42 lines
848 B
Markdown
42 lines
848 B
Markdown
# Homelab Deployment
|
|
|
|
## Overview
|
|
|
|
NexusAI is distributed across three nodes. Each node runs only the
|
|
services appropriate for its hardware.
|
|
|
|
## Mini PC 1 — 192.168.0.81
|
|
|
|
Runs: Qdrant, Memory Service, Embedding Service
|
|
```bash
|
|
ssh username@192.168.0.81
|
|
cd ~/nexusai
|
|
docker compose -f docker-compose.mini1.yml up -d # Qdrant
|
|
npm run memory
|
|
npm run embedding
|
|
```
|
|
|
|
## Mini PC 2 — 192.168.0.205
|
|
|
|
Runs: Gitea, Orchestration Service
|
|
```bash
|
|
ssh username@192.168.0.205
|
|
cd ~/gitea
|
|
docker compose up -d # Gitea
|
|
cd ~/nexusai
|
|
npm run orchestration
|
|
```
|
|
|
|
## Main PC
|
|
|
|
Runs: Ollama, Inference Service
|
|
```bash
|
|
ollama serve
|
|
npm run inference
|
|
```
|
|
|
|
## Environment Files
|
|
|
|
Each node needs a `.env` file in the relevant service package directory.
|
|
These are not committed to git. See each service's documentation for
|
|
required variables. |