JSON Parser

Class: JSONParserBlockV1

Source: inference.core.workflows.core_steps.formatters.json_parser.v1.JSONParserBlockV1

The block expects string input that would be produced by blocks exposing Large Language Models (LLMs) and Visual Language Models (VLMs). Input is parsed to JSON, and its keys are exposed as block outputs.

Accepted formats: - valid JSON strings - JSON documents wrapped with Markdown tags (very common for GPT responses)

{"my": "json"}

Details regarding block behavior:

• error_status is set True whenever at least one of expected_fields cannot be retrieved from input

• in case of multiple markdown blocks with raw JSON content - only first will be parsed and returned, while error_status will remain False

Type identifier

Use the following identifier in step "type" field: roboflow_core/json_parser@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
expected_fields	List[str]	List of expected JSON fields. error_status field name is reserved and cannot be used..	❌

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 JSON Parser in version v1.

• inputs: Florence-2 Model, Google Gemini, OpenAI, Anthropic Claude, Llama 3.2 Vision, Florence-2 Model
• outputs: Multi-Label Classification Model, Image Contours, Stability AI Inpainting, First Non Empty Or Default, Keypoint Detection Model, Detections Consensus, Velocity, SmolVLM2, Image Convert Grayscale, Image Slicer, LMM For Classification, CogVLM, Qwen2.5-VL, Circle Visualization, OpenAI, Single-Label Classification Model, VLM as Classifier, Depth Estimation, Identify Outliers, Polygon Visualization, Stitch Images, Identify Changes, Detections Stitch, Time in Zone, SIFT Comparison, VLM as Detector, Detections Classes Replacement, Bounding Box Visualization, Dominant Color, Time in Zone, Data Aggregator, Classification Label Visualization, Corner Visualization, Relative Static Crop, Camera Calibration, Cache Get, Segment Anything 2 Model, Dimension Collapse, JSON Parser, Crop Visualization, Byte Tracker, Polygon Zone Visualization, Expression, Florence-2 Model, Single-Label Classification Model, Roboflow Dataset Upload, Instance Segmentation Model, Stitch OCR Detections, Florence-2 Model, SIFT Comparison, Object Detection Model, OCR Model, Roboflow Custom Metadata, Instance Segmentation Model, Ellipse Visualization, Keypoint Detection Model, OpenAI, Path Deviation, Slack Notification, Line Counter, Buffer, Path Deviation, Dynamic Crop, Perspective Correction, CLIP Embedding Model, Halo Visualization, Pixelate Visualization, Moondream2, VLM as Classifier, Clip Comparison, Model Comparison Visualization, Clip Comparison, Google Vision OCR, Byte Tracker, Detection Offset, Twilio SMS Notification, Barcode Detection, Detections Filter, Delta Filter, Cosine Similarity, Multi-Label Classification Model, LMM, Pixel Color Count, SIFT, Overlap Filter, Reference Path Visualization, Detections Transformation, Line Counter Visualization, Rate Limiter, Property Definition, Cache Set, VLM as Detector, QR Code Detection, Absolute Static Crop, Triangle Visualization, Keypoint Visualization, Object Detection Model, Webhook Sink, Model Monitoring Inference Aggregator, Image Preprocessing, Detections Stabilizer, YOLO-World Model, Image Threshold, Roboflow Dataset Upload, Anthropic Claude, Local File Sink, Size Measurement, Bounding Rectangle, Line Counter, Continue If, Template Matching, Byte Tracker, Camera Focus, Email Notification, Image Slicer, Mask Visualization, Color Visualization, Grid Visualization, Google Gemini, Background Color Visualization, Llama 3.2 Vision, Detections Merge, Stability AI Image Generation, Gaze Detection, Trace Visualization, Label Visualization, Distance Measurement, Dynamic Zone, Image Blur, Blur Visualization, Dot Visualization, CSV Formatter

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds JSON Parser in version v1 has.

Bindings

• input

  • raw_json (language_model_output): The string with raw JSON to parse..

• output

  • error_status (boolean): Boolean flag.
  • * (*): Equivalent of any element.

Example JSON definition of step JSON Parser in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/json_parser@v1",
    "raw_json": [
        "$steps.lmm.output"
    ],
    "expected_fields": [
        "field_a",
        "field_b"
    ]
}