Prerequisites
Prepare the target server before enabling Easy8 AI.
Base requirements
- Linux server with Docker Engine installed
- Docker Compose plugin available as
docker compose - persistent Docker storage for service data
- Nginx or another reverse proxy in front of Easy8
- enough CPU, RAM, and disk space for the selected product tier
Network requirements
The server must allow:
- browser access to Easy8 through HTTPS
- reverse proxy access to the
chainservice on the host - internal communication between
app,chain,celery,redis, and optionallychroma
If cloud AI is used, the server must also allow outbound access to the configured provider:
- OpenAI
- Azure OpenAI
If self-hosted AI is used, the server must allow outbound or internal access to:
- the local LLM endpoint configured through
LLM_URL - the local embeddings endpoint configured through
EMBEDDINGS_URLwhen Pro products are used
Product-specific runtime requirements
Easy8 AI Basic
Required services:
chaincelery- LLM provider
Not required:
chroma- embeddings service
Easy8 AI Knowledge assistant PRO / Easy8 AI Helpdesk
Required services:
chaincelerychroma- embeddings provider
- LLM provider
Self-hosted AI requirements
If the customer hosts LLMs or embeddings locally, also prepare:
- NVIDIA GPU server when the chosen model requires GPU acceleration
- NVIDIA drivers
- NVIDIA container runtime
- enough GPU memory for the selected model
For self-hosted embeddings with BAAI/bge-m3 served through TEI:
- only NVIDIA GPU deployment is supported
- minimum supported GPU memory is
8 GB VRAM - CPU-only deployment is not supported
16 GB VRAMor more is recommended for faster indexing and higher throughput
For current self-hosted infrastructure guidance, see: