README.md

Lingobot.AI

Lingobot is an AI-powered chatbot built with TypeScript and LangChain that helps users practice and learn new languages through realistic, scene-based conversations. It adapts to user proficiency, corrects mistakes in real-time, stores chat history in SQLite, and offers feedback for continuous improvement. Responsive design and interactive chat UI ensure a smooth learning experience across devices.

https://lingobot-ai.onrender.com/

✨ Key Features

Simulates real-life, scene-based conversations for immersive language learning.
Generates natural language responses to simulate realistic, human-like dialogue.
Provides a personalized experience by storing user preferences, conversation history, and learning progress across sessions.
Supports multiple languages and adapts conversations based on the user's native and target languages.

🛠 Tech Stack

ai: google-genai

development: TypeScript, LangChain

deployment: Render

Project Structure

📁Lingobot.AI

📁public

📄file.svg

📄globe.svg

📄next.svg

📄vercel.svg

📄window.svg

📁tests

📁app

📁api

📁chat

📄route.ts

📁chat

📁components

📄ChatMessages.tsx

📄MessageInput.tsx

📄PreferencesPopup.tsx

📄page.tsx

📄favicon.ico

📄globals.css

📄layout.tsx

📄page.tsx

📁db

📄sqlite.db

📁lib

📄db.ts

📄gemini.ts

📄langchain.ts

📁prisma

📄dev.db

📄dev.db-journal

📄schema.prisma

📄.gitignore

📄README.md

📄next.config.ts

📄package-lock.json

📄package.json

📄postcss.config.mjs

📄tsconfig.json

⚙️ Setup & Installation

# Clone the repository

git clone https://github.com/rahullbyte/Lingobot.AI.git

# Navigate to the project directory

cd Lingobot.AI

# Install dependencies

npm install

# Upgrade the dotenv

# Run the Development

npm run dev

🚀 Live Demo

https://lingobot-ai.onrender.com/

Render URL.

🌍 Deployment

Frontend: Render

Backend: Render

📜 Changelog

Version v1.0.0

Initial release with basic conversation flow and language preference setup.

Version v1.5.0

Introduced scene-based conversations and multilingual support.

Version v2.0.0

Added personalized learning features, conversation history, and progress tracking.

🔥 Challenges & Learnings

Challenge: Creating realistic, engaging dialogues for diverse language learners

Solution: Used scene-based conversation design and integrated LLMs with adaptive response logic

Outcome: Achieved natural, personalized chats that adapt to users’ fluency levels and learning goals

⚡ Performance Optimizations

Implemented conversation streaming for faster, real-time message rendering
Cached language models and user preferences to reduce load times
Optimized database queries and session handling for smoother multi-language support

🔒 Security Measures

Sanitized and validated user inputs to prevent prompt injection and abuse
Encrypted user preferences, chat history, and session data in storage
Implemented rate limiting and auth guards to prevent abuse and ensure API safety

🔮 Future Improvements

Introduce gamified learning modules and achievement badges
Add speech recognition for voice-based conversations
Implement feedback analytics to suggest improvements based on user progress