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

AI Hub

Configure input/output moderation policy

Choose enforcement mode and audit outcomes.

7 min Beginner Admin, Compliance Updated Sep 19, 2025
View App All Guides

Overview

Choose enforcement mode and audit outcomes.

Prerequisites

  • OpenAI moderation key present (optional but recommended)

Permissions required

ai.configure

Steps (2)

Estimated: 7 min
  1. 1

    Pick enforcement mode

    Admin 3 min Back to top

    Set AiPolicy.moderation_mode to block, warn, or allow (via admin tool or PolicyStore::set()).

    Tips

    —

    Validation

    —

    Success criteria

    —

  2. 2

    Review audit logs

    Compliance 4 min Back to top

    Moderation outcomes are recorded in AiAudit. Use CSV export to review.

    Tips

    —

    Validation

    —

    Success criteria

    • New entries appear when flagged content is processed.

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.