 
-"@puppeteer/browsers@1.9.0":
-  version "1.9.0"
-  resolved "https://registry.yarnpkg.com/@puppeteer/browsers/-/browsers-1.9.0.tgz#dfd0aad0bdc039572f1b57648f189525d627b7ff"
-  integrity sha512-QwguOLy44YBGC8vuPP2nmpX4MUN2FzWbsnvZJtiCzecU3lHmVZkaC1tq6rToi9a200m8RzlVtDyxCS0UIDrxUg==
+"@puppeteer/browsers@1.8.0":
+  version "1.8.0"
+  resolved "https://registry.yarnpkg.com/@puppeteer/browsers/-/browsers-1.8.0.tgz#fb6ee61de15e7f0e67737aea9f9bab1512dbd7d8"
+  integrity sha512-TkRHIV6k2D8OlUe8RtG+5jgOF/H98Myx0M6AOafC8DdNVOFiBSFa5cpRDtpm8LXOa9sVwe0+e6Q3FC56X/DZfg==
   dependencies:
     debug "4.3.4"
     extract-zip "2.0.1"
@@ -608,10 +608,10 @@ chownr@^2.0.0:
   resolved "https://registry.yarnpkg.com/chownr/-/chownr-2.0.0.tgz#15bfbe53d2eab4cf70f18a8cd68ebe5b3cb1dece"
   integrity sha512-bIomtDF5KGpdogkLd9VspvFzk9KfpyyGlS8YFVZl7TGPBHL5snIOnxeshwVgPteQ9b4Eydl+pVbIyE1DcvCWgQ==
 
-chromium-bidi@0.5.1:
-  version "0.5.1"
-  resolved "https://registry.yarnpkg.com/chromium-bidi/-/chromium-bidi-0.5.1.tgz#390c1af350c4887824a33d82190de1cc5c5680fc"
-  integrity sha512-dcCqOgq9fHKExc2R4JZs/oKbOghWpUNFAJODS8WKRtLhp3avtIH5UDCBrutdqZdh3pARogH8y1ObXm87emwb3g==
+chromium-bidi@0.4.33:
+  version "0.4.33"
+  resolved "https://registry.yarnpkg.com/chromium-bidi/-/chromium-bidi-0.4.33.tgz#9a9aba5a5b07118c8e7d6405f8ee79f47418dd1d"
+  integrity sha512-IxoFM5WGQOIAd95qrSXzJUv4eXIrh+RvU3rwwqIiwYuvfE7U/Llj4fejbsJnjJMUYCuGtVQsY2gv7oGl4aTNSQ==
   dependencies:
     mitt "3.0.1"
     urlpattern-polyfill "9.0.0"
@@ -2584,26 +2584,26 @@ pump@^3.0.0:
     end-of-stream "^1.1.0"
     once "^1.3.1"
 
-puppeteer-core@21.6.1:
-  version "21.6.1"
-  resolved "https://registry.yarnpkg.com/puppeteer-core/-/puppeteer-core-21.6.1.tgz#10eccb4dc3167c8c26bc21122fabb45a9fda9ca7"
-  integrity sha512-0chaaK/RL9S1U3bsyR4fUeUfoj51vNnjWvXgG6DcsyMjwYNpLcAThv187i1rZCo7QhJP0wZN8plQkjNyrq2h+A==
+puppeteer-core@21.5.2:
+  version "21.5.2"
+  resolved "https://registry.yarnpkg.com/puppeteer-core/-/puppeteer-core-21.5.2.tgz#6d3de4efb2ae65f1ee072043787b75594e88035f"
+  integrity sha512-v4T0cWnujSKs+iEfmb8ccd7u4/x8oblEyKqplqKnJ582Kw8PewYAWvkH4qUWhitN3O2q9RF7dzkvjyK5HbzjLA==
   dependencies:
-    "@puppeteer/browsers" "1.9.0"
-    chromium-bidi "0.5.1"
+    "@puppeteer/browsers" "1.8.0"
+    chromium-bidi "0.4.33"
     cross-fetch "4.0.0"
     debug "4.3.4"
     devtools-protocol "0.0.1203626"
-    ws "8.15.1"
+    ws "8.14.2"
 
