aixplain.modules.pipeline.pipeline
Auto-generated pipeline module containing node classes and Pipeline factory methods.
TextNormalizationInputs Objects
class TextNormalizationInputs(Inputs)
Input parameters for TextNormalization.
__init__
def __init__(node=None)
Initialize TextNormalizationInputs.
TextNormalizationOutputs Objects
class TextNormalizationOutputs(Outputs)
Output parameters for TextNormalization.
__init__
def __init__(node=None)
Initialize TextNormalizationOutputs.
TextNormalization Objects
class TextNormalization(AssetNode[TextNormalizationInputs,
TextNormalizationOutputs])
TextNormalization node.
Converts unstructured or non-standard textual data into a more readable and uniform format, dealing with abbreviations, numerals, and other non-standard words.
InputType: text OutputType: label
ParaphrasingInputs Objects
class ParaphrasingInputs(Inputs)
Input parameters for Paraphrasing.
__init__
def __init__(node=None)
Initialize ParaphrasingInputs.
ParaphrasingOutputs Objects
class ParaphrasingOutputs(Outputs)
Output parameters for Paraphrasing.
__init__
def __init__(node=None)
Initialize ParaphrasingOutputs.
Paraphrasing Objects
class Paraphrasing(AssetNode[ParaphrasingInputs, ParaphrasingOutputs])
Paraphrasing node.
Express the meaning of the writer or speaker or something written or spoken using different words.
InputType: text OutputType: text
LanguageIdentificationInputs Objects
class LanguageIdentificationInputs(Inputs)
Input parameters for LanguageIdentification.
__init__
def __init__(node=None)
Initialize LanguageIdentificationInputs.
LanguageIdentificationOutputs Objects
class LanguageIdentificationOutputs(Outputs)
Output parameters for LanguageIdentification.
__init__
def __init__(node=None)
Initialize LanguageIdentificationOutputs.
LanguageIdentification Objects
class LanguageIdentification(AssetNode[LanguageIdentificationInputs,
LanguageIdentificationOutputs])
LanguageIdentification node.
Detects the language in which a given text is written, aiding in multilingual platforms or content localization.
InputType: text OutputType: text
BenchmarkScoringAsrInputs Objects
class BenchmarkScoringAsrInputs(Inputs)
Input parameters for BenchmarkScoringAsr.
__init__
def __init__(node=None)
Initialize BenchmarkScoringAsrInputs.
BenchmarkScoringAsrOutputs Objects
class BenchmarkScoringAsrOutputs(Outputs)
Output parameters for BenchmarkScoringAsr.
__init__
def __init__(node=None)
Initialize BenchmarkScoringAsrOutputs.
BenchmarkScoringAsr Objects
class BenchmarkScoringAsr(AssetNode[BenchmarkScoringAsrInputs,
BenchmarkScoringAsrOutputs])
BenchmarkScoringAsr node.
Benchmark Scoring ASR is a function that evaluates and compares the performance of automatic speech recognition systems by analyzing their accuracy, speed, and other relevant metrics against a standardized set of benchmarks.
InputType: audio OutputType: label
MultiClassTextClassificationInputs Objects
class MultiClassTextClassificationInputs(Inputs)
Input parameters for MultiClassTextClassification.
__init__
def __init__(node=None)
Initialize MultiClassTextClassificationInputs.
MultiClassTextClassificationOutputs Objects
class MultiClassTextClassificationOutputs(Outputs)
Output parameters for MultiClassTextClassification.
__init__
def __init__(node=None)
Initialize MultiClassTextClassificationOutputs.
MultiClassTextClassification Objects
class MultiClassTextClassification(
AssetNode[MultiClassTextClassificationInputs,
MultiClassTextClassificationOutputs])
MultiClassTextClassification node.
Multi Class Text Classification is a natural language processing task that involves categorizing a given text into one of several predefined classes or categories based on its content.
InputType: text OutputType: label
SpeechEmbeddingInputs Objects
class SpeechEmbeddingInputs(Inputs)
Input parameters for SpeechEmbedding.
__init__
def __init__(node=None)
Initialize SpeechEmbeddingInputs.
SpeechEmbeddingOutputs Objects
class SpeechEmbeddingOutputs(Outputs)
Output parameters for SpeechEmbedding.
__init__
def __init__(node=None)
Initialize SpeechEmbeddingOutputs.
