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