AI · AIC-90

LINE AI Chatbot with Gemini and ChatGPT

LINE AI Chatbot with Gemini and ChatGPT is a hands-on course in building a LINE Official Account chatbot in Node.js that answers with the Gemini API or OpenAI API, remembers conversations, uses RAG over product data and hands chats over to staff. It suits Node.js developers and IT teams at businesses that serve customers on LINE, and you leave with a prototype bot running on Cloud Run.

Updated
From 6,210 THB / person 6,900 −10% excl. VAT 7% · group rates available
PDFDownload the course outline
  • Duration12 hours · 2 days
  • FormatOnsite / live online
  • Next roundOn request
  • CertificateIncluded

Course overview

LINE Official Account is the main channel Thai customers use to contact shops and businesses, yet admins struggle to keep up with questions about prices, stock, order status and the same queries over and over. Older bots that reply by keyword or intent can only answer questions someone prepared in advance. LLMs such as Gemini and ChatGPT understand everyday language far better, but wired straight into LINE the bot forgets the conversation, quotes prices that do not exist and never knows when to let an admin take over.

This course shows learners how to build a LINE OA chatbot in Node.js that answers with AI and the business's own data. Learners set up the Messaging API and webhook, connect the Gemini API and OpenAI API through a common layer that can switch models, keep conversation memory per user, reply with Flex Messages and Quick Replies, and let the bot check stock and order status through function calling. They then add RAG over product data and FAQs, design handover to admins with a case summary, put guardrails and PDPA controls in place and deploy to Cloud Run. It closes with a capstone chatbot for a sample business. (2 days, 6 hours per day, 12 hours in total, Intermediate level.)

What you’ll gain

  • Set up a LINE Official Account, the Messaging API and a webhook in Node.js
  • Connect the Gemini API and OpenAI API through a common layer that can switch providers
  • Keep conversation memory per user while controlling context length and respecting PDPA
  • Reply with Flex Messages, Quick Replies and Rich Menus generated from LLM output
  • Let the bot check live data such as stock and order status through function calling
  • Build RAG over product data and FAQs so the bot answers from the business's own information
  • Design a structured handover to admins and hand the conversation back to the bot
  • Deploy to Cloud Run with logging, guardrails and cost control

Who this course is for

  • JavaScript and Node.js developers who want to build AI chatbots on LINE OA
  • IT teams at online shops, clinics and service businesses that talk to customers through LINE OA
  • People who have built keyword or intent-based LINE bots and want to move to LLMs
  • Freelancers and agencies who build LINE chatbots for clients
  • System owners who want a chatbot architecture that is secure and keeps costs under control

Prerequisites

  • JavaScript skills and basic experience with Node.js and npm
  • A basic understanding of REST APIs, JSON and how webhooks work
  • A basic understanding of using LLMs and writing prompts
  • A laptop that can run Node.js and VS Code, plus a LINE account and a smartphone for testing

Curriculum

Course Details

The course runs for 2 days, 6 hours per day (12 hours in total, 09:00-16:00), as lectures with labs built on a single sample shop throughout. Intermediate level. It focuses on LINE OA chatbots that answer with LLMs, which sets it apart from the Dialogflow LINE chatbot course built on intents, from LINE Workflow Automation with Claude Code & MCP, which covers internal automation, and from LINE LIFF and

MINI App Development, which covers web pages inside the LINE app. Learners use their own or company accounts. The free LINE OA plan has a limited push message quota, the Gemini API has a free tier, and the OpenAI API and Google Cloud Run are billed by usage and need a billing account. Learners take home a lab guide, Node.js code for every lab and a prototype capstone project with a Dockerfile.

Day 1 LINE OA, LLMs and a Bot That Remembers

Section 1: AI Chatbots on LINE OA

  • From keyword and intent bots to bots that answer with an LLM
  • Architecture: LINE Platform, webhook, backend, LLM API and database
  • Choose the Gemini API or OpenAI API by Thai quality, price and features
  • Lab: create a LINE Official Account and a Messaging API channel

Section 2: Lab: A Webhook in Node.js

  • Set up the channel secret, channel access token and webhook URL
  • Receive events with the LINE Messaging API SDK and verify the signature
  • Reply messages compared with push messages, and the LINE OA message quota
  • Test locally through a tunnel before deploying

Section 3: Connecting the Gemini API and OpenAI API

  • Call the Gemini API and OpenAI API from Node.js
  • System instructions that set the persona, scope and brand tone
  • The LINE loading animation while waiting, and handling API timeouts
  • A common layer that switches LLM provider without touching the rest of the code
  • Lab: a bot that answers general shop questions with an LLM

Section 4: Lab: Conversation Memory

  • Store chat history per userId in Firestore or PostgreSQL
  • Limit context length, summarise older turns and delete history on request
  • Remember only what is needed, such as a preferred name and products of interest, respecting PDPA
  • Handle several messages sent in a row and group chats