SpeechEmbedding Objects
class SpeechEmbedding(AssetNode[SpeechEmbeddingInputs,
SpeechEmbeddingOutputs])
SpeechEmbedding node.
Transforms spoken content into a fixed-size vector in a high-dimensional space that captures the content's essence. Facilitates tasks like speech recognition and speaker verification.
InputType: audio OutputType: text
DocumentImageParsingInputs Objects
class DocumentImageParsingInputs(Inputs)
Input parameters for DocumentImageParsing.
__init__
def __init__(node=None)
Initialize DocumentImageParsingInputs.
DocumentImageParsingOutputs Objects
class DocumentImageParsingOutputs(Outputs)
Output parameters for DocumentImageParsing.
__init__
def __init__(node=None)
Initialize DocumentImageParsingOutputs.
DocumentImageParsing Objects
class DocumentImageParsing(AssetNode[DocumentImageParsingInputs,
DocumentImageParsingOutputs])
DocumentImageParsing node.
Document Image Parsing is the process of analyzing and converting scanned or photographed images of documents into structured, machine-readable formats by identifying and extracting text, layout, and other relevant information.
InputType: image OutputType: text
TranslationInputs Objects
class TranslationInputs(Inputs)
Input parameters for Translation.
__init__
def __init__(node=None)
Initialize TranslationInputs.
TranslationOutputs Objects
class TranslationOutputs(Outputs)
Output parameters for Translation.
__init__
def __init__(node=None)
Initialize TranslationOutputs.
Translation Objects
class Translation(AssetNode[TranslationInputs, TranslationOutputs])
Translation node.
Converts text from one language to another while maintaining the original message's essence and context. Crucial for global communication.
InputType: text OutputType: text
AudioSourceSeparationInputs Objects
class AudioSourceSeparationInputs(Inputs)
Input parameters for AudioSourceSeparation.
__init__
def __init__(node=None)
Initialize AudioSourceSeparationInputs.
AudioSourceSeparationOutputs Objects
class AudioSourceSeparationOutputs(Outputs)
Output parameters for AudioSourceSeparation.
__init__
def __init__(node=None)
Initialize AudioSourceSeparationOutputs.
AudioSourceSeparation Objects
class AudioSourceSeparation(AssetNode[AudioSourceSeparationInputs,
AudioSourceSeparationOutputs])
AudioSourceSeparation node.
Audio Source Separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals).
InputType: audio OutputType: audio
SpeechRecognitionInputs Objects
class SpeechRecognitionInputs(Inputs)
Input parameters for SpeechRecognition.
__init__
def __init__(node=None)
Initialize SpeechRecognitionInputs.
SpeechRecognitionOutputs Objects
class SpeechRecognitionOutputs(Outputs)
Output parameters for SpeechRecognition.
__init__
def __init__(node=None)
Initialize SpeechRecognitionOutputs.
SpeechRecognition Objects
class SpeechRecognition(AssetNode[SpeechRecognitionInputs,
SpeechRecognitionOutputs])
SpeechRecognition node.
Converts spoken language into written text. Useful for transcription services, voice assistants, and applications requiring voice-to-text capabilities.
InputType: audio OutputType: text
KeywordSpottingInputs Objects
class KeywordSpottingInputs(Inputs)
Input parameters for KeywordSpotting.
__init__
def __init__(node=None)
Initialize KeywordSpottingInputs.
KeywordSpottingOutputs Objects
class KeywordSpottingOutputs(Outputs)
Output parameters for KeywordSpotting.
__init__
def __init__(node=None)
Initialize KeywordSpottingOutputs.
KeywordSpotting Objects
class KeywordSpotting(AssetNode[KeywordSpottingInputs,
KeywordSpottingOutputs])
KeywordSpotting node.
Keyword Spotting is a function that enables the detection and identification of specific words or phrases within a stream of audio, often used in voice- activated systems to trigger actions or commands based on recognized keywords.
InputType: audio OutputType: label
PartOfSpeechTaggingInputs Objects
class PartOfSpeechTaggingInputs(Inputs)
Input parameters for PartOfSpeechTagging.
__init__
def __init__(node=None)
Initialize PartOfSpeechTaggingInputs.
PartOfSpeechTaggingOutputs Objects
class PartOfSpeechTaggingOutputs(Outputs)
Output parameters for PartOfSpeechTagging.
