Textai

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": "TextAi",
  "nodes": [
    {
      "parameters": {
        "promptType": "define",
        "text": "={{ $json.content }}",
        "options": {
          "systemMessage": "={{ $json.systemMessage }}"
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 2.2,
      "position": [
        1056,
        -400
      ],
      "id": "a973c7f2-7c33-414c-bd63-43994fd337cd",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "modelName": "models/gemini-2.5-flash-lite",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "typeVersion": 1,
      "position": [
        1056,
        -240
      ],
      "id": "1f9886b4-90f7-4dff-997c-4eb5a450dbab",
      "name": "Google Gemini Chat Model",
      "credentials": {
        "googlePalmApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "const rawText = $input.first().json.output;;\n\n// 2. Use a regular expression to find the JSON content.\n// This regex looks for either:\n//   - Content inside a ```json ... ``` block (match[1])\n//   - A raw object starting with { and ending with } (match[2])\nconst match = rawText.match(/```json\\s*([\\s\\S]*?)\\s*```|({[\\s\\S]*})/);\n\n// 3. Get the actual JSON string (whichever part matched).\n// We prioritize the markdown-wrapped content (match[1]) if it exists.\nconst jsonString = match[1] || match[2];\n\n// 4. Check if we actually found any JSON.\nif (!jsonString) {\n  throw new Error(\"Could not find any JSON content in the AI output.\");\n}\n\n// 5. Parse the *clean* JSON string.\nconst parsedJson = JSON.parse(jsonString);\n\n// 6. Return the data, nested under an 'output' field\n// so you can access it as $json.output.content\nreturn [{ json: { output: parsedJson } }];"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1408,
        -400
      ],
      "id": "a3e5b58f-8419-43e3-8044-647c62f4d3dc",
      "name": "Code in JavaScript"
    },
    {
      "parameters": {
        "workflowInputs": {
          "values": [
            {
              "name": "content",
              "type": "any"
            },
            {
              "name": "systemMessage",
              "type": "any"
            }
          ]
        }
      },
      "id": "cba18b13-6b12-4cde-bef9-eac7fe75a650",
      "typeVersion": 1.1,
      "name": "Start",
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "position": [
        832,
        -400
      ]
    }
  ],
  "connections": {
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "AI Agent": {
      "main": [
        [
          {
            "node": "Code in JavaScript",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Start": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "c760ea88-74e2-429c-b673-39643d2c8905",
  "id": "w3q9u9lBl8416dkl",
  "tags": []
}

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.

• googlePalmApi

About this workflow

TextAi. Uses agent, lmChatGoogleGemini, executeWorkflowTrigger. Event-driven trigger; 4 nodes.

Source: https://github.com/memo1918/ImageToAnki-n8nAutomation/blob/428dd50a0c9778efd26a1c3b09b474731da403fa/workflows/TextAi.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.