Automate Your Knowledge Base with n8n and Gemini
detail.loadingPreview
Streamline the ingestion and processing of your documentation into a knowledge base. This workflow leverages n8n's automation capabilities and Google's Gemini 2.5 Flash to clean, split, and prepare your content for intelligent use.
About This Workflow
This n8n workflow automates the process of ingesting and preparing documentation for AI-powered applications. It begins by fetching all links from the n8n documentation website and then filters these to only include relevant paths. The workflow cleans the fetched documentation content, removing unnecessary formatting and extraneous information. Subsequently, it splits the clean text into manageable chunks using a recursive character splitter, with configurable chunk sizes and overlap. Duplicate content is identified and removed at both the link and documentation stages, ensuring data integrity. Finally, the processed documentation is prepared for ingestion into a vector store, likely for use with a large language model like Gemini 2.5 Flash, to build a powerful and searchable knowledge base.
Key Features
- Automated Documentation Ingestion: Scans and extracts links from a specified website.
- Intelligent Content Cleaning: Removes extraneous characters and formatting to ensure data purity.
- Advanced Text Splitting: Utilizes recursive character splitting for optimal chunking of documentation.
- Duplicate Content Removal: Ensures the integrity of your knowledge base by eliminating redundant information.
- AI-Ready Data Preparation: Formats content for seamless integration with Large Language Models like Gemini.
How To Use
- Fetch Documentation Links: Configure the
Get All n8n Documentation Linksnode with the URL of the website you want to process. - Extract Links: The
Extract Links from HTMLnode will automatically parse the HTML to find all<a>tags and extract theirhrefattributes. - Process Links: Use the
Split Out Linksnode to separate individual links and theRemove Duplicate Linksnode to ensure uniqueness. - Filter Relevant Paths: Configure the
Only Keep Doc Pathsnode with conditions to filter links, for example, ensuring they end with '/' and do not start with 'https://'. - Clean Documentation Content: The
Clean Documentationnode uses a JavaScript expression to clean the fetched content. Adjust the regex as needed for your specific documentation format. - Remove Duplicate Content: The
Remove Duplicate Documentation Contentnode identifies and removes duplicate text entries based on previous executions. - Load and Split Data: The
Default Data Loadernode takes the cleaned documentation, and theRecursive Character Text Splitternode breaks it down into smaller, manageable chunks. AdjustchunkSizeandchunkOverlapto suit your needs. - Integrate with AI: Connect the
Gemini 2.5 Flashnode to process the prepared documentation chunks. TheSimple Memorynode can be used to maintain conversation context. TheAdd Documentation Page to Vector Storenode is designed to ingest this processed data into a vector store for AI querying.
Apps Used
Workflow JSON
{
"id": "4a87a094-efe1-49fd-ae38-33e2fa97228e",
"name": "Automate Your Knowledge Base with n8n and Gemini",
"nodes": 14,
"category": "DevOps",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 4a87a094-efe1...
About the Author
Free n8n Workflows Official
System Admin
The official repository for verified enterprise-grade workflows.
Statistics
Related Workflows
Discover more workflows you might like
Automated PR Merged QA Notifications
Streamline your QA process with this automated workflow that notifies your team upon successful Pull Request merges. Leverage AI and vector stores to enrich notifications and ensure seamless integration into your development pipeline.
Automate Qualys Report Generation and Retrieval
Streamline your Qualys security reporting by automating the generation and retrieval of reports. This workflow ensures timely access to crucial security data without manual intervention.
Visualize Your n8n Workflows: Interactive Dashboard with Mermaid.js
Gain unparalleled visibility into your n8n automation landscape. This workflow transforms your n8n instance into a dynamic, interactive dashboard, leveraging Mermaid.js to visualize all your workflows in one accessible place.