From sitemap crawling to vector storage: Creating an efficient workflow for RAG

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Best for

Market Research automation workflows
AI RAG automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.manualtrigger, n8n-nodes-base.httprequest, n8n-nodes-base.xml, n8n-nodes-base.splitout, n8n-nodes-base.splitinbatches, n8n-nodes-base.wait, n8n-nodes-base.if, @n8n/n8n-nodes-langchain.documentdefaultdataloader

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Mariela Slavenova.

Original n8n.io source

1.1 Workflow description

Title: From sitemap crawling to vector storage: Creating an efficient workflow for RAG
Workflow name: From sitemap crawling to vector storage: Creating an efficient workflow for RAG

This template crawls a website from its sitemap, deduplicates URLs in Supabase, scrapes pages with Crawl4AI, cleans and validates the text, then stores content + metadata in a Supabase vector store using OpenAI embeddings. It’s a reliable, repeatable pipeline for building searchable knowledge bases, SEO research corpora, and RAG datasets. ⸻

Good to know

•	Built-in de-duplication via a scrape_queue table (status: pending/completed/error).
•	Resilient flow: waits, retries, and marks failed tasks.
•	Costs depend on Crawl4AI usage and OpenAI embeddings.
•	Replace any placeholders (API keys, tokens, URLs) before running.
•	Respect website robots/ToS and applicable data laws when scraping.

How it works

1.	Sitemap fetch & parse — Load sitemap.xml, extract all URLs.
2.	De-dupe — Normalize URLs, check Supabase scrape_queue; insert only new ones.
3.	Scrape — Send URLs to Crawl4AI; poll task status until completed.
4.	Clean & score — Remove boilerplate/markup, detect content type, compute quality metrics, extract metadata (title, domain, language, length).
5.	Chunk & embed — Split text, create OpenAI embeddings.
6.	Store — Upsert into Supabase vector store (documents) with metadata; update job status.

Requirements

•	Supabase (Postgres + Vector extension enabled)
•	Crawl4AI API key (or header auth)
•	OpenAI API key (for embeddings)
•	n8n credentials set for HTTP, Postgres/Supabase

How to use

1.	Configure credentials (Supabase/Postgres, Crawl4AI, OpenAI).
2.	(Optional) Run the provided SQL to create scrape_queue and documents.
3.	Set your sitemap URL in the HTTP Request node.
4.	Execute the workflow (manual trigger) and monitor Supabase statuses.
5.	Query your documents table or vector store from your app/RAG stack.

Potential Use Cases

This automation is ideal for:

Market research teams collecting competitive data
Content creators monitoring web trends
SEO specialists tracking website content updates
Analysts gathering structured data for insights
Anyone needing reliable, structured web content for analysis

Need help customizing?

Contact me for consulting and support: LinkedIn

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - When clicking ‘Test workflow’

Type / Role: n8n-nodes-base.manualTrigger - manualTrigger
Config choices: Version 1

Block 2 - HTTP Request

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 3 - XML

Type / Role: n8n-nodes-base.xml - xml
Config choices: Version 1

Block 4 - Split Out

Type / Role: n8n-nodes-base.splitOut - splitOut
Config choices: Version 1

Block 5 - Loop Over Items

Type / Role: n8n-nodes-base.splitInBatches - splitInBatches
Config choices: Version 3

Block 6 - Wait

Type / Role: n8n-nodes-base.wait - wait
Config choices: Version 1.1

Block 7 - If

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 8 - Default Data Loader

Type / Role: @n8n/n8n-nodes-langchain.documentDefaultDataLoader - documentDefaultDataLoader
Config choices: Version 1

Block 9 - Character Text Splitter

Type / Role: @n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter - textSplitterCharacterTextSplitter
Config choices: Version 1

Block 10 - Embeddings OpenAI

Type / Role: @n8n/n8n-nodes-langchain.embeddingsOpenAi - embeddingsOpenAi
Config choices: Version 1.1

