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

AI Hub

Enable Redis memo-cache to cut latency & cost

Cache deterministic prompts for 24h using Redis or an in-memory stub.

6 min Beginner Developer, Ops Updated Sep 19, 2025
View App All Guides

Overview

Cache deterministic prompts for 24h using Redis or an in-memory stub.

Prerequisites

  • Optional Redis endpoint; otherwise stub will be used

Permissions required

ai.backend.call

Steps (2)

Estimated: 6 min
  1. 1

    Configure Redis (optional)

    Ops 3 min Back to top

    Provide env vars and ensure ping succeeds. AI Hub will use setex(key, 86400, …).

    Tips

    —

    Validation

    —

    Success criteria

    —

  2. 2

    Verify cache hits

    Developer 3 min Back to top

    Repeat the same provider+model+prompt; expect a fast response and unchanged content/usage.

    Tips

    —

    Validation

    —

    Success criteria

    • Hit rate improves; token usage drops for repeated prompts.

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.