Ragforge
Enterprise patterns for building reliable, scalable RAG systems with clear service boundaries and governance layers.
Check out the Seed service to load the data for more information.
Technology Selection Rationale
| Technology | Why We Chose It | Alternatives Considered |
|---|---|---|
| FastAPI | Async, auto docs, type safety | Flask, Django |
| pgvector | PostgreSQL integration, ACID | Pinecone, Weaviate, Qdrant |
| Neo4j | Mature graph DB, Cypher | AWS Neptune, ArangoDB |
| Next.js | SSR, React, TypeScript | Vue.js, Svelte, vanilla React |
| Docker | Standard, ecosystem | Podman, containerd |
| AWS ECS | Managed, less ops than EKS | EKS, EC2, Lambda |
| Terraform | Multi-cloud, declarative | CloudFormation, Pulumi |
💻 Minimum System Requirements
Local Development
CPU: 4+ cores RAM: 16 GB (8 GB minimum) Disk: 20 GB free space OS: macOS, Linux, Windows with WSL2
Production (AWS)
API Gateway: 0.5 vCPU, 1 GB RAM Orchestrator: 2 vCPU, 4 GB RAM Embeddings: 2 vCPU, 4 GB RAM (CPU) or GPU instance Ontology: 1 vCPU, 2 GB RAM LLM Proxy: 0.5 vCPU, 1 GB RAM RDS: db.t3.large (2 vCPU, 8 GB RAM) Neo4j: t3.medium (2 vCPU, 4 GB RAM)
Quick Setup Commands
Python environment
uv venv
source .venv/bin/activate # or .venv\Scripts\activate on Windows
uv pip install -r pyproject.toml
Frontend
cd ui && npm install
Docker
docker compose up —build
Infrastructure
cd terraform && terraform init && terraform apply
That is the full stack behind Ragforge.