Chat Query Pipeline

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 →

{
  "name": "2. Chat Query Pipeline",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "chat",
        "responseMode": "responseNode",
        "options": {}
      },
      "id": "webhook-chat",
      "name": "Webhook - Chat Query",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 1,
      "position": [
        240,
        300
      ],
      "notes": "Receives chat queries from Next.js frontend"
    },
    {
      "parameters": {
        "values": {
          "string": [
            {
              "name": "question",
              "value": "={{ $json.body.question }}"
            },
            {
              "name": "timestamp",
              "value": "={{ $json.body.timestamp || $now.toISO() }}"
            }
          ]
        }
      },
      "id": "extract-question",
      "name": "Extract Question",
      "type": "n8n-nodes-base.set",
      "typeVersion": 1,
      "position": [
        460,
        300
      ],
      "notes": "Prepares the query for the RAG service"
    },
    {
      "parameters": {
        "url": "=http://host.docker.internal:5001/query",
        "method": "POST",
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "question",
              "value": "={{ $json.question }}"
            }
          ]
        },
        "options": {
          "timeout": 300000
        }
      },
      "id": "call-rag-query",
      "name": "Call RAG Service - Query",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 3,
      "position": [
        680,
        300
      ],
      "notes": "Queries the RAG system for an answer"
    },
    {
      "parameters": {
        "conditions": {
          "string": [
            {
              "value1": "={{ $json.status }}",
              "value2": "success"
            }
          ]
        }
      },
      "id": "check-query-success",
      "name": "Check Query Success",
      "type": "n8n-nodes-base.if",
      "typeVersion": 1,
      "position": [
        900,
        300
      ]
    },
    {
      "parameters": {
        "values": {
          "string": [
            {
              "name": "answer",
              "value": "={{ $json.answer }}"
            },
            {
              "name": "response",
              "value": "={{ $json.answer }}"
            },
            {
              "name": "status",
              "value": "success"
            },
            {
              "name": "timestamp",
              "value": "={{ $now.toISO() }}"
            }
          ],
          "object": [
            {
              "name": "sources",
              "value": "={{ $json.sources }}"
            }
          ]
        }
      },
      "id": "format-success-response",
      "name": "Format Success Response",
      "type": "n8n-nodes-base.set",
      "typeVersion": 1,
      "position": [
        1120,
        200
      ],
      "notes": "Formats the successful response with sources as array"
    },
    {
      "parameters": {
        "values": {
          "string": [
            {
              "name": "answer",
              "value": "Sorry, I couldn't process that query. Please try again."
            },
            {
              "name": "response",
              "value": "Sorry, I couldn't process that query. Please try again."
            },
            {
              "name": "error",
              "value": "={{ $json.answer || 'Unknown error' }}"
            },
            {
              "name": "status",
              "value": "error"
            }
          ],
          "object": [
            {
              "name": "sources",
              "value": "=[]"
            }
          ]
        }
      },
      "id": "format-error-response",
      "name": "Format Error Response",
      "type": "n8n-nodes-base.set",
      "typeVersion": 1,
      "position": [
        1120,
        400
      ],
      "notes": "Handles errors gracefully"
    },
    {
      "parameters": {
        "respondWith": "json"
      },
      "id": "respond-to-frontend",
      "name": "Respond to Frontend",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1,
      "position": [
        1340,
        300
      ],
      "notes": "Sends response back to Next.js - empty body auto-sends $json"
    }
  ],
  "connections": {
    "Webhook - Chat Query": {
      "main": [
        [
          {
            "node": "Extract Question",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Question": {
      "main": [
        [
          {
            "node": "Call RAG Service - Query",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Call RAG Service - Query": {
      "main": [
        [
          {
            "node": "Check Query Success",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check Query Success": {
      "main": [
        [
          {
            "node": "Format Success Response",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Format Error Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format Success Response": {
      "main": [
        [
          {
            "node": "Respond to Frontend",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format Error Response": {
      "main": [
        [
          {
            "node": "Respond to Frontend",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {},
  "versionId": "2",
  "id": "2",
  "tags": []
}

About this workflow

2. Chat Query Pipeline. Uses httpRequest. Webhook trigger; 7 nodes.

Source: https://github.com/omarbakr2020/langraph-docs-ai-agent/blob/e35fb7549f2b00c806fbcb9556b1f94d459396f5/n8n-workflows/2-chat-query.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.