# Copy to .env and adjust — or just run ./scripts/update.sh, which creates
# .env from this file and fills in every secret/key below it can generate
# itself (see each var's comment). All values below are defaults baked into
# docker-compose.yml — only uncomment/change what you actually want to
# override.

# --- llama.cpp / model ---
LLAMA_MODEL_FILE=Qwen3.8-27B-UD-Q4_K_XL.gguf
# 999 = every layer on GPU (this model is dense, not MoE, and already fits
# fully in 32GB VRAM — see docs/research/qwen3.8-27b-quant.md). Lower this
# to leave that many fewer layers on GPU and push the rest to CPU/system RAM
# if something else is contending for VRAM — llama.cpp has no separate
# "RAM offload" flag, --n-gpu-layers *is* the RAM-offload knob for a dense
# model. Don't reach for --n-cpu-moe/--cpu-moe/--override-tensor "exps" —
# those target Mixture-of-Experts models (e.g. Qwen3.8-2.4T-A95B), not this
# one, and are no-ops here.
# There's no separate "then SSD" tier to enable either: llama.cpp mmaps the
# model file by default (no --no-mmap here), so if GPU+RAM ever can't hold
# the working set, the OS pages the rest in from disk automatically — an
# implicit, slow last resort, not a config knob. An explicit tiered SSD
# offload has been an open llama.cpp feature request since 2025 (still
# unimplemented): https://github.com/ggml-org/llama.cpp/discussions/12507
LLAMA_GPU_LAYERS=999
# 131072 (128K): ~25.6GB (17.6GB weights + ~8GB KV cache) on the 32GB
# R9700, ~6GB headroom — see docs/research/qwen3.8-27b-quant.md for the full
# table (64K only used ~19.6GB/~12GB headroom, but real usage was burning
# through 64K fast). If headroom gets tight, quantize the KV cache instead
# of dropping context: --cache-type-k/v q8_0 roughly halves it.
LLAMA_CTX_SIZE=131072

# --- Open WebUI ---
WEBUI_PORT=8008
# Minted automatically by ./scripts/update.sh — leave blank. Manual fallback:
# docs/proxy-key-onboarding.md.
OPENWEBUI_LITELLM_KEY=

# --- Lazytainer ---
# Seconds of inactivity before llama-server is stopped. 900 = 15 min.
LAZYTAINER_INACTIVE_TIMEOUT=900

# --- Embedding model (knowledgebase, see docs/memory-knowledgebase.md) ---
EMBEDDING_MODEL_FILE=nomic-embed-text-v1.5.Q8_0.gguf

# --- SearXNG web search (see docs/research/litellm-searxng-search.md) ---
# Resolved automatically by ./scripts/update.sh from search.home on this
# host — leave blank. Only set by hand if that resolution fails (e.g.
# search.home isn't a static DHCP reservation and its IP drifted).
SEARXNG_LAN_IP=

# --- LiteLLM proxy (see docs/proxy-key-onboarding.md, docs/network-access.md) ---
LITELLM_PORT=4000
# Random values, filled in automatically by ./scripts/update.sh — leave
# blank. LITELLM_SALT_KEY encrypts stored data; do not change it after the
# first run (existing encrypted data becomes unreadable if you do).
LITELLM_MASTER_KEY=
LITELLM_SALT_KEY=
LITELLM_DB_PASSWORD=
# Backs litellm's router state/rate-limits/budgets/cache invalidation
# (the redis service). Random value, filled in automatically — leave blank.
REDIS_PASSWORD=
# Admin UI login (https://<proxy>/ui). Without these, LiteLLM falls back to
# username "admin" / password = LITELLM_MASTER_KEY — set these instead so the
# master key never has to be typed into the browser. UI_PASSWORD is filled
# in automatically by ./scripts/update.sh if blank.
UI_USERNAME=admin
UI_PASSWORD=

# --- Knowledgebase (pgvector + litellm-pgvector, see docs/memory-knowledgebase.md) ---
# Random value, filled in automatically by ./scripts/update.sh — leave blank.
PGVECTOR_DB_PASSWORD=
# Auth key litellm-pgvector requires on its own API (its SERVER_API_KEY).
# Random value, filled in automatically by ./scripts/update.sh — leave blank.
LITELLM_PGVECTOR_API_KEY=
# A virtual key litellm-pgvector uses to call back into litellm for
# embeddings. Minted automatically by ./scripts/update.sh — leave blank.
# Manual fallback: docs/proxy-key-onboarding.md.
LITELLM_PGVECTOR_EMBEDDING_KEY=