Extract pay slip data with Line Chatbot and Gemini to Google Sheets
Needs changesWhat this workflow does
This AI workflow has 12 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects Google Sheets and Google Gemini Chat Model. It also calls api.line.me over HTTP.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Message Type (Edit Fields (Set)): sets 4 fields: body.events[0].message.text, body.events[0].message.id, body.events[0].source.userId…
- Message Classification (Switch): routes items into 3 branches
- Text Message Processing (AI Agent): runs an AI agent, with model: Google Gemini for Text; memory: Window Buffer Memory
- Line: Get Image (HTTP Request): calls an HTTP API
- Line: Text Response to User (HTTP Request): calls api.line.me (POST)
- Image Message Processing (Basic LLM Chain): sends a prompt to an LLM, with model: Google Gemini for Image
- Line: Response to User (HTTP Request): calls api.line.me (POST)
- Text from Slip Result (Google Sheets): append
Services it uses
HTTP calls to: api.line.me
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Text Message Processing (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Text Message Processing (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (9)
- Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set - Switch
n8n-nodes-base.switch - AI Agent
@n8n/n8n-nodes-langchain.agent - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Google Sheets
n8n-nodes-base.googleSheets - Webhook
n8n-nodes-base.webhook - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini
From the author
Workflow Overview: 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 multiple condition and may cause a lot of…