A multilingual loan advisory application developed for Track 2 of the Great Bengaluru Hackathon. This application helps users get loan-related information and advice in their preferred language.
Backend of this Project is available at gnanendranaidun/Langchain
- Multilingual Support: Seamlessly switch between multiple Indian languages
- Voice Interaction: Support for speech-to-text and text-to-speech in multiple languages
- Real-time Translation: Dynamic content translation using advanced language models
- Responsive Design: Works perfectly on both desktop and mobile devices
- Dark/Light Mode: Customizable theme for better user experience
- AI-Powered Advice: Intelligent loan recommendations using Sarvam AI
- Frontend: React with TypeScript
- Styling: Tailwind CSS
- Icons: Lucide React
- Routing: React Router
- State Management: React Context API
- API Integration: Fetch API with CORS support
src/
├── components/
│ ├── FloatingChatbot/ # AI chatbot interface
│ ├── LanguageSelector/ # Language switching component
│ ├── MainLayout/ # Main application layout
│ ├── ThemeToggle/ # Theme switching component
│ └── VoiceRecorder/ # Voice input component
├── contexts/
│ ├── LanguageContext/ # Language state management
│ └── ThemeContext/ # Theme state management
├── services/
│ ├── api.ts # API integration
│ └── sarvamAI.ts # Sarvam AI service integration
└── pages/
├── Home/ # Landing page
├── Loans/ # Loan information
├── Calculator/ # Loan calculator
├── About/ # About page
└── Contact/ # Contact information
The Sarvam AI API provides advanced language processing capabilities for our application:
-
Speech-to-Text API
- Converts voice input to text in multiple Indian languages
- Supports real-time transcription
- Handles multiple audio formats
-
Text-to-Speech API
- Converts text responses to natural-sounding speech
- Supports multiple Indian languages
- Provides voice customization options
-
Translation API
- Translates content between Indian languages
- Maintains context and meaning during translation
- Supports real-time translation
Our custom API handles loan-related queries and provides intelligent responses:
- Base Endpoint:
/ask - Request Format:
{ "question": "your question here" } - Features:
- Processes English text queries
- Returns contextual loan advice
- Integrates with translation services for multilingual support
-
Clone the repository:
git clone [repository-url]
-
Install dependencies:
cd multilingual-loan-sarvam npm install -
Set up environment variables:
cp .env.example .env # Add your API keys and endpoints -
Start the development server:
npm run dev
Create a .env file with the following variables:
VITE_SARVAM_API_KEY=your_api_key_here
VITE_SARVAM_API_ENDPOINT=your_endpoint_here
VITE_CUSTOM_API_ENDPOINT=your_custom_api_endpoint- English (en-IN)
- Hindi (hi-IN)
- Kannada (kn-IN)
- Tamil (ta-IN)
- Telugu (te-IN)
- Malayalam (ml-IN)
- Bengali (bn-IN)
- Marathi (mr-IN)
- Gujarati (gu-IN)
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
This project is licensed under the GNU General Public License v3.0. This means:
- You can freely use, modify, and distribute this software
- Any modifications must also be open source under GPL-3.0
- You must include the original copyright notice
- No warranty is provided
For more details, see the LICENSE file.
This project was developed as part of Track 2 of the Great Bengaluru Hackathon, which focused on:
- Creating innovative solutions for financial inclusion
- Leveraging technology to break language barriers
- Making financial services accessible to all Indians
- Promoting digital literacy and financial awareness
- Aditya Ranjan
- Gnanendra Naidu N
- Mihir Shriniwas Arya
- Sarvam AI for providing the AI and language processing capabilities
- Great Bengaluru Hackathon organizers
- All contributors and supporters
For any questions or issues:
- Open an issue in the GitHub repository
- Contact the development team
- Check the documentation for common solutions


