From 90d7f4472dae028e5eb9dab3cf05f3add4d6142b Mon Sep 17 00:00:00 2001 From: atilgner Date: Fri, 7 Jul 2023 12:39:30 -0700 Subject: [PATCH 1/2] fix: docker should install chromium and puppeteer should be no sandbox --- docker/Dockerfile | 5 +++++ .../nodes/documentloaders/Puppeteer/Puppeteer.ts | 7 ++++++- 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/docker/Dockerfile b/docker/Dockerfile index 2203af11a31..1ad1bf5ee2b 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -6,7 +6,12 @@ RUN apk add --no-cache git RUN apk add --no-cache python3 py3-pip make g++ # needed for pdfjs-dist RUN apk add --no-cache build-base cairo-dev pango-dev + +# Install Chromium +RUN apk add --no-cache chromium + ENV PUPPETEER_SKIP_DOWNLOAD=true +ENV PUPPETEER_EXECUTABLE_PATH=/usr/bin/chromium-browser # You can install a specific version like: flowise@1.0.0 RUN npm install -g flowise diff --git a/packages/components/nodes/documentloaders/Puppeteer/Puppeteer.ts b/packages/components/nodes/documentloaders/Puppeteer/Puppeteer.ts index 1331c736e91..bc1bc9ed628 100644 --- a/packages/components/nodes/documentloaders/Puppeteer/Puppeteer.ts +++ b/packages/components/nodes/documentloaders/Puppeteer/Puppeteer.ts @@ -73,7 +73,12 @@ class Puppeteer_DocumentLoaders implements INode { const puppeteerLoader = async (url: string): Promise => { let docs = [] - const loader = new PuppeteerWebBaseLoader(url) + const loader = new PuppeteerWebBaseLoader(url, { + launchOptions: { + args: ['--no-sandbox'], + headless: 'new' + } + }) if (textSplitter) { docs = await loader.loadAndSplit(textSplitter) } else { From 41346594c60185711e2eb3048e2538b5c44f69e3 Mon Sep 17 00:00:00 2001 From: chungyau97 Date: Sat, 8 Jul 2023 19:01:11 +0800 Subject: [PATCH 2/2] copy paste chrome fix to root docker file --- Dockerfile | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Dockerfile b/Dockerfile index fe01ed8d82d..e485cd3ef35 100644 --- a/Dockerfile +++ b/Dockerfile @@ -8,7 +8,12 @@ FROM node:18-alpine RUN apk add --update libc6-compat python3 make g++ # needed for pdfjs-dist RUN apk add --no-cache build-base cairo-dev pango-dev + +# Install Chromium +RUN apk add --no-cache chromium + ENV PUPPETEER_SKIP_DOWNLOAD=true +ENV PUPPETEER_EXECUTABLE_PATH=/usr/bin/chromium-browser WORKDIR /usr/src/packages