__init__
def __init__(node=None)
Initialize PartOfSpeechTaggingOutputs.
PartOfSpeechTagging Objects
class PartOfSpeechTagging(AssetNode[PartOfSpeechTaggingInputs,
PartOfSpeechTaggingOutputs])
PartOfSpeechTagging node.
Part of Speech Tagging is a natural language processing task that involves assigning each word in a sentence its corresponding part of speech, such as noun, verb, adjective, or adverb, based on its role and context within the sentence.
InputType: text OutputType: label
ReferencelessAudioGenerationMetricInputs Objects
class ReferencelessAudioGenerationMetricInputs(Inputs)
Input parameters for ReferencelessAudioGenerationMetric.
__init__
def __init__(node=None)
Initialize ReferencelessAudioGenerationMetricInputs.
ReferencelessAudioGenerationMetricOutputs Objects
class ReferencelessAudioGenerationMetricOutputs(Outputs)
Output parameters for ReferencelessAudioGenerationMetric.
__init__
def __init__(node=None)
Initialize ReferencelessAudioGenerationMetricOutputs.
ReferencelessAudioGenerationMetric Objects
class ReferencelessAudioGenerationMetric(
BaseMetric[ReferencelessAudioGenerationMetricInputs,
ReferencelessAudioGenerationMetricOutputs])
ReferencelessAudioGenerationMetric node.
The Referenceless Audio Generation Metric is a tool designed to evaluate the quality of generated audio content without the need for a reference or original audio sample for comparison.
InputType: text OutputType: text
VoiceActivityDetectionInputs Objects
class VoiceActivityDetectionInputs(Inputs)
Input parameters for VoiceActivityDetection.
__init__
def __init__(node=None)
Initialize VoiceActivityDetectionInputs.
VoiceActivityDetectionOutputs Objects
class VoiceActivityDetectionOutputs(Outputs)
Output parameters for VoiceActivityDetection.
__init__
def __init__(node=None)
Initialize VoiceActivityDetectionOutputs.
VoiceActivityDetection Objects
class VoiceActivityDetection(BaseSegmentor[VoiceActivityDetectionInputs,
VoiceActivityDetectionOutputs])
VoiceActivityDetection node.
Determines when a person is speaking in an audio clip. It's an essential preprocessing step for other audio-related tasks.
InputType: audio OutputType: audio
SentimentAnalysisInputs Objects
class SentimentAnalysisInputs(Inputs)
Input parameters for SentimentAnalysis.
__init__
def __init__(node=None)
Initialize SentimentAnalysisInputs.
SentimentAnalysisOutputs Objects
class SentimentAnalysisOutputs(Outputs)
Output parameters for SentimentAnalysis.
__init__
def __init__(node=None)
Initialize SentimentAnalysisOutputs.
SentimentAnalysis Objects
class SentimentAnalysis(AssetNode[SentimentAnalysisInputs,
SentimentAnalysisOutputs])
SentimentAnalysis node.
Determines the sentiment or emotion (e.g., positive, negative, neutral) of a piece of text, aiding in understanding user feedback or market sentiment.
InputType: text OutputType: label
SubtitlingInputs Objects
class SubtitlingInputs(Inputs)
Input parameters for Subtitling.
__init__
def __init__(node=None)
Initialize SubtitlingInputs.
SubtitlingOutputs Objects
class SubtitlingOutputs(Outputs)
Output parameters for Subtitling.
__init__
def __init__(node=None)
Initialize SubtitlingOutputs.
Subtitling Objects
class Subtitling(AssetNode[SubtitlingInputs, SubtitlingOutputs])
Subtitling node.
Generates accurate subtitles for videos, enhancing accessibility for diverse audiences.
InputType: audio OutputType: text
MultiLabelTextClassificationInputs Objects
class MultiLabelTextClassificationInputs(Inputs)
Input parameters for MultiLabelTextClassification.
__init__
def __init__(node=None)
Initialize MultiLabelTextClassificationInputs.
MultiLabelTextClassificationOutputs Objects
class MultiLabelTextClassificationOutputs(Outputs)
Output parameters for MultiLabelTextClassification.
__init__
def __init__(node=None)
Initialize MultiLabelTextClassificationOutputs.