Block 11 - Edit Fields

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 12 - Crawl4AI_Task Status

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 13 - Loop Over Items1

Type / Role: n8n-nodes-base.splitInBatches - splitInBatches
Config choices: Version 3

Block 14 - If2

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 15 - Split Out1

Type / Role: n8n-nodes-base.splitOut - splitOut
Config choices: Version 1

Block 16 - Format the URL

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 17 - Check if the URL is in the Supabase Table

Type / Role: n8n-nodes-base.supabase - supabase
Config choices: Version 1

Block 18 - Format the Output from the Supabase node

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 19 - If "shouldInsert" is true

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 20 - URL in a new row

Type / Role: n8n-nodes-base.supabase - supabase
Config choices: Version 1

Block 21 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 22 - CREATE TABLE scrape_queue in Supabase

Type / Role: n8n-nodes-base.postgres - postgres
Config choices: Version 2.6

Block 23 - CREATE TABLE scrape_queue in Supabase1

Type / Role: n8n-nodes-base.postgres - postgres
Config choices: Version 2.6

Block 24 - Sticky Note2

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Showing the first 24 of 40 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow	From sitemap crawling to vector storage: Creating an efficient workflow for RAG
Complexity	advanced
Nodes	40
Categories	Market Research, AI RAG
Author	Mariela Slavenova
Published	18 Sept 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/8707/8707.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Market Research workflows AI RAG workflows

Frequently asked questions

What does From sitemap crawling to vector storage: Creating an efficient workflow for RAG do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Market Research, AI RAG use case.

Mariela Slavenova

3 workflows

Nodes

n8n-nodes-base.manualtrigger n8n-nodes-base.httprequest n8n-nodes-base.xml n8n-nodes-base.splitout n8n-nodes-base.splitinbatches n8n-nodes-base.wait n8n-nodes-base.if @n8n/n8n-nodes-langchain.documentdefaultdataloader

Complexity

advanced

Published 18 Sept 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/8707/8707.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Answer BigQuery questions in Microsoft Teams with Claude 3.5 dual agents

## Quick overview Turn Microsoft Teams into a natural language BI tool. This dual-agent Claude workflow intelligently classifies user questions, generates safe BigQuery SQL, executes the query, and returns a plain-English summary alongside a data preview directly to your Teams channel. ## How it works 1. The workflow listens for new messages in a designated Microsoft Teams channel or chat. 2. It checks a 24-hour static data cache for your BigQuery schema. If the cache is missing or expired, it automatically fetches the latest INFORMATION_SCHEMA metadata. 3. A main Claude 3.5 Sonnet agent classifies the user's intent (analytical, conversational, or unsafe) and identifies the relevant database tables. 4. If the intent is analytical, a specialized Claude SQL sub-agent generates a read-only SELECT query tailored exactly to your schema. 5. The workflow executes the query against BigQuery (safely constrained to a maximum of 100 rows). 6. A final Claude agent translates the raw query results into a concise, plain-English summary. 7. The answer is posted back to Teams as an Adaptive Card, complete with a formatted data preview and the generated SQL code. 8. Non-analytical questions or pipeline errors are intelligently routed to receive standard conversational replies in Teams. ## Setup 1. CRITICAL SECURITY: Restrict your Google Cloud Service Account IAM roles to BigQuery Data Viewer and BigQuery Job User ONLY. Do not use a highly privileged account. 2. Configure your Microsoft Teams trigger and posting credentials, specifying the target team and channel for the bot to operate in. 3. Configure your Google BigQuery credentials to allow reading metadata and executing queries. 4. Configure your Anthropic credentials for the three Claude LangChain nodes. 5. Update the "Configure Variables" node with your specific GCP Project ID and BigQuery Dataset ID. ## Requirements - A Google Cloud project with BigQuery enabled and existing structured datasets. - An Anthropic API key with access to the Claude 3.5 Sonnet model. - Microsoft Teams administrator access to authorize the n8n integration. ## Customization - Distributed Environments: If you are running n8n with multiple worker nodes (Queue Mode), you must swap the $getWorkflowStaticData() schema cache logic to read/write from a dedicated Key-Value store (like Redis or Supabase) to ensure state synchronization. - UI Layout: Modify the Create Teams Adaptive Card node to add corporate branding, custom colors, or alter the FactSet data preview structure. ## Additional info This architecture features built-in pipeline protections, including strict 40,000-character payload limits to prevent LLM context window blowouts, and fallback handling for "zero-row" query results to ensure users are never left without a response.

