Welcome

Introduction

Introduction

Setup & Installation

Setup OverviewPrerequisitesQuick Start
Backend OverviewInstallationConfigurationRunning LocallyDevelopment Guide
MCP Servers

Architecture & Design

Architecture

Features & Scenarios

Deployment

Deployment

API Reference

API Reference

Tools & Utilities

Scripts & UtilitiesTroubleshooting
Setup & InstallationBackend Setup

Backend Overview

Set up the SynapseAI FastAPI backend

Backend Setup

The SynapseAI backend is a FastAPI application powered by LangGraph for conversational AI orchestration.

Setup Steps

Follow these pages in order:

1. Installation

Install Python dependencies and tools

  • Time: 10 minutes
  • Difficulty: Beginner

2. Configuration

Set up environment variables and API keys

  • Time: 15 minutes
  • Difficulty: Beginner

3. Running Locally

Start the backend and verify it's working

  • Time: 5 minutes
  • Difficulty: Beginner

4. Development Guide

Hot reload, debugging, and best practices

  • Time: 20 minutes
  • Difficulty: Intermediate

What You'll Build

By the end of this section, you'll have:

✅ FastAPI backend running on http://localhost:8001
✅ LangGraph AI agent responding to chat messages
✅ MCP clients connecting to Commercetools and Voucherify
✅ Redis session storage
✅ Debug-ready development environment

Architecture Overview

Key Technologies

  • FastAPI: Web framework with automatic API documentation
  • LangGraph: Stateful AI agent orchestration
  • LiteLLM: Multi-provider LLM interface
  • Redis: Session and conversation history storage
  • MCP Protocol: Standardized external service integration
  • Pydantic: Data validation and serialization

Project Structure

backend/
├── app/
│   ├── agent/              # LangGraph AI agent
│   │   ├── intelligent_graph.py
│   │   └── state.py
│   ├── routers/            # API endpoints
│   │   └── auth.py
│   ├── services/           # Business logic
│   │   ├── customers.py
│   │   ├── prompts.py
│   │   └── session.py
│   ├── mcp/                # MCP client
│   │   └── client.py
│   ├── config.py           # Configuration
│   ├── models.py           # Data models
│   └── main.py             # Application entry
├── scripts/                # Utility scripts
├── docker-compose.dev.yml  # Docker setup
├── Dockerfile
├── pyproject.toml          # Dependencies
└── .env                    # Environment vars

Quick Start (Docker)

If you prefer Docker over manual setup:

cd backend
cp env.example .env
# Edit .env with your API keys
docker-compose -f docker-compose.dev.yml up --build -d

Then skip to Configuration to set up your API keys.

Prerequisites

Before proceeding, ensure you have:

  • ✅ Python 3.11+ installed
  • ✅ Docker Desktop running (for Redis)
  • ✅ API keys ready (LLM provider, Commercetools, Voucherify)

Missing something? Go back to Prerequisites

Next Steps

1. Installation →

Install Python and dependencies

2. Configuration →

Set up API keys

Quick Start

Get SynapseAI running in 30 minutes with Docker Compose

Installation

Install Python dependencies and tools

On this page

Backend SetupSetup Steps1. Installation2. Configuration3. Running Locally4. Development GuideWhat You'll BuildArchitecture OverviewKey TechnologiesProject StructureQuick Start (Docker)PrerequisitesNext Steps