TransformersZeroShotTextRouter

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

Work in Progress

We're working on adding pipeline examples and most common component connections.

Key Features

• Routes text strings to different downstream connections based on zero-shot classification.
• Uses a Hugging Face zero-shot classification model to predict the category of the text.
• Supports multi-label classification by setting multi_label=True.
• The set of labels for categorization is configured at initialization time.

Configuration

1. Drag the TransformersZeroShotTextRouter component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   • Set the labels list with the categories to route text to.
   • Set the model name. The default is MoritzLaurer/deberta-v3-base-zeroshot-v1.1-all-33.
4. Go to the Advanced tab to configure multi_label, device, and huggingface_pipeline_kwargs.

Connections

TransformersZeroShotTextRouter accepts a text string as input. Connect it to any component that outputs a string.

It outputs the text to a dynamically created output named after the predicted label. Connect each labeled output to the appropriate downstream component.

Source Code

To check this component's source code, open zero_shot_text_router.py in the Haystack repository.

Usage Examples

Basic Configuration

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

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.
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.