MultiLabelTextClassification Objects
class MultiLabelTextClassification(
AssetNode[MultiLabelTextClassificationInputs,
MultiLabelTextClassificationOutputs])
MultiLabelTextClassification node.
Multi Label Text Classification is a natural language processing task where a given text is analyzed and assigned multiple relevant labels or categories from a predefined set, allowing for the text to belong to more than one category simultaneously.
InputType: text OutputType: label
VisemeGenerationInputs Objects
class VisemeGenerationInputs(Inputs)
Input parameters for VisemeGeneration.
__init__
def __init__(node=None)
Initialize VisemeGenerationInputs.
VisemeGenerationOutputs Objects
class VisemeGenerationOutputs(Outputs)
Output parameters for VisemeGeneration.
__init__
def __init__(node=None)
Initialize VisemeGenerationOutputs.
VisemeGeneration Objects
class VisemeGeneration(AssetNode[VisemeGenerationInputs,
VisemeGenerationOutputs])
VisemeGeneration node.
Viseme Generation is the process of creating visual representations of phonemes, which are the distinct units of sound in speech, to synchronize lip movements with spoken words in animations or virtual avatars.
InputType: text OutputType: label
TextSegmenationInputs Objects
class TextSegmenationInputs(Inputs)
Input parameters for TextSegmenation.
__init__
def __init__(node=None)
Initialize TextSegmenationInputs.
TextSegmenationOutputs Objects
class TextSegmenationOutputs(Outputs)
Output parameters for TextSegmenation.
__init__
def __init__(node=None)
Initialize TextSegmenationOutputs.
TextSegmenation Objects
class TextSegmenation(AssetNode[TextSegmenationInputs,
TextSegmenationOutputs])
TextSegmenation node.
Text Segmentation is the process of dividing a continuous text into meaningful units, such as words, sentences, or topics, to facilitate easier analysis and understanding.
InputType: text OutputType: text
ZeroShotClassificationInputs Objects
class ZeroShotClassificationInputs(Inputs)
Input parameters for ZeroShotClassification.
__init__
def __init__(node=None)
Initialize ZeroShotClassificationInputs.
ZeroShotClassificationOutputs Objects
class ZeroShotClassificationOutputs(Outputs)
Output parameters for ZeroShotClassification.
__init__
def __init__(node=None)
Initialize ZeroShotClassificationOutputs.
ZeroShotClassification Objects
class ZeroShotClassification(AssetNode[ZeroShotClassificationInputs,
ZeroShotClassificationOutputs])
ZeroShotClassification node.
InputType: text OutputType: text
TextGenerationInputs Objects
class TextGenerationInputs(Inputs)
Input parameters for TextGeneration.
__init__
def __init__(node=None)
Initialize TextGenerationInputs.
TextGenerationOutputs Objects
class TextGenerationOutputs(Outputs)
Output parameters for TextGeneration.
__init__
def __init__(node=None)
Initialize TextGenerationOutputs.
TextGeneration Objects
class TextGeneration(AssetNode[TextGenerationInputs, TextGenerationOutputs])
TextGeneration node.
Creates coherent and contextually relevant textual content based on prompts or certain parameters. Useful for chatbots, content creation, and data augmentation.
InputType: text OutputType: text
AudioIntentDetectionInputs Objects
class AudioIntentDetectionInputs(Inputs)
Input parameters for AudioIntentDetection.
__init__
def __init__(node=None)
Initialize AudioIntentDetectionInputs.
AudioIntentDetectionOutputs Objects
class AudioIntentDetectionOutputs(Outputs)
Output parameters for AudioIntentDetection.
__init__
def __init__(node=None)
Initialize AudioIntentDetectionOutputs.
AudioIntentDetection Objects
class AudioIntentDetection(AssetNode[AudioIntentDetectionInputs,
AudioIntentDetectionOutputs])
AudioIntentDetection node.
Audio Intent Detection is a process that involves analyzing audio signals to identify and interpret the underlying intentions or purposes behind spoken words, enabling systems to understand and respond appropriately to human speech.
InputType: audio OutputType: label
EntityLinkingInputs Objects
class EntityLinkingInputs(Inputs)
Input parameters for EntityLinking.
__init__
def __init__(node=None)
Initialize EntityLinkingInputs.
EntityLinkingOutputs Objects
class EntityLinkingOutputs(Outputs)
Output parameters for EntityLinking.
