Skip to content
MCP server built inHow that works

Configuring the AI backend

The chat is the only part of the platform that does not answer until it is configured. No language model ships with it — the choice is yours, and it decides where conversation content flows.

On this page

Only the chat waits

Login, worksheet, import, governance and search run without any backend — the embedding model for search ships with the platform.

Who may do this

Platform administrators configure the backend under KI & Semantik → KI-Anbindung (AI and semantics → AI backend). An ordinary user does not see the page.

The three routes

RouteWhat it needsWhere conversation content goes
Claude (Anthropic)An API key from the Anthropic consoleTo the provider
OpenAIAn API key from OpenAITo the provider
OpenAI-compatibleAddress and key of a self-hosted model, for example behind vLLMWherever that model runs — on your own network: nowhere outside
Sign in with ClaudeNo installation-wide key; each user signs in with their own accountTo the provider, under that user's own account

Setting it up

  1. Sign in as a platform administrator

    In the local compose stack that is flaky-admin.

  2. Open KI & Semantik → KI-Anbindung

    Pick a provider and paste the key. For a self-hosted model, add the base URL as well.

  3. “Verbindung testen und speichern” (test and save)

    The key is verified and then stored encrypted. It cannot be read back — not even by an administrator.

  4. Select a model

    Once the connection stands, you can choose the specific model offered by that provider.

What the choice means for your data

A self-hosted model behind the OpenAI-compatible option keeps conversations on your own network too. With a hosted provider they leave the installation; everything else stays inside either way.

Signing in with your own Claude account

Instead of one shared key for the installation, each user can sign in with their own Claude account. The agent then runs in an isolated environment per request, and the gates remain fully in force — rights still come from Keycloak, not from the model account.

When the chat stays silent

  • “No backend configured” — the expected state before setup, not an error.
  • The connection test fails: with a self-hosted model, check the base URL and the egress guard first — an allowlist that does not name the target host blocks the call.
  • Answers arrive but data is missing: that is not the model but your rights. The agent sees only what your identity may see in Trino.

Applies to: This page describes lavalake 0.16.0. Product and documentation live in separate repositories — when in doubt, what the console shows is authoritative.

Something missing?

If these pages do not answer your question, we will walk through the platform against your own case in half an hour.

Book a demo