TransformersTextRouter

Use TransformersTextRouter to route text strings to different pipeline branches based on a category label predicted by a Hugging Face text classification model.

Key Features

• Routes text to different outputs based on labels from a Hugging Face text classification model
• Automatically fetches available labels from the model's configuration on Hugging Face Hub
• Supports custom label overrides
• Configurable device for model loading (CPU, GPU, or auto-detect)
• Supports private Hugging Face models with API token authentication

Configuration

1. Drag the TransformersTextRouter component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Set model to the name or path of a Hugging Face text classification model (for example, cross-encoder/nli-deberta-v3-small).
4. Go to the Advanced tab to configure labels, device, token, and huggingface_pipeline_kwargs.

Connections

TransformersTextRouter accepts a single text string as input. It creates one output per label the model can predict. Connect each output to the appropriate downstream component for that category.

The available labels are specific to the model you use. Check the model card on Hugging Face to find the expected label names.

Usage Example

components:
  TransformersTextRouter:
    type: components.routers.transformers_text_router.TransformersTextRouter
    init_parameters:

Parameters

Inputs

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

Outputs

The component creates one output per label the model can predict. Each output contains the text string if the model assigns that label.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	str		The name or path of a Hugging Face model for text classification.
labels	Optional[List[str]]	None	The list of labels. If not provided, the component fetches the labels from the model configuration on Hugging Face Hub using transformers.AutoConfig.from_pretrained.
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 for downloading private models from Hugging Face. If True, uses either the HF_API_TOKEN or HF_TOKEN environment variable.
huggingface_pipeline_kwargs	Optional[Dict[str, Any]]	None	A dictionary of keyword arguments for initializing the Hugging Face text classification pipeline.

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.