AcademyWorkflowsData and reporting

Local Chatbot with Retrieval Augmented Generation (RAG)

Teams that want to ask questions about their own PDF documents while keeping the models running on their own machines.

  • Recommendedour rating
  • 28,717views on n8n
Open on n8n.io ↗

Paste it straight onto an n8n canvas with Ctrl+V or Cmd+V.

local-chatbot-with-retrieval-augmented-generation-rag.json

Loading the file...

What it does

An n8n workflow template that builds a chatbot answering questions from PDF files you upload. Documents are split and stored in a Qdrant vector database, and the agent retrieves the relevant chunks, using Ollama models, to answer.

Use cases

  1. 01Ask questions about uploaded contracts or reports
  2. 02Search a set of internal PDF manuals
  3. 03Test a document chatbot on local infrastructure

Connects

AI Agent · Ollama Chat Model · Simple Memory · Recursive Character Text Splitter · Default Data Loader · Qdrant Vector Store · Embeddings Ollama

Questions about
Local Chatbot with Retrieval Augmented Generation (RAG).

What is Local Chatbot with Retrieval Augmented Generation (RAG) used for?

Teams that want to ask questions about their own PDF documents while keeping the models running on their own machines. An n8n workflow template that builds a chatbot answering questions from PDF files you upload. Documents are split and stored in a Qdrant vector database, and the agent retrieves the relevant chunks, using Ollama models, to answer.

How do I import Local Chatbot with Retrieval Augmented Generation (RAG) into n8n?

Copy the workflow JSON from this page and paste it onto the n8n canvas with Ctrl+V or Cmd+V. Then connect your credentials in each node.

Is Local Chatbot with Retrieval Augmented Generation (RAG) safe to use?

It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.