Inner Workflow¶
Class: InnerWorkflowBlockV1
Source: inference.core.workflows.core_steps.flow_control.inner_workflow.v1.InnerWorkflowBlockV1
Execute a nested workflow while mapping parent data into the child's inputs via parameter_bindings.
Provide either a full inline definition in workflow_definition, or resolve a saved workflow using
workflow_workspace_id and workflow_id (optional workflow_version_id).
Reference fields are expanded at compile time via workflows_core.inner_workflow_spec_resolver
(default: Roboflow API using workflows_core.api_key, or local definitions when workspace is
"local").
At compile time the engine validates composition (acyclicity, max depth) and parameter_bindings,
then inlines the child's steps into the parent workflow graph (same execution path as ordinary
steps).
The block's run() method is not used at runtime; do not call it directly.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/inner_workflow@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
workflow_definition |
Dict[Any, Any] |
Full nested workflow definition (same JSON shape as a root workflow: version, inputs, steps, outputs). Required unless workflow_workspace_id and workflow_id are set; mutually exclusive with those reference fields.. |
❌ |
workflow_workspace_id |
str |
Workspace id for a saved workflow to load (Roboflow slug or "local" for on-disk definitions). Use with workflow_id; mutually exclusive with a non-empty workflow_definition.. |
❌ |
workflow_id |
str |
Saved workflow id to fetch. Use with workflow_workspace_id.. |
❌ |
workflow_version_id |
str |
Optional pinned workflow version when resolving by id.. | ❌ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Inner Workflow in version v1.
- inputs:
S3 Sink,Email Notification,Clip Comparison,Morphological Transformation,Path Deviation,SAM 3,VLM As Detector,Keypoint Detection Model,Qwen-VL,Twilio SMS/MMS Notification,YOLO-World Model,Line Counter,Time in Zone,Polygon Zone Visualization,Stitch OCR Detections,MoonshotAI Kimi,OpenAI-Compatible LLM,OpenAI,VLM As Detector,Heatmap Visualization,Keypoint Visualization,Email Notification,Seg Preview,Anthropic Claude,Stability AI Image Generation,Google Vision OCR,Llama 3.2 Vision,Camera Focus,Label Visualization,Instance Segmentation Model,SAM 3,Path Deviation,Qwen3.5,Overlap Filter,Local File Sink,Multi-Label Classification Model,SmolVLM2,Google Gemini,Rate Limiter,Motion Detection,Byte Tracker,Background Color Visualization,Mask Edge Snap,Instance Segmentation Model,Qwen 3.5 API,Google Gemini,Polygon Visualization,Moondream2,Velocity,Grid Visualization,SIFT Comparison,Florence-2 Model,Delta Filter,Barcode Detection,Time in Zone,OCR Model,Detection Event Log,Single-Label Classification Model,VLM As Classifier,Detections Filter,Qwen2.5-VL,Detections Merge,First Non Empty Or Default,Detections Stabilizer,LMM For Classification,Keypoint Detection Model,Image Preprocessing,Roboflow Dataset Upload,SIFT,Dynamic Zone,Corner Visualization,Segment Anything 2 Model,Stability AI Outpainting,Halo Visualization,Multi-Label Classification Model,Qwen3-VL,Qwen3.5-VL,Time in Zone,Detections List Roll-Up,Blur Visualization,Semantic Segmentation Model,Property Definition,Perception Encoder Embedding Model,Distance Measurement,VLM As Classifier,Trace Visualization,Morphological Transformation,Stitch OCR Detections,Gaze Detection,Reference Path Visualization,Halo Visualization,Model Comparison Visualization,Dot Visualization,JSON Parser,Pixel Color Count,Background Subtraction,QR Code Detection,Text Display,Detections Combine,Bounding Rectangle,ByteTrack Tracker,Absolute Static Crop,CSV Formatter,Florence-2 Model,Byte Tracker,Icon Visualization,Identify Outliers,Mask Area Measurement,Object Detection Model,Perspective Correction,SAM 3,BoT-SORT Tracker,Stability AI Inpainting,Image Convert Grayscale,Object Detection Model,Line Counter,QR Code Generator,OpenRouter,Model Monitoring Inference Aggregator,OpenAI,Llama 3.2 Vision,Image Threshold,OC-SORT Tracker,Anthropic Claude,Dynamic Crop,Size Measurement,Detections Consensus,Clip Comparison,Cache Set,Dominant Color,Continue If,Contrast Enhancement,Bounding Box Visualization,Detection Offset,Depth Estimation,Keypoint Detection Model,CLIP Embedding Model,Image Contours,EasyOCR,Relative Static Crop,Multi-Label Classification Model,Polygon Visualization,Google Gemma API,Template Matching,Qwen 3.6 API,Single-Label Classification Model,Image Blur,Anthropic Claude,Per-Class Confidence Filter,Object Detection Model,Triangle Visualization,Roboflow Custom Metadata,OpenAI,SIFT Comparison,Slack Notification,Image Stack,Pixelate Visualization,Single-Label Classification Model,OpenAI,Stitch Images,Buffer,Instance Segmentation Model,Image Slicer,Environment Secrets Store,Line Counter Visualization,Image Slicer,Cosine Similarity,Detections Classes Replacement,Semantic Segmentation Model,Cache Get,LMM,Roboflow Dataset Upload,Expression,Detections Transformation,Color Visualization,Google Gemini,Data Aggregator,Classification Label Visualization,Camera Focus,Camera Calibration,Detections Stitch,Byte Tracker,Ellipse Visualization,PTZ Tracking (ONVIF),Identify Changes,SORT Tracker,Mask Visualization,GLM-OCR,Crop Visualization,Circle Visualization,CogVLM,Inner Workflow,Dimension Collapse,SAM2 Video Tracker,Contrast Equalization,Roboflow Vision Events,Webhook Sink,Twilio SMS Notification,MoonshotAI Kimi,Google Gemma - outputs:
