# Purpose: the settings compose.yaml, its overrides and caddy.conf read. Copy this file to
#          .env beside compose.yaml and fill in the lines that are empty. Nothing here is a
#          secret except WEBUI_SECRET_KEY, which you generate rather than copy.
# Platform: all (Track M reads CHAT_HOST, LAN_IP, WEBUI_SECRET_KEY and the WEBUI_ADMIN_ lines)
# Minimum memory: 8 GB
# Assumes: `cp env-example.txt .env` and then an editor. Docker Compose reads .env from
#          the directory you run it in. Values are literal: no ~, no $HOME, no quotes.

# Which Compose files every `docker compose` command in this directory uses, joined by
# colons. Pick the line for your track and engine; leave the others commented out.
# Track S or N, Ollama:
#COMPOSE_FILE=compose.yaml:compose-nvidia.yaml
# Track X, Ollama:
#COMPOSE_FILE=compose.yaml:compose-amd.yaml
# Track S or N, llama-server:
#COMPOSE_FILE=compose.yaml:compose-nvidia.yaml:compose-llama-server.yaml
# Track X, llama-server:
#COMPOSE_FILE=compose.yaml:compose-amd.yaml:compose-llama-server.yaml

# The name you will type into a browser. Anything under .home.arpa is reserved by RFC 8375
# for names that mean something inside one home network and nothing outside it.
CHAT_HOST=chat.home.arpa

# This machine's address on your home network, and nothing else. Find it with
# `ip -4 -brief addr show scope global` on Linux or `ipconfig getifaddr en0` on macOS.
# Compose refuses to start while this is empty.
LAN_IP=

# Generate with: openssl rand -hex 32
# Signs login tokens. Changing it logs everyone out; losing it is not fatal.
WEBUI_SECRET_KEY=

# The administrator, created on the front-end's first start before it accepts any
# connection. The address is only a login name; nothing is sent to it. Generate a
# temporary password with `openssl rand -base64 18`, change it in the web interface
# after the first sign-in, then delete the WEBUI_ADMIN_PASSWORD line (task 7).
WEBUI_ADMIN_NAME=Admin
WEBUI_ADMIN_EMAIL=
WEBUI_ADMIN_PASSWORD=

# Context length the engine allocates per conversation slot, in tokens. The reality check
# after this lab is how you choose your own number.
OLLAMA_CONTEXT_LENGTH=8192

# Conversations the engine processes at the same time. On Ollama each one gets its own
# OLLAMA_CONTEXT_LENGTH of key-value cache, so 2 costs twice the cache memory of 1.
# On the llama-server path (compose-llama-server.yaml) the context is divided among the
# slots instead, so memory stays the same and each slot gets
# OLLAMA_CONTEXT_LENGTH / OLLAMA_NUM_PARALLEL tokens.
OLLAMA_NUM_PARALLEL=1

# How long a model stays in memory after the last request (Ollama only; llama-server
# keeps its one model loaded for as long as it runs). The Ollama default is 5m.
OLLAMA_KEEP_ALIVE=30m

# llama-server only (compose-llama-server.yaml). Image tags checked on 2026-09-13; the
# b10868 images were built on 2026-09-09. Pick one:
#   Track S (arm64, CUDA 13):                ghcr.io/ggml-org/llama.cpp:server-cuda13-b10868
#   Track N, driver supports CUDA 13:        ghcr.io/ggml-org/llama.cpp:server-cuda13-b10868
#   Track N, driver supports CUDA 12 only:   ghcr.io/ggml-org/llama.cpp:server-cuda-b10868
#   Track X, Vulkan (the course default):    ghcr.io/ggml-org/llama.cpp:server-vulkan-b10868
LLAMA_SERVER_IMAGE=
# Absolute path of your model library, for example /home/you/models
MODELS_DIR=
# Path of the GGUF file inside MODELS_DIR
LLAMA_MODEL_FILE=unsloth/Qwen3-4B-GGUF/Qwen3-4B-Q4_K_M.gguf
# The model name the front-end will list
LLAMA_MODEL_ALIAS=qwen3-4b