-puppeteer@^21.6.1:
-  version "21.6.1"
-  resolved "https://registry.yarnpkg.com/puppeteer/-/puppeteer-21.6.1.tgz#2ec0878906ff90b3a424f19e5eb006592abe25b6"
-  integrity sha512-O+pbc61oj8ln6m8EJKncrsQFmytgRyFYERtk190PeLbJn5JKpmmynn2p1PiFrlhCitAQXLJ0MOy7F0TeyCRqBg==
+puppeteer@~21.5.2:
+  version "21.5.2"
+  resolved "https://registry.yarnpkg.com/puppeteer/-/puppeteer-21.5.2.tgz#0a4a72175c0fd0944d6486f4734807e1671d527b"
+  integrity sha512-BaAGJOq8Fl6/cck6obmwaNLksuY0Bg/lIahCLhJPGXBFUD2mCffypa4A592MaWnDcye7eaHmSK9yot0pxctY8A==
   dependencies:
-    "@puppeteer/browsers" "1.9.0"
+    "@puppeteer/browsers" "1.8.0"
     cosmiconfig "8.3.6"
-    puppeteer-core "21.6.1"
+    puppeteer-core "21.5.2"
 
 [email protected]:
   version "6.11.0"
@@ -3259,10 +3259,10 @@ wrappy@1:
   resolved "https://registry.yarnpkg.com/wrappy/-/wrappy-1.0.2.tgz#b5243d8f3ec1aa35f1364605bc0d1036e30ab69f"
   integrity sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ==
 
-ws@8.15.1:
-  version "8.15.1"
-  resolved "https://registry.yarnpkg.com/ws/-/ws-8.15.1.tgz#271ba33a45ca0cc477940f7f200cd7fba7ee1997"
-  integrity sha512-W5OZiCjXEmk0yZ66ZN82beM5Sz7l7coYxpRkzS+p9PP+ToQry8szKh+61eNktr7EA9DOwvFGhfC605jDHbP6QQ==
+ws@8.14.2:
+  version "8.14.2"
+  resolved "https://registry.yarnpkg.com/ws/-/ws-8.14.2.tgz#6c249a806eb2db7a20d26d51e7709eab7b2e6c7f"
+  integrity sha512-wEBG1ftX4jcglPxgFCMJmZ2PLtSbJ2Peg6TmpJFTbe9GZYOQCDPdMYu/Tm0/bGZkw8paZnJY45J4K2PZrLYq8g==
 
 xmlbuilder@^10.0.0:
   version "10.1.1"

diff --git a/docker/Dockerfile b/docker/Dockerfile
@@ -1,14 +1,15 @@
 # Setup base image
 FROM ubuntu:jammy-20230522 AS base
 
-# Build arguments
 ARG ARG_UID=1000
 ARG ARG_GID=1000
 
-# Install system dependencies
+FROM base AS build-arm64
+RUN echo "Preparing build of AnythingLLM image for arm64 architecture"
+
 RUN DEBIAN_FRONTEND=noninteractive apt-get update && \
     DEBIAN_FRONTEND=noninteractive apt-get install -yq --no-install-recommends \
-        curl gnupg libgfortran5 libgbm1 tzdata netcat \
+        unzip curl gnupg libgfortran5 libgbm1 tzdata netcat \
         libasound2 libatk1.0-0 libc6 libcairo2 libcups2 libdbus-1-3 libexpat1 libfontconfig1 \
         libgcc1 libglib2.0-0 libgtk-3-0 libnspr4 libpango-1.0-0 libx11-6 libx11-xcb1 libxcb1 \
         libxcomposite1 libxcursor1 libxdamage1 libxext6 libxfixes3 libxi6 libxrandr2 libxrender1 \
@@ -38,21 +39,78 @@ RUN chmod +x /usr/local/bin/docker-entrypoint.sh && \
     chmod +x /usr/local/bin/docker-healthcheck.sh
 