S3 Sink,Keypoint Detection Model,Email Notification,Morphological Transformation,SAM 3,Qwen-VL,Path Deviation,Clip Comparison,VLM As Detector,Twilio SMS/MMS Notification,YOLO-World Model,Line Counter,Time in Zone,Polygon Zone Visualization,Stitch OCR Detections,MoonshotAI Kimi,OpenAI-Compatible LLM,OpenAI,VLM As Detector,Heatmap Visualization,Email Notification,Keypoint Visualization,Seg Preview,Anthropic Claude,Llama 3.2 Vision,Google Vision OCR,Stability AI Image Generation,SAM 3,Label Visualization,Instance Segmentation Model,Camera Focus,Path Deviation,Qwen3.5,Overlap Filter,Local File Sink,Multi-Label Classification Model,SmolVLM2,Google Gemini,Rate Limiter,Motion Detection,Byte Tracker,Background Color Visualization,Mask Edge Snap,Instance Segmentation Model,Qwen 3.5 API,Google Gemini,Polygon Visualization,Moondream2,Velocity,SIFT Comparison,Detection Event Log,Florence-2 Model,Delta Filter,Grid Visualization,Time in Zone,Single-Label Classification Model,OCR Model,Barcode Detection,VLM As Classifier,Detections Filter,Qwen2.5-VL,Detections Merge,First Non Empty Or Default,Detections Stabilizer,LMM For Classification,Keypoint Detection Model,Image Preprocessing,Roboflow Dataset Upload,SIFT,Dynamic Zone,Segment Anything 2 Model,Stability AI Outpainting,Corner Visualization,Multi-Label Classification Model,Halo Visualization,Qwen3.5-VL,Qwen3-VL,Time in Zone,Detections List Roll-Up,Blur Visualization,Semantic Segmentation Model,Property Definition,Perception Encoder Embedding Model,Distance Measurement,VLM As Classifier,Trace Visualization,Morphological Transformation,Stitch OCR Detections,Gaze Detection,Reference Path Visualization,Halo Visualization,Model Comparison Visualization,Dot Visualization,JSON Parser,Pixel Color Count,QR Code Detection,Background Subtraction,Text Display,Detections Combine,Bounding Rectangle,ByteTrack Tracker,Absolute Static Crop,CSV Formatter,Florence-2 Model,Byte Tracker,Icon Visualization,Identify Outliers,Mask Area Measurement,Object Detection Model,Perspective Correction,SAM 3,BoT-SORT Tracker,Stability AI Inpainting,Image Convert Grayscale,Object Detection Model,Line Counter,QR Code Generator,OpenRouter,Model Monitoring Inference Aggregator,OpenAI,Llama 3.2 Vision,Image Threshold,OC-SORT Tracker,Anthropic Claude,Dynamic Crop,Detections Consensus,Size Measurement,Clip Comparison,Cache Set,Dominant Color,Continue If,Contrast Enhancement,Bounding Box Visualization,Detection Offset,Depth Estimation,Keypoint Detection Model,Image Contours,CLIP Embedding Model,EasyOCR,Relative Static Crop,Multi-Label Classification Model,Polygon Visualization,Google Gemma API,Template Matching,Qwen 3.6 API,Single-Label Classification Model,Image Blur,Per-Class Confidence Filter,Anthropic Claude,Triangle Visualization,Object Detection Model,Roboflow Custom Metadata,SIFT Comparison,OpenAI,Slack Notification,Image Stack,Pixelate Visualization,Single-Label Classification Model,Stitch Images,Instance Segmentation Model,Buffer,OpenAI,Image Slicer,Line Counter Visualization,Image Slicer,Cosine Similarity,Detections Classes Replacement,Semantic Segmentation Model,Cache Get,LMM,Roboflow Dataset Upload,Data Aggregator,Detections Transformation,Color Visualization,Google Gemini,Expression,Classification Label Visualization,Camera Focus,Camera Calibration,Detections Stitch,Byte Tracker,Ellipse Visualization,PTZ Tracking (ONVIF),Identify Changes,SORT Tracker,Mask Visualization,GLM-OCR,Crop Visualization,Circle Visualization,CogVLM,Inner Workflow,Dimension Collapse,SAM2 Video Tracker,Contrast Equalization,Roboflow Vision Events,Webhook Sink,Twilio SMS Notification,MoonshotAI Kimi,Google Gemma
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Inner Workflow in version v1 has.
Bindings
-
input
parameter_bindings(*): Maps child workflow input names to a selector (or literal coerced by the engine) from the parent. Required for every child input exceptWorkflowParameter/InferenceParameterentries that declare a non-nulldefault_value(those may be omitted and the child's default is used during compilation inlining)..
-
output
*(*): Equivalent of any element.
Example JSON definition of step Inner Workflow in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/inner_workflow@v1",
"workflow_definition": "<block_does_not_provide_example>",
"workflow_workspace_id": "<block_does_not_provide_example>",
"workflow_id": "<block_does_not_provide_example>",
"workflow_version_id": "<block_does_not_provide_example>",
"parameter_bindings": "<block_does_not_provide_example>"
}