AutomationFlowsAI & RAG › AI Agent Wikipedia Query Workflow

AI Agent Wikipedia Query Workflow

Original n8n title: Ai-agent-wikipedia-n8n/

ai-agent-wikipedia-n8n/. Uses agent, lmChatOllama. Event-driven trigger; 10 nodes.

Event trigger★★★★☆ complexityAI-powered10 nodesAgentOllama Chat
AI & RAG Trigger: Event Nodes: 10 Complexity: ★★★★☆ AI nodes: yes Added:

This workflow follows the Agent → Ollama Chat recipe pattern — see all workflows that pair these two integrations.

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

Download .json
{
  "name": "ai-agent-wikipedia-n8n/",
  "nodes": [
    {
      "parameters": {
        "content": "## Self-coded LLM Chain Node",
        "height": 237,
        "width": 432
      },
      "id": "6f608761-0c12-49ea-b478-a07edbedcb4e",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        0,
        0
      ],
      "typeVersion": 1
    },
    {
      "parameters": {},
      "id": "9f15f6e1-2d3e-4063-89bb-8a3286d87ba5",
      "name": "When clicking \"Execute Workflow\"",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -528,
        96
      ],
      "typeVersion": 1
    },
    {
      "parameters": {
        "values": {
          "string": [
            {
              "name": "input",
              "value": "What is machine learning?"
            }
          ]
        },
        "options": {}
      },
      "id": "06595ee0-854d-4fa6-b606-f752cc24aea3",
      "name": "Set",
      "type": "n8n-nodes-base.set",
      "position": [
        -176,
        96
      ],
      "typeVersion": 2
    },
    {
      "parameters": {
        "values": {
          "string": [
            {
              "name": "input",
              "value": "When was Isaac Newton born?"
            }
          ]
        },
        "options": {}
      },
      "id": "bf9914f9-8256-4040-a2b5-0dfee56ab518",
      "name": "Set1",
      "type": "n8n-nodes-base.set",
      "position": [
        -176,
        480
      ],
      "typeVersion": 2
    },
    {
      "parameters": {
        "content": "## Self-coded Tool Node",
        "height": 231,
        "width": 320.2172923777021
      },
      "id": "29d28deb-2014-4e91-856f-41392f949425",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        80,
        688
      ],
      "typeVersion": 1
    },
    {
      "parameters": {
        "code": {
          "supplyData": {
            "code": "return {\n  name: \"wiki_search\",\n  description: \"Search Wikipedia for a topic\",\n  async call(input) {\n    return `Wikipedia result for: ${input}`;\n  }\n};\n"
          }
        },
        "outputs": {
          "output": [
            {
              "type": "ai_tool"
            }
          ]
        }
      },
      "id": "c757d063-1c9a-48b1-a1c2-97a311893a1b",
      "name": "Custom - Wikipedia",
      "type": "@n8n/n8n-nodes-langchain.code",
      "position": [
        176,
        768
      ],
      "typeVersion": 1
    },
    {
      "parameters": {
        "code": {
          "execute": {
            "code": "const { PromptTemplate } = require('@langchain/core/prompts');\n\nconst query = $input.item.json.input;\n\nconst prompt = PromptTemplate.fromTemplate(query);\n\nconst llm = await this.getInputConnectionData('ai_languageModel', 0);\n\nconst chain = prompt.pipe(llm);\n\nconst output = await chain.invoke({});\n\nreturn [\n  {\n    json: {\n      output: output.content ?? output\n    }\n  }\n];\n"
          }
        },
        "inputs": {
          "input": [
            {
              "type": "main"
            },
            {
              "type": "ai_languageModel",
              "maxConnections": 1,
              "required": true
            }
          ]
        },
        "outputs": {
          "output": [
            {
              "type": "main"
            }
          ]
        }
      },
      "id": "e7d3ce87-90bc-46ec-8b16-07a9be50b4de",
      "name": "Custom - LLM Chain Node",
      "type": "@n8n/n8n-nodes-langchain.code",
      "position": [
        80,
        96
      ],
      "typeVersion": 1
    },
    {
      "parameters": {
        "options": {}
      },
      "id": "320b9116-010a-49c6-a190-05e68bdedf36",
      "name": "Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        80,
        480
      ],
      "typeVersion": 1
    },
    {
      "parameters": {
        "model": "mistral:latest",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOllama",
      "typeVersion": 1,
      "position": [
        112,
        288
      ],
      "id": "9946f478-96d7-4eca-ad1c-d5d7c449a341",
      "name": "Ollama Chat Model",
      "credentials": {
        "ollamaApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "model": "mistral:latest",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOllama",
      "typeVersion": 1,
      "position": [
        -64,
        768
      ],
      "id": "c70ca981-d1a3-4e66-afa9-a45efdea6dab",
      "name": "Ollama Chat Model1",
      "credentials": {
        "ollamaApi": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "Set": {
      "main": [
        [
          {
            "node": "Custom - LLM Chain Node",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Set1": {
      "main": [
        [
          {
            "node": "Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Custom - Wikipedia": {
      "ai_tool": [
        [
          {
            "node": "Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "When clicking \"Execute Workflow\"": {
      "main": [
        [
          {
            "node": "Set",
            "type": "main",
            "index": 0
          },
          {
            "node": "Set1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Ollama Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Custom - LLM Chain Node",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Ollama Chat Model1": {
      "ai_languageModel": [
        [
          {
            "node": "Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1",
    "binaryMode": "separate",
    "availableInMCP": false
  },
  "versionId": "2943333c-d5e5-4561-8b2b-36c18c2f1da4",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "5vega138aMYQLJhaxMEa5",
  "tags": [
    {
      "name": "LangChain - Example",
      "id": "x5Zde9M4RWRMpzup",
      "updatedAt": "2026-02-10T20:59:54.850Z",
      "createdAt": "2026-02-10T20:59:54.850Z"
    }
  ]
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

