🧠 DevBrain

AI-Powered Document Intelligence Platform

Upload documents. Chat with them. Search semantically. Get AI-powered insights.

Demo · Quick Start · Architecture · Documentation

---

✨ Features

• 📄 Document Processing — Upload PDF, Markdown, and code files with automatic parsing
• 🔍 Semantic Search — Find documents by meaning, not just keywords, using pgvector
• 💬 Chat with Documents — RAG pipeline with inline citations and streaming responses
• 📊 Dashboard — Real-time metrics, document stats, and system health
• 🤖 AI Agents — Intelligent agents that search, summarize, and connect information
• 📈 Quality Evaluation — Systematic RAG evaluation with RAGAS framework
• 👍 Feedback Loop — Thumbs up/down to continuously improve AI responses
• 🔐 Authentication — OAuth with GitHub/Google via Auth.js v5

🏗️ Tech Stack

Layer	Technology
Frontend	Next.js 15+, TypeScript, Tailwind CSS v4, shadcn/ui
Backend	Python 3.12, FastAPI, Pydantic v2, SQLAlchemy
AI	LiteLLM, LangGraph, Google AI Studio, Groq, HuggingFace
Database	PostgreSQL 16 + pgvector, Redis
Infrastructure	Docker Compose, GitHub Actions, Vercel, Railway
Package Manager	uv (Python), npm (Node.js)

🚀 Quick Start

Prerequisites

• Docker Desktop (v24+)
• Python 3.12+ with uv
• Node.js 20+ with npm
• Git

Setup

# Clone the repository
git clone https://github.com/YOUR_USERNAME/devbrain.git
cd devbrain

# Copy environment variables
cp .env.example .env

# Start infrastructure (PostgreSQL + Redis)
make up

# Install backend dependencies
make install-backend

# Install frontend dependencies
make install-frontend

# Run database migrations
make migrate

# Start development servers
make dev

The app will be available at:

• Frontend: http://localhost:3000
• Backend API: http://localhost:8000
• API Docs: http://localhost:8000/docs

🏛️ Architecture

Browser → Next.js (Vercel) → FastAPI (Railway) → PostgreSQL + pgvector
                                    ↓
                              LiteLLM → Google AI Studio / Groq / HuggingFace

See docs/ARCHITECTURE.md for detailed architecture documentation.

📁 Project Structure

DevBrain/
├── backend/          # FastAPI application (Python)
├── frontend/         # Next.js application (TypeScript)
├── docs/             # Documentation & architecture guides
├── scripts/          # Helper scripts (seeding, evaluation)
├── docker-compose.yml
├── Makefile          # Project command interface
└── .env.example      # Environment template

🧪 Testing

# Run all backend tests
make test-backend

# Run frontend tests
make test-frontend

# Run phase verification checks
make verify-phase0
make verify-phase1
# ... etc

# Run all verifications
make verify-all

📝 License

This project is licensed under the MIT License — see the LICENSE file for details.

---

_{Built with ❤️ as a Fullstack AI Engineer portfolio project}