Auto-index your website and build a RAG chatbot with Firecrawl, Qdrant, and GPT-4o-mini
UnknownUnknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 22 nodes and runs when a chat message arrives (plus 1 other trigger). Along the way it connects Gmail, Qdrant Vector Store, Embeddings Mistral Cloud and OpenAI Chat Model and 1 more.
How it runs
Trigger: When a chat message arrives (plus 1 other trigger).
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 2 tools (Qdrant Vector Store, Send a message in Gmail); memory: Simple Memory
- set urls to scrape (Code): runs custom JavaScript code
- Loop Over urls (Loop Over Items (Split in Batches)): loops over the items in batches
- Remove Duplicates: removes duplicate items
- Map Site (Firecrawl): map (map search)
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Split Out: splits a list into separate items
- Single Scrape (Firecrawl): scrape
- extract only urls (Edit Fields (Set)): sets 1 field: url
- remove irrelevant params (Edit Fields (Set)): sets 1 field: data.markdown
…plus 2 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that @mendable/n8n-nodes-firecrawl is verified or supports 3.0 (used in Map Site, Single Scrape).
Nodes used (17)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Gmail Tool
n8n-nodes-base.gmailTool - Manual Trigger
n8n-nodes-base.manualTrigger - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Firecrawl
@mendable/n8n-nodes-firecrawl.firecrawl - Remove Duplicates
n8n-nodes-base.removeDuplicates - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Code
n8n-nodes-base.code - Split Out
n8n-nodes-base.splitOut - Edit Fields (Set)
n8n-nodes-base.set - Embeddings Mistral Cloud
@n8n/n8n-nodes-langchain.embeddingsMistralCloud - Wait
n8n-nodes-base.wait - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi
From the author
Build a fully functional AI chatbot for any website using Retrieval-Augmented Generation (RAG). This workflow automatically crawls and indexes your entire site into a Qdrant vector database, then powers a conversational chatbot that searches your content to…