TransformersZeroShotTextRouter

Route text strings to different connections based on a category label.

Key Features

• Routes text to different pipeline branches based on zero-shot classification — no training data required.
• Uses a Hugging Face NLI model to classify text against the labels you provide.
• Supports multi-label classification to allow multiple labels per input.
• Each label becomes a separate output connection for downstream routing.
• Compatible with any Hugging Face zero-shot classification model.

Configuration

1. Drag the TransformersZeroShotTextRouter component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Enter the labels to use for routing, such as ["technical", "billing", "general"].
   2. Enter the model name or path, such as MoritzLaurer/deberta-v3-base-zeroshot-v1.1-all-33.
4. Go to the Advanced tab to configure multi-label mode, device, token, and Hugging Face pipeline kwargs.

Connections

TransformersZeroShotTextRouter receives a text string as input. It routes the text to one of its output connections, where each label becomes a separate output. Connect each label output to a different downstream component based on the routing logic you want.

Usage Example

components:
  TransformersZeroShotTextRouter:
    type: components.routers.zero_shot_text_router.TransformersZeroShotTextRouter
    init_parameters:

Parameters

Inputs

Parameter	Type	Default	Description
text	str		A string of text to route.

Outputs

Parameter	Type	Default	Description

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
labels	List[str]		The set of labels to use for classification. Can be a single label, a string of comma-separated labels, or a list of labels.
multi_label	bool	False	Indicates if multiple labels can be true. If False, label scores are normalized so their sum equals 1 for each sequence. If True, the labels are considered independent and probabilities are normalized for each candidate by doing a softmax of the entailment score vs. the contradiction score.
model	str	MoritzLaurer/deberta-v3-base-zeroshot-v1.1-all-33	The name or path of a Hugging Face model for zero-shot text classification.
device	Optional[ComponentDevice]	None	The device for loading the model. If None, automatically selects the default device. If a device or device map is specified in huggingface_pipeline_kwargs, it overrides this parameter.
token	Optional[Secret]	Secret.from_env_var(['HF_API_TOKEN', 'HF_TOKEN'], strict=False)	The API token used to download private models from Hugging Face. If True, uses either HF_API_TOKEN or HF_TOKEN environment variables.
huggingface_pipeline_kwargs	Optional[Dict[str, Any]]	None	A dictionary of keyword arguments for initializing the Hugging Face zero shot text classification.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
text	str		A string of text to route.