Aida is a compassionate AI assistant designed to help people in crisis navigate the complex wall of bureaucracy. It transforms a stressful, confusing process into a simple and dignified conversation, providing clear guidance on social support programs.

This project was created for the GNEC Hackathon 2025 Fall, with the goal of demonstrating how modern AI technologies can be used to directly address UN Sustainable Development Goal #1: No Poverty.

Aida serves as a prototype for a future of humane digitalization, where technology empowers and supports the most vulnerable.

Main Interface	Architecture Diagram

• Compassionate Conversational AI: Powered by Google Gemini, Aida understands natural language and provides empathetic, human-like responses.
• RAG-Powered Knowledge Base: Ensures all answers are accurate and trustworthy by grounding them in a vector database of official documents.
• OCR Document Recognition: Utilizes Google Cloud Vision to instantly extract text from uploaded documents, eliminating the need for manual data entry.
• Clean & Accessible UI: A modern, calm, and intuitive interface built with Next.js and Tailwind CSS.

• Frontend: Next.js, React, TypeScript, Tailwind CSS
• Backend: Python, FastAPI
• AI: Google Gemini & Google Cloud Vision
• RAG Pipeline: LangChain, Hugging Face Sentence Transformers, FAISS Vector Store

To get a local copy up and running, follow these simple steps.

• Node.js (v18 or later)
• Python (v3.9 or later)
• Google Cloud account with API keys for Gemini and Vision.

1. Clone the repo

   git clone https://github.com/vero-code/aida.git
   cd aida

2. Backend Setup

   # Navigate to the backend folder
   cd backend
   
   # Create and activate a virtual environment
   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`
   
   # Install required packages
   pip install -r requirements.txt
   
   # Create the knowledge base
   python create_knowledge_base.py
   
   # Create a .env file and add your Google API Key
   echo 'GOOGLE_API_KEY="YOUR_GEMINI_API_KEY"' > .env
   
   # Place your Google Cloud service account key file here
   # and name it gcp-credentials.json

3. Frontend Setup

   # Navigate to the frontend folder
   cd ../frontend
   
   # Install NPM packages
   npm install

You will need to run the backend and frontend servers in two separate terminals.

1. Run the Backend Server (from the backend folder):

   uvicorn main:app --reload

   The backend will be running on http://127.0.0.1:8000.

2. Run the Frontend Server (from the frontend folder):

   npm run dev

   Open http://localhost:3000 in your browser to see the result.

This project is licensed under the MIT License. See the LICENSE file for more details.