.env.example

# Copy this file to ".env" and adjust as needed. All values are optional —
# DocuMaker falls back to sensible defaults. HF_TOKEN is also read from your
# environment (HF_TOKEN / HUGGINGFACEHUB_API_TOKEN) if not set here.

# HuggingFace token — https://huggingface.co/settings/tokens
# NOTE: the Gradio app takes your token from its UI field, NOT from here.
# This is only used by the headless smoke test (scripts/smoke_test.py) / CLI.
HF_TOKEN=

# --- Text LLM (HuggingFace Inference API) ---
# Any instruct model available via HF Inference Providers. Swap if a model is
# unavailable on the free tier. Good options: Qwen/Qwen2.5-7B-Instruct,
# meta-llama/Llama-3.1-8B-Instruct, mistralai/Mistral-7B-Instruct-v0.3
DOCUMAKER_LLM_MODEL=Qwen/Qwen2.5-7B-Instruct
# DOCUMAKER_LLM_PROVIDER=          # e.g. hf-inference, together, novita (blank = auto)
DOCUMAKER_LLM_MAX_TOKENS=2048
DOCUMAKER_LLM_TEMPERATURE=0.3

# --- Vision LLM (HuggingFace Inference API) ---
DOCUMAKER_VLM_MODEL=Qwen/Qwen2-VL-7B-Instruct
DOCUMAKER_ENABLE_VISION=1          # set 0 to skip captioning entirely
# DOCUMAKER_VLM_PROVIDER=
# DOCUMAKER_LOCAL_CAPTION_MODEL=Salesforce/blip-image-captioning-base

# --- Whisper (local faster-whisper) ---
DOCUMAKER_WHISPER_MODEL=small      # tiny | base | small | medium | large-v3
DOCUMAKER_WHISPER_DEVICE=auto      # auto | cuda | cpu
# DOCUMAKER_WHISPER_COMPUTE_TYPE=  # blank = auto; e.g. int8_float16, int8, float16

# --- Frame extraction ---
DOCUMAKER_SCENE_THRESHOLD=27.0     # lower = more scenes detected
DOCUMAKER_DEDUP_HASH_DISTANCE=6    # higher = more aggressive dedup

# --- Output ---
DOCUMAKER_DOCX_IMAGE_WIDTH_INCHES=5.5