This workflow follows the Agent → Chainllm 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 →
{
"id": "bPxDenPJ5Ixx0txY",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Line_Chatbot_Extract_Text_from_Pay_Slip_with_Gemini",
"tags": [],
"nodes": [
{
"id": "83f758b4-a80b-4f27-ac13-ee0958ed97f2",
"name": "Window Buffer Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
200,
320
],
"parameters": {
"sessionKey": "={{ $json.body.events[0].source.userId }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "c41976eb-4a35-4c59-8167-538c651ad7e5",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-200,
520
],
"parameters": {
"width": 620,
"height": 500,
"content": "## Extract text from image\n**Prompt for Gemini**\nAnalyze image and then return in JSON Response that has the only following value: Status, From, To, Date, Amount"
},
"typeVersion": 1
},
{
"id": "c3eb2420-a503-4039-874c-df3c2799c561",
"name": "Line: Get Image",
"type": "n8n-nodes-base.httpRequest",
"position": [
-160,
660
],
"parameters": {
"url": "=https://api-data.line.me/v2/bot/message/{{ $json.body.events[0].message.id }}/content ",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "e39e5392-b287-4efe-a9a9-1f241e82cd92",
"name": "Message Type",
"type": "n8n-nodes-base.set",
"position": [
-620,
400
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "e9deec19-c171-4af5-bfb7-f0917ba658c5",
"name": "body.events[0].message.text",
"type": "string",
"value": "={{ $json.body.events[0].message.text }}"
},
{
"id": "ae9ee257-494f-4c65-a39d-4dc3505f2c01",
"name": "body.events[0].message.id",
"type": "string",
"value": "={{ $json.body.events[0].message.id }}"
},
{
"id": "5e3dfc31-ed6e-4899-880d-ce73076e0cfd",
"name": "body.events[0].source.userId",
"type": "string",
"value": "={{ $json.body.events[0].source.userId }}"
},
{
"id": "8918e8d3-2a30-40df-b452-c07f340972cf",
"name": "body.events[0].message.type",
"type": "string",
"value": "={{ $json.body.events[0].message.type }}"
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "a166e880-9291-4794-a6be-47f0a86e77e7",
"name": "Message Classification",
"type": "n8n-nodes-base.switch",
"position": [
-420,
400
],
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "7f862599-1eb2-4f76-910f-6caae33ea292",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Line: Messaging API').item.json.body.events[0].message.type }}",
"rightValue": "text"
}
]
}
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "0b661fab-e556-45ee-b845-67aff27fd862",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Line: Messaging API').item.json.body.events[0].message.type }}",
"rightValue": "image"
}
]
}
},
{
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "550e6e18-6b3e-4b08-8344-12bc76a1f736",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Line: Messaging API').item.json.body.events[0].message.stickerId }}",
"rightValue": "=150"
}
]
}
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "d7c29939-dd8e-43e9-89f2-879dc8ea318c",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
0
],
"parameters": {
"width": 420,
"height": 460,
"content": "## Gemini AI Assistant\n\nAI Assistant using Gemini 2.0 Flash Experiment unlocks new possibilities for AI agents - intelligent systems that can use memory, reasoning, and planning to complete tasks for you."
},
"typeVersion": 1
},
{
"id": "0df36c5d-ec2a-492d-b688-4bad8d81cf38",
"name": "Text Message Processing",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
100,
140
],
"parameters": {
"text": "=This is the message from User: {{ $json.body.events[0].message.text }}",
"agent": "conversationalAgent",
"options": {},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "dfafa5ba-a855-4ebf-a19d-2addb556e791",
"name": "Image Message Processing",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
100,
660
],
"parameters": {
"text": "Analyze image and then return in JSON Response that has the only following Value:\nStatus, From, To, Date, Amount",
"messages": {
"messageValues": [
{
"message": "You are the image analyzer. You can analyze image and extract the important information from image."