Section 5: Lab: Flex Messages, Quick Replies and Images

  • Have the LLM answer in JSON and turn it into Flex Messages and Quick Replies
  • Receive customer photos and let a vision model describe them or find products
  • Rich Menus for the main menu, switched according to the user's status
  • Lab: show recommended products as a Flex Message carousel

Section 6: Lab: Function Calling for Live Data

  • Let the LLM call functions to check stock, prices and order status
  • Validate the input the LLM sends before calling real systems
  • Handle missing data and downstream systems that are down
  • Stop the bot from revealing other customers' data
Day 2 Product RAG, Admin Handover and Going Live

Section 7: RAG over Product Data and FAQs

  • Prepare product data, prices, policies and FAQs for search
  • Managed file search in the Gemini API or OpenAI compared with running your own vector search
  • Hybrid search that combines vector search with filters such as category and price range
  • Say I do not know when there is no data instead of guessing a price
  • Lab: a bot that answers product questions from a sample catalogue

Section 8: Lab: Updating Data Without Changing Code

  • Keep product data in Google Sheets or a database that the team can edit
  • Sync changes into the index automatically
  • Keep prompts and standard replies outside the code
  • Re-run a fixed set of test questions before switching on new data or prompts

Section 9: Lab: Handover to Admins

  • Handover triggers: the customer asks for a person, the bot is unsure, or it is a complaint
  • Pause the bot for that customer only and let admins reply through Chat in LINE Official Account Manager
  • Alert the team with a conversation summary and give control back to the bot when the case is closed
  • Lab: an admin handover system with a case summary

Section 10: Guardrails, PDPA and Security

  • Defend against prompt injection and attempts to push the bot off topic
  • Define what the bot must never promise, such as discounts or refunds outside policy
  • PDPA: data collection notices, retention periods and customer rights
  • Store API keys and the channel secret securely

Section 11: Lab: Deploying to Cloud Run and Operations

  • Containerise with Docker and deploy the backend to Cloud Run
  • Logging, monitoring and alerts when the bot fails
  • Control LLM cost by choosing models, limiting length and caching answers
  • Measure real conversations and keep refining prompts

Section 12: Workshop: LINE AI Chatbot Capstone

  • Choose a sample business: an online shop, a clinic or after-sales service
  • Assemble the full bot: memory, RAG, function calling and admin handover
  • Test with a realistic question set and hard cases
  • Demo it on your own LINE account with a launch plan

Schedule & training options

For individuals — public rounds

No public rounds are open right now. Join the waiting list and we will contact you first when the next round opens, or ask us on LINE. Or call 02-570-8449 or 088-807-9770

For organisations — in-house / private

  • Tailor the content to your team’s tools and projects
  • Your dates, at your office or live online
  • Quotation with tax ID for procurement
Corporate training quote

Instructors

Frequently asked questions

Who is LINE AI Chatbot with Gemini and ChatGPT for, and what background is needed?

Built for JavaScript and Node.js developers who want to build AI chatbots on LINE OA · IT teams at online shops, clinics and service businesses that talk to customers through LINE OA · People who have built keyword or intent-based LINE bots and want to move to LLMs Background you should have: JavaScript skills and basic experience with Node.js and npm · A basic understanding of REST APIs, JSON and how webhooks work Not sure the fit is right? Talk to our team on LINE @itgenius or call 02-570-8449.

How much does LINE AI Chatbot with Gemini and ChatGPT cost and how long does it run?

THB 6,900 (currently THB 6,210 on promotion). The course runs 12 hours. The price excludes 7% VAT (for payment in a company's name). Pay by bank transfer to the company account, confirm it on our payment page, and we can issue the receipt or tax invoice in your company's name.

Do I get a certificate?

Yes. Everyone who completes the course receives a Certificate of Completion from IT Genius Institute. Each certificate carries its own number, and anyone holding that number can verify it online on our certificate page, so you can add it to your portfolio or pass it to HR as evidence of training.

Where does the training take place, and is there an online option?

You can attend onsite at IT Genius Institute or arrange to join online, and we also run it as a private in-house session for your team. Ask about dates and venues on LINE @itgenius or call 02-570-8449.

What if I fall behind or miss a session — can I retake it?

Yes. You may retake the same course free of charge in a later round, under the institute's conditions. Tell our team which course and round you attended, and we will check it and offer you the rounds that still have seats. Ask us on LINE @itgenius or call 02-570-8449.

How do I enrol, or request a quotation for my company?

Enrol online with the registration form on this page. You can register several attendees at once and enter your tax ID and billing address for the tax invoice. Or request a company quotation straight from the quote button. For anything else call 02-570-8449 or reach us on LINE @itgenius.