# Copy to .env and adjust. 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
LLAMA_GPU_LAYERS=999
# 65536 (64K) fits comfortably in 32GB VRAM alongside the model weights.
# Raise toward 131072 if you need more context; see docs/research/qwen3.8-27b-quant.md
# for the VRAM math at larger context sizes.
LLAMA_CTX_SIZE=65536

# --- Open WebUI ---
WEBUI_PORT=8008
# Required — create an "openwebui" virtual key in LiteLLM's Admin UI first
# (see docs/proxy-key-onboarding.md), then paste it here.
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) ---
# Required — the litellm container can't resolve search.home's LAN mDNS
# name on its own; this becomes an extra_hosts entry. Use a static
# DHCP-reserved IP so it doesn't drift.
SEARXNG_LAN_IP=

# --- LiteLLM proxy (see docs/proxy-key-onboarding.md, docs/network-access.md) ---
LITELLM_PORT=4000
# Required — generate real random values before first run, e.g. `openssl rand -hex 32`.
# LITELLM_SALT_KEY encrypts stored data; do not change it after the first run
# (existing encrypted data becomes unreadable if you do).
# Required — generate a real random value before first run, e.g. `openssl rand -hex 32`.
LITELLM_MASTER_KEY=
LITELLM_SALT_KEY=
LITELLM_DB_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_USERNAME=admin
UI_PASSWORD=

# --- Knowledgebase (pgvector + memory-retrieval, see docs/memory-knowledgebase.md) ---
# Required — random values, e.g. `openssl rand -hex 32`.
PGVECTOR_DB_PASSWORD=
# Auth key memory-retrieval requires on its own API (its SERVER_API_KEY).
MEMORY_RETRIEVAL_API_KEY=
# A virtual key memory-retrieval uses to call back into litellm for
# embeddings — create it in the Admin UI like any other workload key
# (see docs/proxy-key-onboarding.md), name it "memory-retrieval".
MEMORY_RETRIEVAL_EMBEDDING_KEY=