__init__
def __init__(node=None)
Initialize EntityLinkingOutputs.
EntityLinking Objects
class EntityLinking(AssetNode[EntityLinkingInputs, EntityLinkingOutputs])
EntityLinking node.
Associates identified entities in the text with specific entries in a knowledge base or database.
InputType: text OutputType: label
ConnectionInputs Objects
class ConnectionInputs(Inputs)
Input parameters for Connection.
__init__
def __init__(node=None)
Initialize ConnectionInputs.
ConnectionOutputs Objects
class ConnectionOutputs(Outputs)
Output parameters for Connection.
__init__
def __init__(node=None)
Initialize ConnectionOutputs.
Connection Objects
class Connection(AssetNode[ConnectionInputs, ConnectionOutputs])
Connection node.
Connections are integration that allow you to connect your AI agents to external tools
InputType: text OutputType: text
VisualQuestionAnsweringInputs Objects
class VisualQuestionAnsweringInputs(Inputs)
Input parameters for VisualQuestionAnswering.
__init__
def __init__(node=None)
Initialize VisualQuestionAnsweringInputs.
VisualQuestionAnsweringOutputs Objects
class VisualQuestionAnsweringOutputs(Outputs)
Output parameters for VisualQuestionAnswering.
__init__
def __init__(node=None)
Initialize VisualQuestionAnsweringOutputs.
VisualQuestionAnswering Objects
class VisualQuestionAnswering(AssetNode[VisualQuestionAnsweringInputs,
VisualQuestionAnsweringOutputs])
VisualQuestionAnswering node.
Visual Question Answering (VQA) is a task in artificial intelligence that involves analyzing an image and providing accurate, contextually relevant answers to questions posed about the visual content of that image.
InputType: image OutputType: video
LoglikelihoodInputs Objects
class LoglikelihoodInputs(Inputs)
Input parameters for Loglikelihood.
__init__
def __init__(node=None)
Initialize LoglikelihoodInputs.
LoglikelihoodOutputs Objects
class LoglikelihoodOutputs(Outputs)
Output parameters for Loglikelihood.
__init__
def __init__(node=None)
Initialize LoglikelihoodOutputs.
Loglikelihood Objects
class Loglikelihood(AssetNode[LoglikelihoodInputs, LoglikelihoodOutputs])
Loglikelihood node.
The Log Likelihood function measures the probability of observing the given data under a specific statistical model by taking the natural logarithm of the likelihood function, thereby transforming the product of probabilities into a sum, which simplifies the process of optimization and parameter estimation.
InputType: text OutputType: number
LanguageIdentificationAudioInputs Objects
class LanguageIdentificationAudioInputs(Inputs)
Input parameters for LanguageIdentificationAudio.
__init__
def __init__(node=None)
Initialize LanguageIdentificationAudioInputs.
LanguageIdentificationAudioOutputs Objects
class LanguageIdentificationAudioOutputs(Outputs)
Output parameters for LanguageIdentificationAudio.
__init__
def __init__(node=None)
Initialize LanguageIdentificationAudioOutputs.
LanguageIdentificationAudio Objects
class LanguageIdentificationAudio(AssetNode[LanguageIdentificationAudioInputs,
LanguageIdentificationAudioOutputs]
)
LanguageIdentificationAudio node.
The Language Identification Audio function analyzes audio input to determine and identify the language being spoken.
InputType: audio OutputType: label
FactCheckingInputs Objects
class FactCheckingInputs(Inputs)
Input parameters for FactChecking.
__init__
def __init__(node=None)
Initialize FactCheckingInputs.
FactCheckingOutputs Objects
class FactCheckingOutputs(Outputs)
Output parameters for FactChecking.
__init__
def __init__(node=None)
Initialize FactCheckingOutputs.
FactChecking Objects
class FactChecking(AssetNode[FactCheckingInputs, FactCheckingOutputs])
FactChecking node.
Fact Checking is the process of verifying the accuracy and truthfulness of information, statements, or claims by cross-referencing with reliable sources and evidence.
InputType: text OutputType: label
TableQuestionAnsweringInputs Objects
class TableQuestionAnsweringInputs(Inputs)
Input parameters for TableQuestionAnswering.
__init__
def __init__(node=None)
Initialize TableQuestionAnsweringInputs.
