38 lines
1.0 KiB
Plaintext
38 lines
1.0 KiB
Plaintext
# Example env file — copy to .env and fill real values (DO NOT COMMIT .env)
|
|
# Generate a secure API key: `openssl rand -hex 32` or `python -c "import secrets;print(secrets.token_urlsafe(32))"`
|
|
|
|
# Gateway
|
|
API_KEY=change-me-to-a-strong-random-value
|
|
CLIP_URL=http://clip:8000
|
|
BLIP_URL=http://blip:8000
|
|
YOLO_URL=http://yolo:8000
|
|
QDRANT_SVC_URL=http://qdrant-svc:8000
|
|
LLM_URL=http://llm:8080
|
|
LLM_ENABLED=false
|
|
LLM_TIMEOUT=120
|
|
LLM_DEFAULT_MODEL=qwen3-1.7b-instruct-q4_k_m
|
|
LLM_MAX_TOKENS_DEFAULT=256
|
|
LLM_MAX_TOKENS_HARD_LIMIT=1024
|
|
LLM_MAX_REQUEST_BYTES=65536
|
|
|
|
# HuggingFace token for private/gated models (optional). Leave empty if unused.
|
|
# Never commit a real token to this file.
|
|
HUGGINGFACE_TOKEN=
|
|
|
|
# Qdrant wrapper (qdrant-svc)
|
|
QDRANT_HOST=qdrant
|
|
QDRANT_PORT=6333
|
|
COLLECTION_NAME=images
|
|
VECTOR_DIM=512
|
|
|
|
# Gateway runtime
|
|
VISION_TIMEOUT=300
|
|
MAX_IMAGE_BYTES=52428800
|
|
|
|
# Local llama.cpp LLM service (only needed when you run the llm profile locally)
|
|
MODEL_PATH=/models/Qwen3-1.7B-Instruct-Q4_K_M.gguf
|
|
LLM_CONTEXT_SIZE=4096
|
|
LLM_THREADS=4
|
|
LLM_GPU_LAYERS=0
|
|
LLM_EXTRA_ARGS=
|