Python package

pangram.text_classifier module

class pangram.text_classifier.PangramText(api_key: str | None = None, max_batch_size=32)

Bases: object

__init__(api_key: str | None = None, max_batch_size=32) → None

A classifier for text inputs using the Pangram Labs API.

This class provides synchronous and asynchronous methods to classify text by making API requests.

Parameters:

api_key (str, optional) – Your API key for the Pangram Labs. If not provided, the environment variable PANGRAM_API_KEY will be used.

Raises:

ValueError – If the API key is not provided and not set in the environment.

predict(text: str)

Classify text as AI- or human-written.

Sends a request to the Pangram Text API and returns the classification result.

Parameters:

text (str) – The text to be classified.

Returns:

The classification result from the API.

Return type:

dict

batch_predict(text_batch: List[str])

Classify a batch of text as AI- or human-written.

This method sends a batch of text to the Pangram Text API and returns the classification results.

Parameters:

text_batch (List[str]) – A list of strings to be classified.

Returns:

A list of classification results from the API for each text in the batch.

Return type:

List[dict]

predict_sliding_window(text: str)

Classify a long document using a sliding window to iterate across the full document. :param text: The text to be classified. :type text: str :return: The classification result from the API. :rtype: dict