> ## Documentation Index
> Fetch the complete documentation index at: https://docs.quackai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Self-Hosting

> Host your Quack suite on your own

## Backend API

### Prerequisites

Whatever your installation method, you'll need at least the following to be installed:

1. [Docker](https://docs.docker.com/engine/install/) (and [Docker compose](https://docs.docker.com/compose/) if you're using an old version)
2. [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) and a GPU

*We recommend min 5Gb of VRAM on your GPU for good performance/latency balance. Please note that by default, this will run your LLM locally (available offline) but if you don't have a GPU, you can use online LLM providers (currently supported: Groq, OpenAI)*

### 60 seconds setup ⏱️

This method is easier for you to try it out locally. Follow the instructions over [here](https://github.com/quack-ai/companion#get-started-).

### Production setup

This method is more adequate if you have an isolated/remote environment where you don't necessarily want Git to interfere.
You'll need to own a domain name with the default configuration (e.g. "mydomain.nom")

<Steps>
  <Step title="Create a `.env` file">
    Save this [example file](https://raw.githubusercontent.com/quack-ai/companion/main/.env.example) and name it `.env`.
  </Step>

  <Step title="Edit your environment variables">
    Edit your `.env` and replace the following values:

    * `SUPERADMIN_GH_PAT`: your Github user Personal Access Token to authenticate you as the admin. Head over to your [Developer settings](https://github.com/settings/tokens?type=beta) on GitHub, and "Generate new token",
      pick a name and an expiration and confirm with "Generate token" *(no need for extra permissions i.e. read-only)*
    * pick secure passwords for `POSTGRES_PASSWORD`, `SUPERADMIN_PWD`, `GF_ADMIN_PWD`
    * `ACME_EMAIL`: the email linked to your certificate for HTTPS
    * `POSTGRES_HOST` & `POSTGRES_PORT`: the host and port of your remote PostgreSQL database service.
    * `BACKEND_HOST`: the subdomain where your users will access your API (e.g "api.mydomain.com")

    If you want to edit other aspects, check the [env variable description](https://github.com/quack-ai/companion/blob/main/CONTRIBUTING.md#environment-configuration).
  </Step>

  <Step title="Define a Docker orchestration">
    Save this [docker compose configuration](https://raw.githubusercontent.com/quack-ai/companion/main/docker-compose.prod.yml) and name it `docker-compose.yml`.
    You can comment the `deploy` section of the ollama service if you wish to use your CPU to run the LLM instead.
  </Step>

  <Step title="Setting the certificate access permission">
    Before starting our docker setup, we need to make sure your ACME certificate will be readable:

    ```shell
    touch acme.json
    sudo chmod 600 acme.json
    ```
  </Step>

  <Step title="Run the service">
    You should now have two files (`.env`, `docker-compose.yml`) in your folder. Time to start the services:

    ```shell
    docker compose up -d --wait ollama backend traefik
    ```
  </Step>
</Steps>

## Using your API

Bravo, you now have a full running service!
You can now start your [VSCode extension](https://marketplace.visualstudio.com/items?itemName=quackai.quack-companion), open the command palette and look for "Quack Companion: Set API endpoint" where you'll need to paste the URL to the API endpoint.

## Additional options

There are additional options to customize your service, here are a few:

<Card title="Database hosting" icon="database">
  Instead of hosting your PostgreSQL database locally or self-hosted, you can use hosting services like [Supabase](https://supabase.com/). You only need to replace the values of `POSTGRES_HOST` & `POSTGRES_PORT` in your `.env` file.
</Card>

<Card title="LLM selection" icon="laptop-code">
  We use [Ollama](https://ollama.ai/) to serve LLMs. Edit `OLLAMA_MODEL` to use other models from the [hub](https://ollama.com/library).
  For a good performance/latency balance, we recommend you use one of the following models: `dolphin-mistral:7b-v2.6-dpo-laser-q4_K_M`, `deepseek-coder:6.7b-instruct-q4_K_M`.
  Please don't pick oversized hardware or models for your needs, to preserve both your hardware life expectancy and your energy bills 💚
</Card>

<Card title="Application performance monitoring" icon="chart-simple">
  When you start running your service at high workload, you might want to monitor its performances. You'll find additional service in your docker compose using [Prometheus](https://prometheus.io/) & [Grafana](https://grafana.com/) to give you a proper APM dashboard.
</Card>