caikit.interfaces.nlp.tasks

This module holds the Task definitions for all common NLP tasks

Classes

`TextGenerationTask`	The Text Generation Task is responsible for taking input prompting text
`TextClassificationTask`	The text classification task is responsible for assigning a label or class to text.
`TokenClassificationTask`	The token classification task is responsible for assigning a label to individual
`TokenizationTask`	The tokenization task is responsible for splitting a document into tokens.
`ClassificationWithTextGenerationTask`	The classification with text generation task is responsible for taking
`EmbeddingTask`	Return a text embedding for the input text string
`EmbeddingTasks`	Return a text embedding for each text string in the input list
`RerankTask`	Returns an ordered list ranking the most relevant documents for the query
`RerankTasks`	Returns an ordered list for each query ranking the most relevant documents for the query
`SentenceSimilarityTask`	Compare the source_sentence to each of the sentences.
`SentenceSimilarityTasks`	Compare each of the source_sentences to each of the sentences.
`ChunkerTokenizationTask`	The Chunk tokenization task is responsible for taking input text

Module Contents

class caikit.interfaces.nlp.tasks.TextGenerationTask[source]

Bases: caikit.core.TaskBase

The Text Generation Task is responsible for taking input prompting text and generating additional text from that prompt.

class caikit.interfaces.nlp.tasks.TextClassificationTask[source]

Bases: caikit.core.TaskBase

The text classification task is responsible for assigning a label or class to text.

class caikit.interfaces.nlp.tasks.TokenClassificationTask[source]

Bases: caikit.core.TaskBase

The token classification task is responsible for assigning a label to individual tokens in a document.

class caikit.interfaces.nlp.tasks.TokenizationTask[source]

Bases: caikit.core.TaskBase

The tokenization task is responsible for splitting a document into tokens.

class caikit.interfaces.nlp.tasks.ClassificationWithTextGenerationTask[source]

Bases: caikit.core.TaskBase

The classification with text generation task is responsible for taking input prompting text, generating additional text from that prompt and classifying the generated text based on detectors.

class caikit.interfaces.nlp.tasks.EmbeddingTask[source]

Bases: caikit.core.TaskBase

Return a text embedding for the input text string

class caikit.interfaces.nlp.tasks.EmbeddingTasks[source]

Bases: caikit.core.TaskBase

Return a text embedding for each text string in the input list

class caikit.interfaces.nlp.tasks.RerankTask[source]

Bases: caikit.core.TaskBase

Returns an ordered list ranking the most relevant documents for the query

Required parameters:: query: The search query documents: JSON documents containing “text” or alternative “_text” to search
Returns:: The top_n documents in order of relevance (most relevant first). For each, a score and document index (position in input) is returned. The original document JSON is returned depending on optional args. The top_n optional parameter limits the results when used.

class caikit.interfaces.nlp.tasks.RerankTasks[source]

Bases: caikit.core.TaskBase

Returns an ordered list for each query ranking the most relevant documents for the query

Required parameters:: queries: The search queries documents: JSON documents containing “text” or alternative “_text” to search
Returns:: Results in order of the queries. In each query result:

The query text is optionally included for visual convenience. The top_n documents in order of relevance (most relevant first). For each, a score and document index (position in input) is returned. The original document JSON is returned depending on optional args. The top_n optional parameter limits the results when used.

class caikit.interfaces.nlp.tasks.SentenceSimilarityTask[source]

Bases: caikit.core.TaskBase

Compare the source_sentence to each of the sentences. Result contains a list of scores in the order of the input sentences.

class caikit.interfaces.nlp.tasks.SentenceSimilarityTasks[source]

Bases: caikit.core.TaskBase

Compare each of the source_sentences to each of the sentences. Returns a list of results in the order of the source_sentences. Each result contains a list of scores in the order of the input sentences.

class caikit.interfaces.nlp.tasks.ChunkerTokenizationTask[source]

Bases: caikit.core.TaskBase

The Chunk tokenization task is responsible for taking input text and giving out chunks of pre-configured type, like sentences.