Basic RAG chat
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 12 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Embeddings Cohere and Groq Chat Model.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Read/Write Files from Disk: reads a file from disk
- Question and Answer Chain: answers questions over your documents (RAG), with model: Groq Chat Model; retriever: Vector Store Retriever
- In-Memory Vector Store (Simple Vector Store): stores documents in the Simple vector store, with embeddings: Embeddings Cohere; document loader: Default Data Loader
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (10)
- Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Question and Answer Chain
@n8n/n8n-nodes-langchain.chainRetrievalQa - Vector Store Retriever
@n8n/n8n-nodes-langchain.retrieverVectorStore - Manual Trigger
n8n-nodes-base.manualTrigger - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Read/Write Files from Disk
n8n-nodes-base.readWriteFile - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Embeddings Cohere
@n8n/n8n-nodes-langchain.embeddingsCohere - Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq
From the author
This workflow demonstrates a simple Retrieval-Augmented Generation (RAG) pipeline in n8n, split into two main sections: 🔹 Part 1: Load Data into Vector Store Reads files from disk (or Google Drive). Splits content into manageable chunks using a recursive…