We just released a production ready RAG template project for Bult.ai.
Full step-by-step video tutorial is here: https://youtu.be/CkcVGtiSGDQ?si=Y1X1LP-Aw09g_zIp
Full text tutorial is here: https://docs.bult.ai/tutorials/tutorial-rag
If you want to deploy a serious Retrieval Augmented Generation (RAG) system, this is for you.
What it includes:
• Hybrid search combining BM25 and vector similarity
• Cross encoder reranking for higher precision
• Optional HyDE and multi query retrieval
• Multi model support: OpenAI, Anthropic, Google, Ollama
• OCR for scanned PDFs
• JWT authentication and optional Google OAuth
• Analytics dashboard with usage and latency tracking
• Conversation export to Markdown, JSON, and PDF
• Async background processing with job tracking
You upload documents.
Ask questions.
Get answers with inline citations and source scoring.
It deploys on Bult.ai using:
• GitHub based app service
• PostgreSQL
• pgvector
No Kubernetes. No infrastructure gymnastics.
This template demonstrates how to run production grade AI workloads on a PaaS with full control over architecture.
If you're building AI products and need a strong RAG foundation, fork it and deploy in minutes.
Would love feedback from builders pushing RAG systems to real world scale.
Top comments (0)