feat: n8n user docs for WCC actor app #1763
Conversation
protoss70
added
the
t-integrations
protoss70
modified the milestones:
120th sprint - Integrations team,
121st sprint - Integrations team
|
Preview for this PR was built for commit |
1 similar comment
|
Preview for this PR was built for commit |
|
Preview for this PR was built for commit |
|
Preview for this PR was built for commit |
|
Preview for this PR was built for commit |
| @@ -0,0 +1,165 @@ | |||
| --- | |||
| title: N8N - AI crawling Actor integration | |||
There was a problem hiding this comment.
Is N8N correct? I think they spell it n8n.
|
Preview for this PR was built for commit |
|
|
||
| ## Apify Scraper for AI Crawling | ||
|
|
||
| Apify Scraper for AI Crawling from [Apify](https://apify.com/) lets you extract text content from websites to feed AI models, LLM applications, vector databases, or Retrieval Augmented Generation (RAG) pipelines. It supports rich formatting using Markdown, cleans the HTML of irrelevant elements, downloads linked files, and integrates with AI ecosystems like LangChain, LlamaIndex, and other LLM frameworks. |
There was a problem hiding this comment.
Shouldn't this be a link to specific Actor, not general link to apify.com?
sources/platform/integrations/workflows-and-notifications/n8n/ai-crawling.md
Outdated
Show resolved
Hide resolved
|
|
||
|  | ||
|
|
||
| Once connected, you can build workflows to automate website extraction and integrate results into your AI applications. |
There was a problem hiding this comment.
This repeats sentence from intro section and seems redundant
| ## Prerequisites | ||
|
|
||
| Before you begin, make sure you have: | ||
|
|
||
| - An [Apify account](https://console.apify.com/) | ||
| - An [n8n instance](https://docs.n8n.io/getting-started/) (self‑hosted or cloud) |
There was a problem hiding this comment.
This section should be below ## Apify Scraper for AI crawling. First we need to introduce the concept, then show what is needed
| ## Install the Apify Node (self-hosted) | ||
|
|
||
| If you're running a self-hosted n8n instance, you can install the Apify community node directly from the editor. This process adds the node to your available tools, enabling Apify operations in workflows. | ||
|
|
||
| 1. Open your n8n instance. | ||
| 1. Go to **Settings > Community Nodes**. | ||
| 1. Select **Install**. | ||
| 1. Enter the npm package name: `@apify/n8n-nodes-apify-content-crawler` (for latest version). To install a specific [version](https://www.npmjs.com/package/@apify/n8n-nodes-apify-content-crawler?activeTab=versions) enter e.g `@apify/[email protected]`. | ||
| 1. Agree to the [risks](https://docs.n8n.io/integrations/community-nodes/risks/) of using community nodes and select **Install**. | ||
| 1. You can now use the node in your workflows. | ||
|
|
||
|  | ||
|
|
||
| ## Connect Apify Scraper for AI Crawling (self-hosted) | ||
|
|
||
| 1. Create an account at [Apify](https://console.apify.com/). You can sign up using your email, Gmail, or GitHub account. | ||
|
|
||
|  | ||
|
|
||
| 1. To connect your Apify account to n8n, you can use an OAuth connection (recommended) or an Apify API token. To get the Apify API token, navigate to **[Settings > API & Integrations](https://console.apify.com/settings/integrations)** in the Apify Console. | ||
|
|
||
|  | ||
|
|
||
| 1. Find your token under **Personal API tokens** section. You can also create a new API token with multiple customizable permissions by clicking on **+ Create a new token**. | ||
| 1. Click the **Copy** icon next to your API token to copy it to your clipboard. Then, return to your n8n workflow interface. | ||
|
|
||
|  | ||
|
|
||
| 1. In n8n, click **Create new credential** of the chosen Apify Scraper module. | ||
| 1. In the **API key** field, paste the API token you copied from Apify and click **Save**. | ||
|
|
||
|  | ||
|
|
||
| Once connected, you can build workflows to automate website extraction and integrate results into your AI applications. |
There was a problem hiding this comment.
