Tembo AI Kenya Travel Assistant
# π Tembo AI β Kenya Travel Assistant
An AI-powered travel assistant for Kenya with a beautiful React frontend and a fully free tech stack.
**π Live Demo:**
tembo-ai-frontend.onrender.β¦
---
## β¨ Features
- π¦ **Smart RAG Pipeline** β Retrieval-augmented generation for accurate Kenya travel info
- π¬ **Conversational AI** β Personalized responses with Swahili flair
- π¨ **Beautiful UI** β Modern React + Tailwind CSS frontend with animations
- β‘ **Real-time Typing Effect** β Character-by-character response display
- π·οΈ **Category Filters** β Filter by Safari, Beaches, Culture, Transport
- π **Source Attribution** β See which documents informed each answer
- π **100% Free Stack** β Cohere embeddings + Groq LLM + Supabase
---
## π οΈ Tech Stack
| Component | Technology |
|-----------|------------|
| **Frontend** | React + Tailwind CSS |
| **Backend** | FastAPI (Python) |
| **Embeddings** | Cohere `embed-english-light-v3.0` (free tier) |
| **LLM** | Groq `llama-3.3-70b-versatile` (free tier) |
| **Vector DB** | PostgreSQL + pgvector (Supabase) |
| **Hosting** | Render (free tier) |
---
## π Quick Start
### Backend
```bash
# Clone the repo
git clone
github.com
cd tembo-ai
# Create virtual environment
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Set up PostgreSQL with pgvector
psql -U postgres -f setup_vector.py # Run SQL commands to create tables
# Set up environment variables
cp .env.example .env
# Edit .env and add your API keys
# Populate the knowledge base
python massive_kenya_data.py # Or: python scrape_kenya_data.py
# Run the server
uvicorn main:app --reload
```
### Frontend
```bash
cd frontend
npm install
npm run dev
```
- **Backend API**: `
localhost`
- **Frontend UI**: `
localhost`
- **API Docs**: `
localhost`
---
## π Project Structure
```
tembo-ai/
βββ main.py β¦