Data ExpoNumaga is exhibiting at Data Expo, 9 & 10 September — come visit our stand.Get your free ticket
Numaga.Built by Replikate
Solutions

What you get a grip on

Cost control

Usage insightsSee who uses AI, for what and how much — per user, group, agent and application.User limitsA usage ceiling per user and group — not an open tab.TiersThe right access level per group — not the most expensive profile for everyone.Model choiceNot one model — the right model, for every prompt.

Compliance

GuardrailsYour AI policy, enforced at the gate — configurable per organisation.Audit trailsEvery interaction logged — and retrievable when you need it.Prompt loggingThe full content of every interaction — question and answer — recorded.RBACYour team sees only what it is entitled to — end-to-end.

The platform

ChatOne familiar chat window, answers from your own knowledge — with sources.AppFor your people: just a familiar, secure assistant.Knowledge baseConnect your data sources; the knowledge base syncs automatically.EmbeddingsSearch your own documents by meaning — through the same gateway, with cost reported separately.Coding agentsRun your own coding agent — Claude Code, opencode — against the Numaga gateway.Applications & APIBuild Numaga governance into your own applications, via the API.
Solutions
Control planeCompliancePricingBlogAbout us
Book a demo

July 14, 2026

New in Numaga: embeddings through the gateway

Knowledge bases searchable by meaning, with cost and usage reported separately — inside the same governance as the rest of your AI traffic.

As of today, Numaga supports embeddings as a first-class part of the platform. Embeddings turn text into a numeric representation of meaning — the technique that lets a knowledge base find what you mean, even when your words differ from the document’s. Anyone working seriously with knowledge bases needs them; and precisely for that reason they belong inside your governance, not next to it.

Why this was needed

Knowledge bases grow fast. An organisation that connects thousands of documents — policy, manuals, registrations — quickly finds that keyword search falls short. Semantic search solves that, but until now it came with two problems: embedding traffic ran out of sight of governance, and the cost (real API rates, not token budgets) mixed with chat usage. That distorts every report.

So we routed embeddings through the same gateway as all other AI traffic. Same access policy, same logging, same cost controls — and vector storage sits in the managed database of your own environment, single-tenant in the Netherlands. No separate vector stack or external search service involved.

What you’ll notice

For users: better answers from the knowledge base, particularly in Dutch, and a combination of searching by meaning and by exact terms — the latter stays important for names, codes and domain jargon.

For administrators: a dedicated Embeddings overview in the dashboard. It shows which embedding models are active, how many calls run and what they cost — deliberately separated from the regular usage statistics, because putting tens of thousands of small embedding calls next to ordinary chat conversations is comparing apples and oranges.

Who this matters to

This is mainly relevant for organisations with large or growing knowledge bases. A concrete example from our own practice: a standard data source with tens of thousands of documents — including thousands of PDFs — is embedded end-to-end and stays searchable while the sync runs, without users noticing a thing.

Embeddings are on by default for new environments and can be enabled per environment for existing customers. Wondering what this means for your knowledge base? Book a demo — we’ll show it live.

← All articles

Numaga.

A managed, sovereign AI platform.

A product ofReplikate
PlatformControl planeModel routingArchitecturePricing
ComplianceEU AI ActAudit & observabilityAssurance packManaged service
ReplikateAbout usAbout ReplikateContactPrivacyResponsible disclosure
Numaga is a product of Replikate · ISO 27001 · Dutch sovereign infrastructure · © 2026