TableQuestionAnsweringOutputs Objects
class TableQuestionAnsweringOutputs(Outputs)
Output parameters for TableQuestionAnswering.
__init__
def __init__(node=None)
Initialize TableQuestionAnsweringOutputs.
TableQuestionAnswering Objects
class TableQuestionAnswering(AssetNode[TableQuestionAnsweringInputs,
TableQuestionAnsweringOutputs])
TableQuestionAnswering node.
The task of question answering over tables is given an input table (or a set of tables) T and a natural language question Q (a user query), output the correct answer A
InputType: text OutputType: text
SpeechClassificationInputs Objects
class SpeechClassificationInputs(Inputs)
Input parameters for SpeechClassification.
__init__
def __init__(node=None)
Initialize SpeechClassificationInputs.
SpeechClassificationOutputs Objects
class SpeechClassificationOutputs(Outputs)
Output parameters for SpeechClassification.
__init__
def __init__(node=None)
Initialize SpeechClassificationOutputs.
SpeechClassification Objects
class SpeechClassification(AssetNode[SpeechClassificationInputs,
SpeechClassificationOutputs])
SpeechClassification node.
Categorizes audio clips based on their content, aiding in content organization and targeted actions.
InputType: audio OutputType: label
InverseTextNormalizationInputs Objects
class InverseTextNormalizationInputs(Inputs)
Input parameters for InverseTextNormalization.
__init__
def __init__(node=None)
Initialize InverseTextNormalizationInputs.
InverseTextNormalizationOutputs Objects
class InverseTextNormalizationOutputs(Outputs)
Output parameters for InverseTextNormalization.
__init__
def __init__(node=None)
Initialize InverseTextNormalizationOutputs.
InverseTextNormalization Objects
class InverseTextNormalization(AssetNode[InverseTextNormalizationInputs,
InverseTextNormalizationOutputs])
InverseTextNormalization node.
Inverse Text Normalization is the process of converting spoken or written language in its normalized form, such as numbers, dates, and abbreviations, back into their original, more complex or detailed textual representations.
InputType: text OutputType: label
MultiClassImageClassificationInputs Objects
class MultiClassImageClassificationInputs(Inputs)
Input parameters for MultiClassImageClassification.
__init__
def __init__(node=None)
Initialize MultiClassImageClassificationInputs.
MultiClassImageClassificationOutputs Objects
class MultiClassImageClassificationOutputs(Outputs)
Output parameters for MultiClassImageClassification.
__init__
def __init__(node=None)
Initialize MultiClassImageClassificationOutputs.
MultiClassImageClassification Objects
class MultiClassImageClassification(
AssetNode[MultiClassImageClassificationInputs,
MultiClassImageClassificationOutputs])
MultiClassImageClassification node.
Multi Class Image Classification is a machine learning task where an algorithm is trained to categorize images into one of several predefined classes or categories based on their visual content.
InputType: image OutputType: label
AsrGenderClassificationInputs Objects
class AsrGenderClassificationInputs(Inputs)
Input parameters for AsrGenderClassification.
__init__
def __init__(node=None)
Initialize AsrGenderClassificationInputs.
AsrGenderClassificationOutputs Objects
class AsrGenderClassificationOutputs(Outputs)
Output parameters for AsrGenderClassification.
__init__
def __init__(node=None)
Initialize AsrGenderClassificationOutputs.
AsrGenderClassification Objects
class AsrGenderClassification(AssetNode[AsrGenderClassificationInputs,
AsrGenderClassificationOutputs])
AsrGenderClassification node.
The ASR Gender Classification function analyzes audio recordings to determine and classify the speaker's gender based on their voice characteristics.
InputType: audio OutputType: label
SummarizationInputs Objects
class SummarizationInputs(Inputs)
Input parameters for Summarization.
__init__
def __init__(node=None)
Initialize SummarizationInputs.
SummarizationOutputs Objects
class SummarizationOutputs(Outputs)
Output parameters for Summarization.
__init__
def __init__(node=None)
Initialize SummarizationOutputs.
Summarization Objects
class Summarization(AssetNode[SummarizationInputs, SummarizationOutputs])
Summarization node.
Text summarization is the process of distilling the most important information from a source (or sources) to produce an abridged version for a particular user (or users) and task (or tasks)
InputType: text OutputType: text
TopicModelingInputs Objects
class TopicModelingInputs(Inputs)
Input parameters for TopicModeling.