 USER anythingllm
+WORKDIR /app
+
+# Puppeteer does not ship with an ARM86 compatible build for Chromium
+# so web-scraping would be broken in arm docker containers unless we patch it
+# by manually installing a compatible chromedriver.
+RUN echo "Need to patch Puppeteer x Chromium support for ARM86 - installing dep!" && \
+    curl https://playwright.azureedge.net/builds/chromium/1088/chromium-linux-arm64.zip -o chrome-linux.zip && \
+    unzip chrome-linux.zip && \
+    rm -rf chrome-linux.zip
+
+ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD=true
+ENV CHROME_PATH=/app/chrome-linux/chrome
+ENV PUPPETEER_EXECUTABLE_PATH=/app/chrome-linux/chrome
+
+RUN echo "Done running arm64 specific installtion steps"
 
+#############################################
+
+# amd64-specific stage
+FROM base AS build-amd64
+RUN echo "Preparing build of AnythingLLM image for non-ARM architecture"
+
+RUN DEBIAN_FRONTEND=noninteractive apt-get update && \
+    DEBIAN_FRONTEND=noninteractive apt-get install -yq --no-install-recommends \
+        curl gnupg libgfortran5 libgbm1 tzdata netcat \
+        libasound2 libatk1.0-0 libc6 libcairo2 libcups2 libdbus-1-3 libexpat1 libfontconfig1 \
+        libgcc1 libglib2.0-0 libgtk-3-0 libnspr4 libpango-1.0-0 libx11-6 libx11-xcb1 libxcb1 \
+        libxcomposite1 libxcursor1 libxdamage1 libxext6 libxfixes3 libxi6 libxrandr2 libxrender1 \
+        libxss1 libxtst6 ca-certificates fonts-liberation libappindicator1 libnss3 lsb-release \
+        xdg-utils git build-essential ffmpeg && \
+    mkdir -p /etc/apt/keyrings && \
+    curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg && \
+    echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_18.x nodistro main" | tee /etc/apt/sources.list.d/nodesource.list && \
+    apt-get update && \
+    apt-get install -yq --no-install-recommends nodejs && \
+    curl -LO https://github.com/yarnpkg/yarn/releases/download/v1.22.19/yarn_1.22.19_all.deb \
+        && dpkg -i yarn_1.22.19_all.deb \
+        && rm yarn_1.22.19_all.deb
+
+# Create a group and user with specific UID and GID
+RUN groupadd -g $ARG_GID anythingllm && \
+    useradd -u $ARG_UID -m -d /app -s /bin/bash -g anythingllm anythingllm && \
+    mkdir -p /app/frontend/ /app/server/ /app/collector/ && chown -R anythingllm:anythingllm /app
+
+# Copy docker helper scripts
+COPY ./docker/docker-entrypoint.sh /usr/local/bin/
+COPY ./docker/docker-healthcheck.sh /usr/local/bin/
+COPY --chown=anythingllm:anythingllm ./docker/.env.example /app/server/.env
+
+# Ensure the scripts are executable
+RUN chmod +x /usr/local/bin/docker-entrypoint.sh && \
+    chmod +x /usr/local/bin/docker-healthcheck.sh
+
+#############################################
+# COMMON BUILD FLOW FOR ALL ARCHS
+#############################################
+FROM build-${TARGETARCH} AS build
+RUN echo "Running common build flow of AnythingLLM image for all architectures"
+
+USER anythingllm
 WORKDIR /app
 
 # Install frontend dependencies
-FROM base as frontend-deps
+FROM build as frontend-deps
 
 COPY ./frontend/package.json ./frontend/yarn.lock ./frontend/
-RUN cd ./frontend/ && yarn install && yarn cache clean
+RUN cd ./frontend/ && yarn install --network-timeout 100000 && yarn cache clean
 
 # Install server dependencies
-FROM base as server-deps
+FROM build as server-deps
 COPY ./server/package.json ./server/yarn.lock ./server/
-RUN cd ./server/ && yarn install --production && yarn cache clean && \
-    rm /app/server/node_modules/vectordb/x86_64-apple-darwin.node && \
-    rm /app/server/node_modules/vectordb/aarch64-apple-darwin.node
+RUN cd ./server/ && yarn install --production --network-timeout 100000 && yarn cache clean
 