We mention that cloud is also an option, shouldn't there be also a brief explanation how to configure it for cloud version?
sources/platform/integrations/workflows-and-notifications/n8n/ai-crawling.md
Outdated
Show resolved
Hide resolved
sources/platform/integrations/workflows-and-notifications/n8n/ai-crawling.md
Outdated
Show resolved
Hide resolved
sources/platform/integrations/workflows-and-notifications/n8n/ai-crawling.md
Outdated
Show resolved
Hide resolved
sources/platform/integrations/workflows-and-notifications/n8n/ai-crawling.md
Outdated
Show resolved
Hide resolved
sources/platform/integrations/workflows-and-notifications/n8n/ai-crawling.md
Outdated
Show resolved
Hide resolved
Co-authored-by: Michał Olender <[email protected]>
🚨 Bugbot Trial ExpiredYour team's Bugbot trial has expired. Please contact your team administrator to turn on the paid plan to continue using Bugbot. A team admin can activate the plan in the Cursor dashboard. |
|
Preview for this PR was built for commit |
Co-authored-by: Michał Olender <[email protected]>
|
Preview for this PR was built for commit |
|
@protoss70 Hi there, thanks for the update and more context, I'll take a look today evening/tomorrow at the latest |
|
Preview for this PR was built for commit |
sources/platform/integrations/workflows-and-notifications/n8n/website-content-crawler.md
Outdated
Show resolved
Hide resolved
sources/platform/integrations/workflows-and-notifications/n8n/website-content-crawler.md
Show resolved
Hide resolved
sources/platform/integrations/workflows-and-notifications/n8n/website-content-crawler.md
Outdated
Show resolved
Hide resolved
sources/platform/integrations/workflows-and-notifications/n8n/website-content-crawler.md
Outdated
Show resolved
Hide resolved
sources/platform/integrations/workflows-and-notifications/n8n/website-content-crawler.md
Outdated
Show resolved
Hide resolved
sources/platform/integrations/workflows-and-notifications/n8n/website-content-crawler.md
Outdated
Show resolved
Hide resolved
…/n8n/website-content-crawler.md Co-authored-by: Michał Olender <[email protected]>
…/n8n/website-content-crawler.md Co-authored-by: Michał Olender <[email protected]>
|
Preview for this PR was built for commit |
|
Preview for this PR was built for commit |
|
Preview for this PR was built for commit |
|
Preview for this PR was built for commit |
|
Preview for this PR was built for commit |
|
Preview for this PR was built for commit |
|
|
||
| ### How it works | ||
|
|
||
| The **Advanced Settings** module provides granular control over the entire crawling process. For _Crawler selection_, you can choose from Playwright (Firefox/Chrome) or Cheerio, depending on the complexity of the target website. _URL management_ allows you to define the crawling scope with include and exclude URL patterns. You can also exercise precise _DOM manipulation_ by controlling which HTML elements to keep or remove. To ensure the best results, you can apply specialized algorithms for _Content transformation_ and select from various _Output formatting_ options for better AI model compatibility. |
There was a problem hiding this comment.
There is no advanced module anymore
|
Preview for this PR was built for commit |
|
|
||
|  | ||
| :::note |
There was a problem hiding this comment.
can we get some clear title that sums up the note to improve scanability? 2/3 words maximum
|
Preview for this PR was built for commit |
|
Preview for this PR was built for commit |
Added docs for the new n8n WCC single actor app I am developing. Most of the text is copy pasted from Make.com ai crawling documentation
Note
Adds comprehensive docs for the n8n Website Content Crawler module and updates image paths/notes in existing n8n integration docs.
sources/platform/integrations/workflows-and-notifications/n8n/website-content-crawler.mdsources/platform/integrations/workflows-and-notifications/n8n/index.md../images/...to../../images/....Written by Cursor Bugbot for commit a8832f2. This will update automatically on new commits. Configure here.