Ai agent with Ollama for current weather and wiki
Needs changesWhat this workflow does
This AI workflow has 6 nodes and runs on Manual Chat events. Along the way it connects Wikipedia, HTTP Request and Ollama Chat Model. It also calls api.open-meteo.com over HTTP.
How it runs
Trigger: On Manual Chat events.
- AI Agent: runs an AI agent, with model: Ollama Chat Model; 2 tools (Wikipedia, Weather HTTP Request); memory: Window Buffer Memory
Services it uses
HTTP calls to: api.open-meteo.com
Before you upgrade to n8n 3.0
3 things in this workflow are removed in n8n 3.0. Fix them before you upgrade:
- Manual Chat Trigger in On new manual Chat Message: replace with Chat Trigger.
- AI Agent v1 (old agent modes) in AI Agent (v1.6): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
- HTTP Request Tool (legacy) in Weather HTTP Request: replace with HTTP Request node connected to the AI Agent's Tool input.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| Manual Chat Trigger On new manual Chat Message | Chat Trigger |
| AI Agent v1 (old agent modes) AI Agent (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
| HTTP Request Tool (legacy) Weather HTTP Request | HTTP Request node connected to the AI Agent's Tool input |
Nodes used (6)
- Manual Chat Trigger
@n8n/n8n-nodes-langchain.manualChatTrigger - Wikipedia
@n8n/n8n-nodes-langchain.toolWikipedia - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - AI Agent
@n8n/n8n-nodes-langchain.agent - HTTP Request Tool
@n8n/n8n-nodes-langchain.toolHttpRequest - Ollama Chat Model
@n8n/n8n-nodes-langchain.lmChatOllama
From the author
This workflow template demonstrates how to create an AI-powered agent that provides users with current weather information and Wikipedia summaries. By integrating n8n with Ollama's local Large Language Models (LLMs), this template offers a seamless and…