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

AI Hub

Start a chat and store searchable history

Use Chat API to create threads, add messages, search FTS, rate replies, and fork conversations.

12 min Beginner End-user, Support, Product Updated Sep 19, 2025
View App All Guides
Chat UI
Chat UI with memory & ratings

Overview

Use Chat API to create threads, add messages, search FTS, rate replies, and fork conversations.

Prerequisites

  • Permission ai.chat.use in the active workspace

Permissions required

ai.chat.use

Steps (4)

Estimated: 12 min
  1. 1

    Create or open a conversation

    User 3 min Back to top

    POST /ChatApi.php with {"title":"Notes","provider":"openai"} to create; GET /ChatApi.php to list.

    Tips

    —

    Validation

    • Response includes {"ok":true,"conv_id":N}.

    Success criteria

    —

  2. 2

    Add a user message

    User 2 min Back to top

    POST /ChatApi.php with {"conv_id":N,"role":"user","content":"Summarise this…"}

    Tips

    —

    Validation

    —

    Success criteria

    —

  3. 3

    Fetch thread or search history

    User 3 min Back to top

    GET /ChatApi.php?conv=N for the thread; GET /ChatApi.php?search=keywords for FTS previews.

    Tips

    —

    Validation

    —

    Success criteria

    —

  4. 4

    Rate & fork

    User 4 min Back to top

    PATCH /ChatApi.php with {"rate":1,"conv_id":N,"delta":D} for 👍 (−1 for 👎). {"fork":N} clones the conversation.

    Tips

    —

    Validation

    —

    Success criteria

    • Ratings stored; fork returns new conv_id.

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.