AutomationFlowsAI & RAG › AI Chatbot with Web Search

AI Chatbot with Web Search

Original n8n title: AI Chatbot That Can Search the Web

Ai Chatbot That Can Search The Web. Uses stickyNote, manualChatTrigger, lmChatOpenAi, toolWikipedia. Chat trigger; 9 nodes.

Chat trigger trigger★★★☆☆ complexityAI-powered9 nodesManual Chat TriggerOpenAI ChatTool WikipediaMemory Buffer WindowTool Serp ApiAgent
AI & RAG Trigger: Chat trigger Nodes: 9 Complexity: ★★★☆☆ AI nodes: yes Added:

This workflow follows the Agent → OpenAI 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
{
  "nodes": [
    {
      "id": "3a3bcb2d-cb94-40d8-8b9e-322ea9d27f6e",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1000,
        640
      ],
      "parameters": {
        "width": 300,
        "height": 185,
        "content": "### The conversation history(last 20 messages) is stored in a buffer memory"
      },
      "typeVersion": 1
    },
    {
      "id": "e279af43-b003-4499-b221-58716e735379",
      "name": "On new manual Chat Message",
      "type": "@n8n/n8n-nodes-langchain.manualChatTrigger",
      "position": [
        740,
        340
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "f4f8bf03-a43e-4a1f-a592-cd0f8408f552",
      "name": "Chat OpenAI",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        840,
        653
      ],
      "parameters": {
        "model": "gpt-4o-mini",
        "options": {
          "temperature": 0.3
        }
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "66b60f68-bae8-4958-ac81-03883f563ab3",
      "name": "Wikipedia",
      "type": "@n8n/n8n-nodes-langchain.toolWikipedia",
      "position": [
        1480,
        693
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "70f6b43b-9290-4fbc-992f-0895d4578c9f",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1340,
        633
      ],
      "parameters": {
        "width": 300,
        "height": 185,
        "content": "### Tools which agent can use to accomplish the task"
      },
      "typeVersion": 1
    },
    {
      "id": "8696269f-6556-41f1-bbe4-5597e4e46e02",
      "name": "Sticky Note6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        960,
        260
      ],
      "parameters": {
        "width": 422,
        "height": 211,
        "content": "### Conversational agent will utilise available tools to answer the prompt. "
      },
      "typeVersion": 1
    },
    {
      "id": "6814967b-4567-4cdd-bf09-6b1b5ed0c68e",
      "name": "Window Buffer Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        1100,
        700
      ],
      "parameters": {
        "contextWindowLength": 20
      },
      "typeVersion": 1
    },
    {
      "id": "ce4358ac-c2cc-45ba-b950-247f8360b36c",
      "name": "SerpAPI",
      "type": "@n8n/n8n-nodes-langchain.toolSerpApi",
      "position": [
        1380,
        693
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1
    },
    {
      "id": "de80add8-c37d-4d46-80ec-b43234e21150",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        1040,
        340
      ],
      "parameters": {
        "text": "={{ $json.input }}",
        "options": {},
        "promptType": "define"
      },
      "typeVersion": 1.6
    }
  ],
  "connections": {
    "SerpAPI": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Wikipedia": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Chat OpenAI": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Window Buffer Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "On new manual Chat Message": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

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

About this workflow

Ai Chatbot That Can Search The Web. Uses stickyNote, manualChatTrigger, lmChatOpenAi, toolWikipedia. Chat trigger; 9 nodes.

Source: https://github.com/Zie619/n8n-workflows — 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

✨ Intro This workflow shows how to go beyond a “plain” AI chatbot by:

Telegram, OpenAI, OpenAI Chat +13
AI & RAG

Stickynote. Uses stickyNote, chatTrigger, lmChatOpenAi, memoryBufferWindow. Chat trigger; 9 nodes.

Chat Trigger, OpenAI Chat, Memory Buffer Window +3
AI & RAG

This workflow is designed for dynamic and intelligent conversational capabilities. It incorporates OpenAI's GPT-4o model for natural language understanding and generation. Additional tools include Ser

Chat Trigger, OpenAI Chat, Memory Buffer Window +3
AI & RAG

Use cases are many: This is perfect for researchers needing instant, up-to-date data; support teams providing live, accurate answers; content creators looking to verify facts or find hot topics; and a

Manual Chat Trigger, OpenAI Chat, Memory Buffer Window +3
AI & RAG

This workflow automates end-to-end curriculum planning using a multi-agent AI architecture in n8n. Designed for educators, instructional designers, and academic institutions, it eliminates the manual

Agent, OpenAI Chat, Memory Buffer Window +8