Multi-tenant
An architecture that runs multiple companies on shared infrastructure while keeping their data separate.
TL;DR
Isolated data per company on shared infrastructure.
Quick facts
- Category
- AI & knowledge management
- Product tie-in
- KobiGPT RAG platform
- Related
- See compare and tools pages
- Locale
- TR and EN site
Why teams choose KobiGPT
- Understand terms before evaluating vendors.
- Link concepts to KobiGPT features (RAG, Kobi Kredi).
- Share glossary links with procurement and legal.
- Explore assistant use cases next.
Product facts
- Ücretsiz plan
- 100 doküman · 2 departman · 120 Kobi/ay(PLAN_CONFIG)
- Starter
- 1000 doküman · 5 departman · 1000 Kobi/ay(PLAN_CONFIG)
- Pro
- 12500 doküman · 25 departman · 12500 Kobi/ay(PLAN_CONFIG)
- Tenant plan scope
- Per-company plan, user, and document limits(packages/types/src/plan-config.ts → PLAN_CONFIG)
What multi-tenant means
In a multi-tenant SaaS application, each company is a tenant and several tenants share the same application infrastructure. Shared servers do not mean shared records: users, documents, settings, and usage data remain bounded by the company.
For KobiGPT, the company boundary is the important one. A user’s chat runs against assistants and document scope belonging to that company; another company’s file must not appear in retrieval results or citations.
Where isolation is enforced
Isolation is more than selecting a company in the interface. API queries are bounded by companyId, relational records carry ownership, and vector retrieval runs against a company-named collection. Every layer has to apply the same boundary.
Department scope is a second boundary inside the company. HR, finance, and legal assistants have their own document and user relationships; a role grants access within the tenant, not outside it.
The practical SME trade-off
The multi-tenant model provides plan, user, and document management without requiring a separate server for every company. In return, tenant boundaries, authorisation, and retrieval filters must be checked whenever a new feature is designed.
When evaluating a product, do not stop at the phrase shared infrastructure. Verify company-scoped collections, company-bound queries, and role checks together, including what happens when a record has the wrong or missing scope.
Applying What multi-tenant means in a controlled workflow
A useful way to evaluate multi-tenant is to follow one real question from the source document to the final answer. Record which file was selected, what context reached the model, and what a reviewer would need to verify. This turns a definition into an operational check and makes the result comparable across teams.
The same check should include ownership and change management. Decide who updates the relevant documents, how an outdated result is reported, and which access boundary applies. KobiGPT can provide the assistant and the cited document context, but the organisation still owns the source material, permissions, and the decision made from the answer.
FAQ
What is Multi-tenant in practice?
Isolated data per company on shared infrastructure.
Does KobiGPT use this?
See product docs and feature pages for implementation details.
More reading?
Visit our blog and FAQ.
Accuracy disclaimer?
Educational content; verify for compliance decisions.
Do companies share one vector collection?
No. KobiGPT derives the Qdrant collection name from the company identity and searches that company collection.
Is multi-tenancy incompatible with self-hosting?
No. A self-hosted deployment can run on your infrastructure while retaining the same isolation model.
Comparison
| Feature | KobiGPT | Alternative |
|---|---|---|
| SME focus | Yes | N/A |
| Citations | When using RAG | N/A |
| Glossary depth | Growing | N/A |
| Tools | Interactive | N/A |