# Infinity stack tunables. Copy this to `.env` on the server before deploying.
#
#   cp .env.example .env
#   # edit .env with real values
#   docker compose up -d

# Image version — pin for reproducibility (`latest` for edge)
INFINITY_VERSION=latest

# Port exposed on host
INFINITY_PORT=7997

# GPU assignment (ana-ml2 has 0 and 1; default 1 keeps 0 free for heavy LLM work)
GPU_ID=1

# Models — both served simultaneously; reference by the full repo name in requests
EMBED_MODEL=Qwen/Qwen3-Embedding-0.6B
RERANK_MODEL=Qwen/Qwen3-Reranker-0.6B

# Inference engine: torch (widest support) or optimum (ONNX, sometimes faster)
ENGINE=torch

# Batch size — 32 is a safe default; bump for throughput if VRAM allows
BATCH_SIZE=32

# Optional API key — leave blank for no auth (fine on the internal network)
API_KEY=

# HuggingFace token — only needed for gated models
HF_TOKEN=