Velaxe
AI Hub — Unified LLM Gateway, Chat, Embeddings & Jobs | Velaxe

AI Hub

Connect LLM providers & save workspace credentials

Use the Admin API to store API keys in the per-workspace KeyVault.

10 min Beginner Admin Updated Sep 19, 2025
Provider Keys screen
Encrypt & store provider credentials

Overview

Use the Admin API to store API keys in the per-workspace KeyVault.

Prerequisites

  • Workspace admin access with permission ai.configure
  • Valid API keys for one or more providers (OpenAI, Anthropic, Gemini, Mistral, Hugging Face)

Permissions required

ai.configure

Steps (3)

Estimated: 10 min
  1. 1

    Open Provider Keys

    Admin 2 min Back to top

    From AI Hub, choose “Provider Keys”. Or call GET /AdminApi.php?provider=openai to check existing credentials.

    Tips

    Validation

    • If GET returns {"ok":true,"creds":{…}}, the vault is reachable.

    Success criteria

  2. 2

    Save credentials to KeyVault

    Admin 5 min Back to top

    POST /AdminApi.php with {"provider":"openai","creds":{"api_key":"sk-…"}}. Repeat for other providers as needed.

    Tips

    Validation

    Success criteria

    • Admin API returns {"ok":true}.
  3. 3

    Verify encryption & rotation

    Admin 3 min Back to top

    Ensure AI_KEYRING_SECRET is set for AES-256-GCM. For rotations, provide comma-separated secrets; old keys remain valid for decrypt.

    Tips

    • Keep the old secret to the right of the comma until all creds are verified with the new key.

    Validation

    Success criteria

About this guide

AI Hub centralizes generative AI for your workspace with a single, policy-aware gateway to multiple providers. Teams get a streamlined chat experience with searchable history and feedback, a minimal Query API for quick prompts, and embeddings for retrieval workflows. Operators gain visibility with usage & cost tracking, quotas, and exportable audit logs.

Choose the best model for each task, fail over between providers, and moderate inputs/outputs with block/warn/allow policies. Keys are encrypted at rest and scoped per workspace. Long-running tasks run on a background worker and broadcast events so other apps can react in real time.

Designed for safety and speed: opinionated defaults, least-privilege access, and drop-in APIs that make it easy to bring AI to every surface of Velaxe.