Build an on-premises AI Kaggle competition assistant with Qdrant RAG and Ollama
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 21 nodes and runs on Local File events (add) (plus 1 other trigger). Along the way it connects Qdrant Vector Store, Embeddings Ollama, Ollama Model and Vector Store Question Answer and 1 more.
How it runs
Trigger: On Local File events (add) (plus 1 other trigger).
- Settings (Edit Fields (Set)): sets 2 fields: path, filename
- AI Agent: runs an AI agent, with model: Ollama Chat Model; 1 tool (Vector Store Tool); memory: Window Buffer Memory
- Import File (Read/Write Files from Disk): reads a file from disk
- Get FileType (Switch): routes items into 1 branches
- Extract from TEXT (Extract from File): extracts data from a file (text)
- Markdown: converts between Markdown and HTML
- Summarization Chain: summarizes text with AI, with model: Ollama Summarizer
- Merge: merges the data from its input branches
- Qdrant Vector Store: stores documents in the Qdrant vector store, with embeddings: Embeddings Ollama; document loader: Default Data Loader
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (18)
- Local File Trigger
n8n-nodes-base.localFileTrigger - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Edit Fields (Set)
n8n-nodes-base.set - Merge
n8n-nodes-base.merge - Switch
n8n-nodes-base.switch - Read/Write Files from Disk
n8n-nodes-base.readWriteFile - Extract from File
n8n-nodes-base.extractFromFile - Summarization Chain
@n8n/n8n-nodes-langchain.chainSummarization - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Markdown
n8n-nodes-base.markdown - Embeddings Ollama
@n8n/n8n-nodes-langchain.embeddingsOllama - Ollama Model
@n8n/n8n-nodes-langchain.lmOllama - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Ollama Chat Model
@n8n/n8n-nodes-langchain.lmChatOllama
From the author
LLM/RAG Kaggle Development Assistant An on-premises, domain-specific AI assistant for Kaggle (tested on binary disaster-tweet classification), combining LLM, an n8n workflow engine, and Qdrant-backed Retrieval-Augmented Generation (RAG). Deploy via…