},
{
"type": "HumanMessagePromptTemplate",
"messageType": "imageBinary"
}
]
},
"promptType": "define"
},
"typeVersion": 1.5
},
{
"id": "b9a309bf-2c49-40e1-a0e4-9cced43d6e85",
"name": "Line: Response to User",
"type": "n8n-nodes-base.httpRequest",
"position": [
580,
660
],
"parameters": {
"url": "https://api.line.me/v2/bot/message/reply",
"method": "POST",
"options": {},
"jsonBody": "={\n \"replyToken\":\"{{ $('Line: Messaging API').item.json.body.events[0].replyToken }}\",\n \"messages\":[\n {\n \"type\":\"text\",\n \"text\": {{ JSON.stringify($json.text.replace(/^```(?:json|markdown)?\\n?/, \"\").replace(/\\n?```$/, \"\")) }}\n }\n ]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "ff5561fa-b334-4639-a513-554ee3507ab0",
"name": "Line: Text Response to User",
"type": "n8n-nodes-base.httpRequest",
"position": [
580,
140
],
"parameters": {
"url": "https://api.line.me/v2/bot/message/reply",
"method": "POST",
"options": {},
"jsonBody": "={\n \"replyToken\":\"{{ $('Line: Messaging API').item.json.body.events[0].replyToken }}\",\n \"messages\":[\n {\n \"type\":\"text\",\n \"text\": {{ JSON.stringify($json.output) }}\n }\n ]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "850f1079-cecf-4680-835f-34af829ee8f5",
"name": "Text from Slip Result",
"type": "n8n-nodes-base.googleSheets",
"position": [
1020,
660
],
"parameters": {
"columns": {
"value": {
"To": "={{ JSON.parse($('Image Message Processing').item.json.text.replace(/^```(?:json|markdown)?\\n?/, \"\").replace(/\\n?```$/, \"\")).To }}",
"Date": "={{ JSON.parse($('Image Message Processing').item.json.text.replace(/^```(?:json|markdown)?\\n?/, \"\").replace(/\\n?```$/, \"\")).Date }}",
"From": "={{ JSON.parse($('Image Message Processing').item.json.text.replace(/^```(?:json|markdown)?\\n?/, \"\").replace(/\\n?```$/, \"\")).From}}",
"Amount": "={{ JSON.parse($('Image Message Processing').item.json.text.replace(/^```(?:json|markdown)?\\n?/, \"\").replace(/\\n?```$/, \"\")).Amount }}",
"Status": "={{ JSON.parse($('Image Message Processing').item.json.text.replace(/^```(?:json|markdown)?\\n?/, \"\").replace(/\\n?```$/, \"\")).Status }}"
},
"schema": [
{
"id": "Status",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Status",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "From",
"type": "string",
"display": true,
"required": false,
"displayName": "From",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "To",
"type": "string",
"display": true,
"required": false,
"displayName": "To",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Date",
"type": "string",
"display": true,
"required": false,
"displayName": "Date",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Amount",
"type": "string",
"display": true,
"required": false,
"displayName": "Amount",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"Status"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1PUXj_t3G-arnfzNDbY0g9Pr1G4YMGrc68fDs98pV-n4/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "url",
"value": "https://docs.google.com/spreadsheets/d/1PUXj_t3G-arnfzNDbY0g9Pr1G4YMGrc68fDs98pV-n4/edit?gid=0#gid=0"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.5
},
{
"id": "a268daa7-76d9-437b-99e9-bd755eb4d36f",
"name": "Line: Messaging API",
"type": "n8n-nodes-base.webhook",
"position": [
-820,
400
],
"parameters": {
"path": "4c0de537-2889-47d2-ac44-3a9cda89c9f3",
"options": {},
"httpMethod": "POST"
},
"typeVersion": 2
},
{
"id": "b3c4c66a-78d6-4ad5-9a5c-afef6f86e5cc",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
460,
0
],
"parameters": {
"width": 420,
"height": 1020,
"content": "## Reply to User\n\nReply the processing result to the user without coding or OCR processing."
},
"typeVersion": 1
},
{
"id": "6c76dc81-6c10-4522-9d5f-da4579391281",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
900,
520
],
"parameters": {
"width": 420,
"height": 500,
"content": "## Insert result to Google Sheet\nGet all important information from the Pay Slip and insert into Google Sheet in the same format that we have provided in our prompt.\n"
},
"typeVersion": 1
},
{
"id": "49bac770-adb1-4ef3-8bf9-c8cf107471ad",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-860,
260
],
"parameters": {
"width": 620,
"height": 500,
"content": "## Get Line Message from User\nUser can send message in both text and Pay Slip image then classify the message type in text or image so we could have single workflow for AI Assistant that support anything."
