Image description, OCR, and screen capture

arka describe photo.jpg
arka describe ~/Downloads/chart.png

DESCRIBE_IMAGE_BACKEND=auto   # auto | gemini | ollama | vllm
GEMINI_API_KEY=...
# DESCRIBE_IMAGE_TWO_LAYER=1
# DESCRIBE_IMAGE_OCR=1

pip install "arka-agent[vision]"
brew install tesseract    # OCR layer

arka analyze plan.pdf "extract door schedule and room dimensions"
arka analyze --pages 1-3 specs.pdf "summarize payment terms"

pip install "arka-agent[drawings]"

# DRAWING_MODEL=gemini-2.5-flash
# DRAWING_MAX_PAGES=8

arka describe screen
arka describe my screen
arka describe screen "what app is in focus"

arka describe_video demo.mp4
arka describe_video demo.mp4 "find visual glitches and confusing UI states"
arka "describe video gameplay.mp4"
arka "who is in meeting.mp4 and where are they"

brew install ffmpeg
pip install "arka-agent[vision]"