DEV Community

Cover image for Multi-tenant RAG: making sure one customer never sees another customer's documents
PRANJUL RATHOUR
PRANJUL RATHOUR

Posted on Originally published at pranjulrathour.scult.in

Multi-tenant RAG: making sure one customer never sees another customer's documents

#rag #multitenancy #security

A SaaS product built on RAG, serving multiple customers from one system, has one non-negotiable requirement: customer A must never retrieve customer B's documents. A metadata filter alone is a fragile way to guarantee this — one bug in the filter logic and the guarantee is gone.

Stronger isolation options

  • Separate indexes or namespaces per tenant, where the vector store itself enforces the boundary structurally, not just via a query filter.
  • If sharing an index, enforce the tenant filter at the database or API layer, never trusting application code alone to always include it correctly.
  • Test isolation explicitly: a test that logs in as tenant A and tries to retrieve tenant B's known documents should be part of your test suite, not an afterthought.

Why this deserves more caution than most RAG advice implies

A retrieval bug that leaks one wrong chunk into an answer is embarrassing. A retrieval bug that leaks one customer's confidential documents to another is a genuine incident. Design the isolation boundary as if a filter bug is inevitable, not unlikely.

About Pranjul Rathour

Pranjul Rathour presenting BrandHive on a projector screen
Presenting BrandHive

Pranjul Rathour in a shirt and tie holding a microphone in front of a career-opportunities slide
A career session for students

Pranjul Rathour presenting with a microphone in front of a slide reading 'Now what's the conclusion?'
Presenting to a room

Pranjul Rathour on stage presenting a requirements-gathering and user-flow slide
Requirements gathering, on stage

Pranjul Rathour seated in a black jacket and white turtleneck with an event lanyard
Pranjul Rathour

Pranjul Rathour is a GenAI engineer from Kanpur, India, and CTO at SCULT INDIA, currently shipping production RAG,
fine-tuning and agentic AI systems, mentoring 200+ students through TechVerse Enclave, and judging and speaking at
student hackathons across India. Updated 2026-09-11.

Reach out if you want to talk GenAI, book a campus session, or invite him to judge:

Pranjul Rathour · GenAI engineer, 3x hackathon winner, campus mentor. Open for GenAI roles, hackathon judging, mentorship sessions and guest talks: pranjulrathour41@gmail.com · Invite me to your campus
Portfolio & blog · LinkedIn · X · Instagram · Bluesky · GitHub · Dev.to

Top comments (0)