
Auto-index your website and build a RAG chatbot with Firecrawl, Qdrant, and GPT-4o-mini
Use for free
Workflow Automation - n8n
When chat message received
Workflow Config:
Open the “set urls to scrape” Code node
Replace the placeholder URLs with your own site’s root domains
Run the indexing pipeline manually
Why It Was Built This Way
Map then scrape, not crawl
Two separate loops
Wait node: This pause exists to protect you from API rate limits.
Same embedding model in both pipelines: It's critical for indexing and retrieval.
Setup Checklist
Add required credentials in n8n Settings > Credentials
Create a Qdrant Cloud collection
Update the collection name in both Qdrant Vector Store nodes
Open the 'set urls to scrape' Code node
What You Can Tweak
Swap the chat model
Change the embedding model
Add more URLs
Adjust chunk size
How to use
Complete every item below before running anything.
Add your root domains here before running.
Update the Gmail tool with your support inbox address
Conclusion
This workflow allows you to automatically crawl and index your website into a Qdrant database, powering a chatbot that answers user questions and escalates unresolved issues to your support team via Gmail.
Related Integrations:
Firecrawl
Mistral Cloud
Qdrant Cloud
OpenAI
Gmail OAuth2
0 likes · 0 views · May 14, 2026
Developed a chatbot that indexes websites and escalates queries through Gmail.