 # Compile Llama.cpp bindings for node-llama-cpp for this operating system.
 USER root
@@ -75,7 +133,7 @@ COPY --from=build-stage /app/frontend/dist ./server/public
 COPY --chown=anythingllm:anythingllm ./collector/ ./collector/
 
 # Install collector dependencies
-RUN cd /app/collector && yarn install --production && yarn cache clean
+RUN cd /app/collector && yarn install --production --network-timeout 100000 && yarn cache clean
 
 # Migrate and Run Prisma against known schema
 RUN cd ./server && npx prisma generate --schema=./prisma/schema.prisma
@@ -93,4 +151,4 @@ HEALTHCHECK --interval=1m --timeout=10s --start-period=1m \
   CMD /bin/bash /usr/local/bin/docker-healthcheck.sh || exit 1
 
 # Run the server
-ENTRYPOINT ["/bin/bash", "/usr/local/bin/docker-entrypoint.sh"]
+ENTRYPOINT ["/bin/bash", "/usr/local/bin/docker-entrypoint.sh"]
diff --git a/docker/HOW_TO_USE_DOCKER.md b/docker/HOW_TO_USE_DOCKER.md
@@ -29,14 +29,19 @@ Use the Dockerized version of AnythingLLM for a much faster and complete startup
 > It is best to mount the containers storage volume to a folder on your host machine
 > so that you can pull in future updates without deleting your existing data!
 
-`docker pull mintplexlabs/anythingllm:master`
+Pull in the latest image from docker. Supports both `amd64` and `arm64` CPU architectures.
+```shell
+docker pull mintplexlabs/anythingllm
+```
 
 <table>
 <tr>
-<th>Linux/MacOs</th>
-<th>Windows Powershell</th>
+<th colspan="2">Mount the storage locally and run AnythingLLM in Docker</th>
 </tr>
 <tr>
+<td>
+  Linux/MacOs
+</td>
 <td>
 
 ```shell
@@ -48,13 +53,19 @@ docker run -d -p 3001:3001 \
 -v ${STORAGE_LOCATION}:/app/server/storage \
 -v ${STORAGE_LOCATION}/.env:/app/server/.env \
 -e STORAGE_DIR="/app/server/storage" \
-mintplexlabs/anythingllm:master
+mintplexlabs/anythingllm
 ```
 
+</td>
+</tr>
+<tr>
+<td>
+  Windows
 </td>
 <td>
 
 ```powershell
+# Run this in powershell terminal
 $env:STORAGE_LOCATION="$HOME\Documents\anythingllm"; `
 If(!(Test-Path $env:STORAGE_LOCATION)) {New-Item $env:STORAGE_LOCATION -ItemType Directory}; `
 If(!(Test-Path "$env:STORAGE_LOCATION\.env")) {New-Item "$env:STORAGE_LOCATION\.env"}; `
@@ -63,7 +74,7 @@ docker run -d -p 3001:3001 `
 -v "$env:STORAGE_LOCATION`:/app/server/storage" `
 -v "$env:STORAGE_LOCATION\.env:/app/server/.env" `
 -e STORAGE_DIR="/app/server/storage" `
-mintplexlabs/anythingllm:master;
+mintplexlabs/anythingllm;
 ```
 
 </td>

diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml
@@ -1,4 +1,4 @@
-version: '3.9'
+version: "3.9"
 
 name: anythingllm
 
@@ -10,7 +10,6 @@ services:
   anything-llm:
     container_name: anything-llm
     image: anything-llm:latest
-    platform: linux/amd64
     build:
       context: ../.
       dockerfile: ./docker/Dockerfile

diff --git a/server/package.json b/server/package.json
@@ -59,7 +59,7 @@
     "swagger-ui-express": "^5.0.0",
     "uuid": "^9.0.0",
     "uuid-apikey": "^1.5.3",
-    "vectordb": "0.1.12",
+    "vectordb": "0.1.19",
     "weaviate-ts-client": "^1.4.0"
   },
   "devDependencies": {