# Purpose: the settings compose.yaml, litellm-config.yaml, llama-swap.yaml and the native
#          start script all read. Copy this file to `.env` beside compose.yaml and fill in
#          the lines that are empty. Nothing here is a secret except the two keys, which
#          you generate rather than copy.
# Platform: all
# Minimum memory: 8 GB
# Assumes: `cp env-example.txt .env` and then an editor. Docker Compose reads `.env`
#          automatically from the directory you run it in; the native start script reads
#          it with `set -a; . ./.env; set +a`.

# ---------------------------------------------------------------- where things listen
# The gateway is the only thing anything else talks to. Keep it on the loopback address
# until Part 23 puts authentication and TLS in front of it properly.
GATEWAY_HOST=127.0.0.1
GATEWAY_PORT=4000

# llama-swap's own port. Nothing outside this stack should need it; it is published only
# so you can look at its web page while you are setting the gateway up.
SWAP_HOST=127.0.0.1
SWAP_PORT=9292

# ------------------------------------------------------------------------ your models
# Absolute path to the model library you built in Part 4. llama-swap reads GGUF files
# from here; the container path mounts it read-only.
MODELS_DIR=

# Absolute path to the llama-server binary, for the native path only. The container image
# brings its own. Leave it empty if you are using Compose.
LLAMA_BIN=

# ------------------------------------------------------------------------------- keys
# Generate with: openssl rand -hex 24
# The proxy admin key. It must begin with sk-, so write it as sk-<the hex you generated>.
# It is the key that creates other keys; it is not the key your applications should use.
LITELLM_MASTER_KEY=

# Generate with: openssl rand -hex 24
# Used to encrypt stored credentials. Changing it invalidates what is already stored.
LITELLM_SALT_KEY=

# The key the gateway presents to llama-swap, if you set one there. Leave it empty when
# llama-swap is only reachable from inside the stack, which is the default here.
LOCAL_API_KEY=

# ------------------------------------------------------------------- the spend database
# Virtual keys and usage records need a database. These values are read only by the
# container path; the native path runs without a database and the page says what you
# lose. Generate the password with: openssl rand -hex 16
GATEWAY_DB_USER=gateway
GATEWAY_DB_PASSWORD=
GATEWAY_DB_NAME=gateway

# ---------------------------------------------------------------------------- images
# llama-swap publishes one image with several tags. Pick the one for your accelerator:
#   unified-cuda13   multi-architecture, NVIDIA Ampere through Blackwell  (Tracks S and N)
#   unified-cuda     amd64 only, older NVIDIA Pascal through Ada          (Track N)
#   unified-vulkan   amd64, AMD and other Vulkan-capable GPUs             (Track X)
LLAMA_SWAP_IMAGE=ghcr.io/mostlygeek/llama-swap:unified-cuda13

# LiteLLM's deployment page says to pin a version tag rather than a moving one so that
# rollbacks are deterministic. This course pins LiteLLM 1.100.0; confirm the tag exists
# on the registry before your first run, and change it here rather than in compose.yaml.
LITELLM_IMAGE=ghcr.io/berriai/litellm:v1.100.0

POSTGRES_IMAGE=postgres:17-alpine