},
"typeVersion": 1
},
{
"id": "9f034b6f-bb5b-4dc6-941d-b745f15da254",
"name": "Google Gemini for Text",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
60,
320
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "15fa3203-9230-4a1d-9e0d-87652cb9d9ab",
"name": "Google Gemini for Image",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
60,
880
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
}
],
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "d14ef869-77c2-49a8-9867-1775d8f0b085",
"connections": {
"Message Type": {
"main": [
[
{
"node": "Message Classification",
"type": "main",
"index": 0
}
]
]
},
"Line: Get Image": {
"main": [
[
{
"node": "Image Message Processing",
"type": "main",
"index": 0
}
]
]
},
"Line: Messaging API": {
"main": [
[
{
"node": "Message Type",
"type": "main",
"index": 0
}
]
]
},
"Window Buffer Memory": {
"ai_memory": [
[
{
"node": "Text Message Processing",
"type": "ai_memory",
"index": 0
}
]
]
},
"Google Gemini for Text": {
"ai_languageModel": [
[
{
"node": "Text Message Processing",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Line: Response to User": {
"main": [
[
{
"node": "Text from Slip Result",
"type": "main",
"index": 0
}
]
]
},
"Message Classification": {
"main": [
[
{
"node": "Text Message Processing",
"type": "main",
"index": 0
}
],
[
{
"node": "Line: Get Image",
"type": "main",
"index": 0
}
],
[]
]
},
"Google Gemini for Image": {
"ai_languageModel": [
[
{
"node": "Image Message Processing",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Text Message Processing": {
"main": [
[
{
"node": "Line: Text Response to User",
"type": "main",
"index": 0
}
]
]
},
"Image Message Processing": {
"main": [
[
{
"node": "Line: Response to User",
"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.
googlePalmApigoogleSheetsOAuth2ApihttpHeaderAuth
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow enables you to build an intelligent chatbot on Line that swiftly extracts key details from uploaded payslips, saving users hours of manual data entry and reducing errors in payroll processing. It's ideal for HR teams or small businesses handling employee queries about salaries, deductions, or bonuses via chat. The core step involves receiving an image via Line's webhook, classifying the message, and using Google's Gemini AI to analyse and pull out structured text data, which can then feed into Google Sheets for seamless record-keeping.
Use this workflow when you need a quick, automated way to process payslip images in customer support chats, especially for high-volume queries in multilingual environments. Avoid it for non-image formats like PDFs, where specialised OCR tools might be better, or if your compliance requires on-premise processing rather than cloud AI. Common variations include adapting it for invoice extraction or integrating with email triggers instead of Line for broader messaging support.
About this workflow
Line_Chatbot_Extract_Text_from_Pay_Slip_with_Gemini. Uses memoryBufferWindow, stickyNote, httpRequest, agent. Webhook trigger; 17 nodes.
Source: https://github.com/Zie619/n8n-workflows — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Extract text from image using AI is worth because you need no code. It incorporates Google Gemini 2.0 Flash model for important text extraction from image. If you code without AI, you have to use mult
Memory Buffer Window, HTTP Request, Agent +3
Resume Screening & Behavioral Interviews with Gemini, Elevenlabs, & Notion ATS copy. Uses outputParserStructured, chainLlm, googleDrive, stickyNote. Webhook trigger; 67 nodes.
Output Parser Structured, Chain Llm, Google Drive +9
Candidate Engagement | Resume Screening | AI Voice Interviews | Applicant Insights
Output Parser Structured, Chain Llm, Google Drive +9
leads. Uses supabase, gmail, formTrigger, httpRequest. Webhook trigger; 62 nodes.
Supabase, Gmail, Form Trigger +13
This workflow acts as an AI-powered research assistant that takes a topic from the user, performs multi-step intelligent research, and stores the final report in Notion. It uses advanced search, conte
Memory Buffer Window, Output Parser Structured, Agent +6