pip install --upgrade potato-annotation

pip install ultralytics opencv-python

annotation_task_name: "Object Detection with YOLO"
 
data_files:
  - data/images.json
 
item_properties:
  id_key: id
  text_key: image_url
 
instance_display:
  fields:
    - key: image_url
      type: image
      display_options:
        max_width: 800
        zoomable: true
 
annotation_schemes:
  - annotation_type: image_annotation
    name: objects
    description: "Detect and label objects"
    source_field: "image_url"
    tools:
      - bbox
    labels:
      - name: "person"
        color: "#FF6B6B"
      - name: "car"
        color: "#4ECDC4"
      - name: "dog"
        color: "#45B7D1"
      - name: "cat"
        color: "#96CEB4"
 
    ai_support:
      enabled: true
      features:
        detection: true
        pre_annotate: true
        hint: true
 
ai_support:
  enabled: true
  endpoint_type: "yolo"
  ai_config:
    model: "yolov8m.pt"
    confidence_threshold: 0.5
    iou_threshold: 0.45
 
output_annotation_dir: "annotation_output/"
user_config:
  allow_all_users: true

{"id": "img_001", "image_url": "images/street_scene_1.jpg"}
{"id": "img_002", "image_url": "images/park_photo.jpg"}
{"id": "img_003", "image_url": "https://example.com/images/office.jpg"}

ai_config:
  model: "yolo-world"
  confidence_threshold: 0.3

ai_config:
  confidence_threshold: 0.3  # More detections, more false positives

ai_config:
  confidence_threshold: 0.7  # Fewer detections, higher precision

# Install Ollama
curl -fsSL https://ollama.ai/install.sh | sh
 
# Pull a vision model
ollama pull llava
 
# Or for better performance:
ollama pull qwen2.5-vl:7b

annotation_task_name: "Image Classification with Ollama Vision"
 
data_files:
  - data/images.json
 
item_properties:
  id_key: id
  text_key: image_url
 
instance_display:
  fields:
    - key: image_url
      type: image
      display_options:
        max_width: 600
        zoomable: true
 
annotation_schemes:
  - annotation_type: radio
    name: scene_type
    description: "What type of scene is shown?"
    labels:
      - indoor
      - outdoor_urban
      - outdoor_nature
      - aerial
      - underwater
 
    ai_support:
      enabled: true
      features:
        hint: true
        classification: true
 
ai_support:
  enabled: true
  endpoint_type: "ollama_vision"
  ai_config:
    model: "llava:latest"
    base_url: "http://localhost:11434"
    max_tokens: 500
    temperature: 0.1
 
output_annotation_dir: "annotation_output/"
user_config:
  allow_all_users: true

ai_support:
  enabled: true
  endpoint_type: "openai_vision"
  ai_config:
    api_key: "${OPENAI_API_KEY}"
    model: "gpt-4o"
    max_tokens: 1000
    detail: "auto"  # "low" for faster/cheaper, "high" for detail

export OPENAI_API_KEY="sk-..."

ai_support:
  enabled: true
  endpoint_type: "anthropic_vision"
  ai_config:
    api_key: "${ANTHROPIC_API_KEY}"
    model: "claude-sonnet-4-20250514"
    max_tokens: 1024

export ANTHROPIC_API_KEY="sk-ant-..."

ai_support:
  enabled: true
  features:
    detection: true

ai_support:
  enabled: true
  features:
    pre_annotate: true

ai_support:
  enabled: true
  features:
    classification: true

ai_support:
  enabled: true
  features:
    hint: true

annotation_schemes:
  - annotation_type: video_annotation
    name: scenes
    description: "Segment this video into scenes"
    mode: segment
    labels:
      - name: "intro"
        color: "#4ECDC4"
      - name: "main_content"
        color: "#FF6B6B"
      - name: "outro"
        color: "#45B7D1"
 
    ai_support:
      enabled: true
      features:
        scene_detection: true
        pre_annotate: true
        hint: true
 
ai_support:
  enabled: true
  endpoint_type: "ollama_vision"
  ai_config:
    model: "llava:latest"
    max_frames: 10  # Number of frames to sample

ai_support:
  enabled: true
 
  # Text AI for radio buttons, text schemes, etc.
  endpoint_type: "ollama"
  ai_config:
    model: "llama3.2"
    include:
      all: true
 
  # Visual AI for image/video schemes
  visual_endpoint_type: "yolo"
  visual_ai_config:
    model: "yolov8m.pt"
    confidence_threshold: 0.5

ai_support:
  enabled: true
  endpoint_type: "ollama"
  visual_endpoint_type: "openai_vision"
  ai_config:
    model: "llama3.2"
  visual_ai_config:
    api_key: "${OPENAI_API_KEY}"
    model: "gpt-4o"

annotation_task_name: "Product Photo Annotation"
 
data_files:
  - data/product_photos.json
 
item_properties:
  id_key: sku
  text_key: photo_url
 
instance_display:
  layout:
    direction: horizontal
    gap: 24px
  fields:
    - key: photo_url
      type: image
      label: "Product Photo"
      display_options:
        max_width: 600
        zoomable: true
    - key: product_description
      type: text
      label: "Product Details"
 
annotation_schemes:
  - annotation_type: image_annotation
    name: product_regions
    description: "Draw boxes around products and defects"
    source_field: "photo_url"
    tools:
      - bbox
    labels:
      - name: "product"
        color: "#4ECDC4"
      - name: "defect"
        color: "#FF6B6B"
      - name: "label"
        color: "#45B7D1"
      - name: "packaging"
        color: "#96CEB4"
 
    ai_support:
      enabled: true
      features:
        detection: true
        pre_annotate: true
 
  - annotation_type: radio
    name: photo_quality
    description: "Is this photo suitable for the product listing?"
    labels:
      - Approved
      - Needs editing
      - Reshoot required
 
  - annotation_type: multiselect
    name: quality_issues
    description: "Select any issues present"
    labels:
      - Blurry
      - Poor lighting
      - Wrong angle
      - Background clutter
      - Color inaccurate
 
ai_support:
  enabled: true
  endpoint_type: "ollama"
  visual_endpoint_type: "yolo"
 
  ai_config:
    model: "llama3.2"
    include:
      all: true
 
  visual_ai_config:
    model: "yolov8m.pt"
    confidence_threshold: 0.5
 
output_annotation_dir: "annotation_output/"
output_annotation_format: "json"
user_config:
  allow_all_users: true

{"sku": "SKU-001", "photo_url": "images/products/laptop_front.jpg", "product_description": "15-inch laptop, silver finish"}
{"sku": "SKU-002", "photo_url": "images/products/headphones_side.jpg", "product_description": "Over-ear wireless headphones, black"}
{"sku": "SKU-003", "photo_url": "images/products/backpack_full.jpg", "product_description": "40L hiking backpack, navy blue"}

curl http://localhost:11434/api/tags  # Check Ollama is running
ollama list                           # Check installed models

ai_support:
  cache_config:
    disk_cache:
      enabled: true
      path: "ai_cache/visual_cache.json"