How this works

This workflow empowers you to query Wikipedia effortlessly through a local AI agent, delivering concise summaries or insights without leaving your automation setup. It's ideal for researchers, content creators, or anyone needing quick factual overviews from reliable sources, saving hours of manual searching. The key step involves the AI agent chaining a custom Wikipedia fetcher with the lmChatOllama model to process and refine the retrieved information into tailored responses.

Use this when you want event-driven, on-demand Wikipedia lookups integrated into broader automations, such as research pipelines or chatbots. Avoid it for high-volume queries that might strain local Ollama resources, or when real-time web access is needed beyond Wikipedia's scope. Common variations include swapping lmChatOllama for other local models or adding output to tools like email for instant notifications.

About this workflow

ai-agent-wikipedia-n8n/. Uses agent, lmChatOllama. Event-driven trigger; 10 nodes.

Source: https://github.com/avarose57/ai-agent-wikipedia-n8n/blob/main/workflow.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.

AI & RAG

This workflow is designed for marketers, content creators, agencies, and solo founders who want to publish long‑form posts with visuals on autopilot using n8n and AI agents. ​

Tool Http Request, Agent, HTTP Request +27
AI & RAG

Description

Agent, Edit Image, HTTP Request +6
AI & RAG

This workflow is an AI-powered voice assistant that transforms natural language voice or text inputs into actionable productivity tasks such as professional emails and calendar events.Built using Whis

Telegram Trigger, Telegram, HTTP Request +6
AI & RAG

My workflow 30. Uses lmChatOpenAi, httpRequest, agent, lmChatOllama. Event-driven trigger; 52 nodes.

OpenAI Chat, HTTP Request, Agent +12
AI & RAG

Episode 14: Seedance + ASMR. Uses lmChatOpenAi, agent, httpRequest, lmChatOllama. Event-driven trigger; 51 nodes.

OpenAI Chat, Agent, HTTP Request +12