View

Evaluate LinkedIn profiles with Apify and Groq Llama chat model

## Quick overview This workflow collects a LinkedIn profile URL via an n8n form, scrapes the public profile data using the Apify LinkedIn Profile Scraper actor, analyzes the results with a Groq-hosted Llama model, and displays an HTML-formatted evaluation back to the user. ## How it works 1. Receives a LinkedIn Profile URL when a user submits the n8n form. 2. Prepares the LinkedIn URL along with the Apify API token and Groq API key used for downstream requests. 3. Sends the profile URL to the Apify `harvestapi/linkedin-profile-scraper` actor and retrieves the scraped dataset items. 4. Passes the scraped profile JSON to a Groq chat model via an LLM chain to generate an HTML evaluation with a score and recommendations. 5. Displays the generated HTML evaluation to the user as the form completion message. ## Setup 1. Add a valid Apify API token and ensure the Apify actor endpoint (`harvestapi/linkedin-profile-scraper`) is accessible for your account. 2. Add Groq API credentials in n8n and confirm the selected model (meta-llama/llama-4-scout-17b-16e-instruct) is available to your Groq account. 3. Replace the placeholder API key values in the workflow (or move them to n8n credentials/environment variables) and verify the form field label matches `LinkedIn Profile URL`.

View

Validate startup ideas with Google Gemini, Groq, and Gmail

## Quick overview This workflow collects a startup idea via an n8n form, uses Google Gemini to generate a SWOT-style analysis, assigns a viability score, uses Groq to turn the results into a structured validation report, and emails the final report through Gmail. ## How it works 1. Receives a startup idea, industry, and target audience from an n8n Form trigger. 2. Sends the submission to Google Gemini to generate a professional analysis covering the problem, business model, and SWOT factors. 3. Generates a startup viability score (currently a random value from 80–100) and packages it with the Gemini analysis. 4. Sends the score and analysis to Groq (Llama 3.3 70B) to compile a full validation report with an executive summary, market potential, recommendations, and final verdict. 5. Emails the generated validation report to the configured recipient using Gmail. ## Setup 1. Add credentials for Google Gemini (PaLM) API, Groq API, and a Gmail OAuth2 connection. 2. Replace the placeholder recipient address in the Gmail step ("[email protected]") with your target email address before activating the workflow. 3. Publish the n8n form, then share the form URL with the users who should submit their startup ideas for validation.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

From sitemap crawling to vector storage: Creating an efficient workflow for RAG

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

Good to know

How it works

Requirements

How to use

Potential Use Cases

Need help customizing?

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - When clicking ‘Test workflow’

Block 2 - HTTP Request

Block 3 - XML

Block 4 - Split Out

Block 5 - Loop Over Items

Block 6 - Wait

Block 7 - If

Block 8 - Default Data Loader

Block 9 - Character Text Splitter

Block 10 - Embeddings OpenAI

Block 11 - Edit Fields

Block 12 - Crawl4AI_Task Status

Block 13 - Loop Over Items1

Block 14 - If2

Block 15 - Split Out1

Block 16 - Format the URL

Block 17 - Check if the URL is in the Supabase Table

Block 18 - Format the Output from the Supabase node

Block 19 - If "shouldInsert" is true

Block 20 - URL in a new row

Block 21 - Sticky Note1

Block 22 - CREATE TABLE scrape_queue in Supabase

Block 23 - CREATE TABLE scrape_queue in Supabase1

Block 24 - Sticky Note2

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions