Sovnex
Install Guide

Install Sovnex in 3 steps

Copy-paste three commands on your computer or server. No tech skills needed — just follow along.

Download Install Open browser
🖥️
Mac or Linuxa computer/server
🧠
16GB+ RAMdisk 50GB+
🌐
Internetto download
0

Install these first (one time)

Sovnex runs on Docker. Set up what your system needs below and keep them running. Already have them? Skip this.

🍎 macOS

1. Docker Desktop — download, install and open it (the whale icon in the menu bar means it's ready).

docker.com/products/docker-desktop ↗

2. Ollama — the local AI engine. Download the app, install and open it (it sits in the menu bar); Sovnex connects to it automatically. Skipped it? The installer offers to install it with Homebrew and start it — without Homebrew you have to install it yourself.

ollama.com/download ↗
🐧 Linux

Paste this to auto-install Docker (needs sudo):

linux
$ curl -fsSL https://get.docker.com | sh
$ sudo systemctl enable --now docker

Ollama needs nothing here — the installer sets the local AI engine up inside Docker (uses your NVIDIA GPU if present, otherwise the CPU). On very large NVIDIA servers it runs vLLM instead and creates no Ollama container.

💡

Linux shortcut: you can skip Docker here and go to step 2 — ./install.sh will offer to install Docker for you (also needs sudo).

1

Download the installer

Open your Terminal, paste and run this — it downloads and unpacks automatically.

terminal
$ curl -fsSL https://download.sovnexai.com/sovnex-install.tar.gz | tar xz
$ cd sovnex-install
🐧

Linux users only — run this one line first (else the search engine won't start). Mac users skip it:

linux only
$ sudo sysctl -w vm.max_map_count=262144
2

Run the installer

One command does the rest — it configures, downloads and starts everything, including a few-GB local AI model. Grab a coffee for 10–20 min; it tells you how to open it when done.

terminal
$ ./install.sh
  ==> checking… generating secrets… pulling… starting… ✅ Sovnex is up.
🔐

If your vendor uses private images, run docker login once before this. Everything else is automatic — no config to edit.

🔑

Write down the admin login it prints at the endadmin@sovnex.io and a password generated for this install (also in .env as DEFAULT_SUPERUSER_PASSWORD). There is no factory default password any more.

3

Open browser · Activate

Open the Admin console in your browser and sign in with the login the installer printed → License. Click Purchase a plan and pay: your deployment activates by itself in about 30 seconds. Already have an activation code from your vendor? Paste it under Activate online instead.

browser
# Admin console (replace localhost with server IP)
http://localhost/admin  →  License
👉

Next: connect the built-in API gateway to your local AI engine and add a model provider — the Getting started guide walks you through it.

Optional, NVIDIA servers running vLLM: a rerank model makes retrieval find answers the wording missed — worth it when your questions and your documents are in different languages. It is not started by the installer. From the install folder: docker compose -p sovnex-vllm -f docker-compose-vllm.yml --profile rerank up -d vllm-rerank, then add it in the app under Model providers → VLLM, type Rerank, base URL http://vllm-rerank:8000/v1.

🎉 All set! Here's how to open it

Sovnex
http://<host>
main app — build a knowledge base
Admin
http://<host>/admin
admin · license activation
📍

<host> = localhost on this machine; use the server's IP or domain for remote access.

Everyday commands

stop./install.sh down
start./install.sh up
status./install.sh status
logs./install.sh logs
upgrade./install.sh upgrade

Something wrong?

pull faileddocker login
port in useedit .env
not up./install.sh logs
elseask your vendor