{
  "schema_version": "2",
  "name": "MiniCPM-V 4.7 Vision Workflows",
  "runtime": {"default": "client"},
  "references": [
    {
      "id": "ref-image",
      "role": "reference",
      "label": "Image",
      "asset_type": "image",
      "inputs": [{"id": "in", "label": "Image", "type": "image"}],
      "outputs": [{"id": "out", "label": "Image", "type": "image"}],
      "x": 80,
      "y": 100,
      "width": 220,
      "height": 220,
      "data": {"in": null, "out": null}
    },
    {
      "id": "ref-prompt",
      "role": "reference",
      "label": "Prompt",
      "asset_type": "text",
      "inputs": [{"id": "in", "label": "Prompt", "type": "text"}],
      "outputs": [{"id": "out", "label": "Prompt", "type": "text"}],
      "x": 80,
      "y": 360,
      "width": 220,
      "height": 160,
      "data": {"in": "What is happening in this image?", "out": "What is happening in this image?"}
    },
    {
      "id": "ref-image-2",
      "role": "reference",
      "label": "Scene Image",
      "asset_type": "image",
      "inputs": [{"id": "in", "label": "Image", "type": "image"}],
      "outputs": [{"id": "out", "label": "Image", "type": "image"}],
      "x": 80,
      "y": 680,
      "width": 220,
      "height": 220,
      "data": {"in": null, "out": null}
    },
    {
      "id": "ref-caption-prompt",
      "role": "reference",
      "label": "Caption Prompt",
      "asset_type": "text",
      "inputs": [{"id": "in", "label": "Prompt", "type": "text"}],
      "outputs": [{"id": "out", "label": "Prompt", "type": "text"}],
      "x": 80,
      "y": 940,
      "width": 220,
      "height": 160,
      "data": {"in": "Describe this image in one detailed paragraph.", "out": "Describe this image in one detailed paragraph."}
    }
  ],
  "operators": [
    {
      "id": "op-ask",
      "role": "operator",
      "kind": "fn",
      "fn": "ask",
      "label": "MiniCPM-V Ask",
      "inputs": [
        {"id": "image", "label": "Image", "type": "image", "required": true},
        {"id": "prompt", "label": "Prompt", "type": "text", "required": true},
        {"id": "temperature", "label": "Temperature", "type": "number", "required": false, "custom": true}
      ],
      "outputs": [{"id": "out_0", "label": "Text", "type": "text"}],
      "x": 380,
      "y": 180,
      "width": 260,
      "height": 240,
      "data": {"temperature": 0.7}
    },
    {
      "id": "op-caption",
      "role": "operator",
      "kind": "fn",
      "fn": "caption",
      "label": "MiniCPM-V Caption",
      "inputs": [
        {"id": "image", "label": "Image", "type": "image", "required": true},
        {"id": "prompt", "label": "Prompt", "type": "text", "required": true}
      ],
      "outputs": [{"id": "out_0", "label": "Caption", "type": "text"}],
      "x": 380,
      "y": 740,
      "width": 260,
      "height": 220
    },
    {
      "id": "op-compose",
      "role": "operator",
      "kind": "fn",
      "fn": "compose_extraction_prompt",
      "label": "Compose Extraction Prompt",
      "inputs": [
        {"id": "caption", "label": "Caption", "type": "text", "required": true}
      ],
      "outputs": [{"id": "out_0", "label": "Prompt", "type": "text"}],
      "x": 720,
      "y": 780,
      "width": 260,
      "height": 180
    },
    {
      "id": "op-extract",
      "role": "operator",
      "kind": "fn",
      "fn": "extract_json",
      "label": "MiniCPM-V Extract JSON",
      "inputs": [
        {"id": "prompt", "label": "Prompt", "type": "text", "required": true}
      ],
      "outputs": [{"id": "out_0", "label": "JSON", "type": "text"}],
      "x": 1060,
      "y": 760,
      "width": 260,
      "height": 220
    }
  ],
  "subjects": [
    {
      "id": "subj-answer",
      "role": "subject",
      "label": "Answer",
      "asset_type": "text",
      "inputs": [{"id": "in", "label": "Text", "type": "text"}],
      "outputs": [{"id": "out", "label": "Text", "type": "text"}],
      "x": 720,
      "y": 200,
      "width": 320,
      "height": 200,
      "data": {"in": ""}
    },
    {
      "id": "subj-json",
      "role": "subject",
      "label": "Scene JSON",
      "asset_type": "text",
      "inputs": [{"id": "in", "label": "Text", "type": "text"}],
      "outputs": [{"id": "out", "label": "Text", "type": "text"}],
      "x": 1400,
      "y": 780,
      "width": 320,
      "height": 200,
      "data": {"in": ""}
    }
  ],
  "edges": [
    {"id": "e1", "from_node_id": "ref-image", "from_port_id": "out", "to_node_id": "op-ask", "to_port_id": "image", "type": "image"},
    {"id": "e2", "from_node_id": "ref-prompt", "from_port_id": "out", "to_node_id": "op-ask", "to_port_id": "prompt", "type": "text"},
    {"id": "e3", "from_node_id": "op-ask", "from_port_id": "out_0", "to_node_id": "subj-answer", "to_port_id": "in", "type": "text"},
    {"id": "e4", "from_node_id": "ref-image-2", "from_port_id": "out", "to_node_id": "op-caption", "to_port_id": "image", "type": "image"},
    {"id": "e5", "from_node_id": "ref-caption-prompt", "from_port_id": "out", "to_node_id": "op-caption", "to_port_id": "prompt", "type": "text"},
    {"id": "e6", "from_node_id": "op-caption", "from_port_id": "out_0", "to_node_id": "op-compose", "to_port_id": "caption", "type": "text"},
    {"id": "e7", "from_node_id": "op-compose", "from_port_id": "out_0", "to_node_id": "op-extract", "to_port_id": "prompt", "type": "text"},
    {"id": "e8", "from_node_id": "op-extract", "from_port_id": "out_0", "to_node_id": "subj-json", "to_port_id": "in", "type": "text"}
  ],
  "view": {"default": "canvas"}
}