__init__
def __init__(node=None)
Initialize TopicModelingInputs.
TopicModelingOutputs Objects
class TopicModelingOutputs(Outputs)
Output parameters for TopicModeling.
__init__
def __init__(node=None)
Initialize TopicModelingOutputs.
TopicModeling Objects
class TopicModeling(AssetNode[TopicModelingInputs, TopicModelingOutputs])
TopicModeling node.
Topic modeling is a type of statistical modeling for discovering the abstract “topics” that occur in a collection of documents.
InputType: text OutputType: label
AudioReconstructionInputs Objects
class AudioReconstructionInputs(Inputs)
Input parameters for AudioReconstruction.
__init__
def __init__(node=None)
Initialize AudioReconstructionInputs.
AudioReconstructionOutputs Objects
class AudioReconstructionOutputs(Outputs)
Output parameters for AudioReconstruction.
__init__
def __init__(node=None)
Initialize AudioReconstructionOutputs.
AudioReconstruction Objects
class AudioReconstruction(BaseReconstructor[AudioReconstructionInputs,
AudioReconstructionOutputs])
AudioReconstruction node.
Audio Reconstruction is the process of restoring or recreating audio signals from incomplete, damaged, or degraded recordings to achieve a high-quality, accurate representation of the original sound.
InputType: audio OutputType: audio
TextEmbeddingInputs Objects
class TextEmbeddingInputs(Inputs)
Input parameters for TextEmbedding.
__init__
def __init__(node=None)
Initialize TextEmbeddingInputs.
TextEmbeddingOutputs Objects
class TextEmbeddingOutputs(Outputs)
Output parameters for TextEmbedding.
__init__
def __init__(node=None)
Initialize TextEmbeddingOutputs.
TextEmbedding Objects
class TextEmbedding(AssetNode[TextEmbeddingInputs, TextEmbeddingOutputs])
TextEmbedding node.
Text embedding is a process that converts text into numerical vectors, capturing the semantic meaning and contextual relationships of words or phrases, enabling machines to understand and analyze natural language more effectively.
InputType: text OutputType: text
DetectLanguageFromTextInputs Objects
class DetectLanguageFromTextInputs(Inputs)
Input parameters for DetectLanguageFromText.
__init__
def __init__(node=None)
Initialize DetectLanguageFromTextInputs.
DetectLanguageFromTextOutputs Objects
class DetectLanguageFromTextOutputs(Outputs)
Output parameters for DetectLanguageFromText.
__init__
def __init__(node=None)
Initialize DetectLanguageFromTextOutputs.
DetectLanguageFromText Objects
class DetectLanguageFromText(AssetNode[DetectLanguageFromTextInputs,
DetectLanguageFromTextOutputs])
DetectLanguageFromText node.
Detect Language From Text
InputType: text OutputType: label
ExtractAudioFromVideoInputs Objects
class ExtractAudioFromVideoInputs(Inputs)
Input parameters for ExtractAudioFromVideo.
__init__
def __init__(node=None)
Initialize ExtractAudioFromVideoInputs.
ExtractAudioFromVideoOutputs Objects
class ExtractAudioFromVideoOutputs(Outputs)
Output parameters for ExtractAudioFromVideo.
__init__
def __init__(node=None)
Initialize ExtractAudioFromVideoOutputs.
ExtractAudioFromVideo Objects
class ExtractAudioFromVideo(AssetNode[ExtractAudioFromVideoInputs,
ExtractAudioFromVideoOutputs])
ExtractAudioFromVideo node.
Isolates and extracts audio tracks from video files, aiding in audio analysis or transcription tasks.
InputType: video OutputType: audio
SceneDetectionInputs Objects
class SceneDetectionInputs(Inputs)
Input parameters for SceneDetection.
__init__
def __init__(node=None)
Initialize SceneDetectionInputs.
SceneDetectionOutputs Objects
class SceneDetectionOutputs(Outputs)
Output parameters for SceneDetection.
__init__
def __init__(node=None)
Initialize SceneDetectionOutputs.
SceneDetection Objects
class SceneDetection(AssetNode[SceneDetectionInputs, SceneDetectionOutputs])
SceneDetection node.
Scene detection is used for detecting transitions between shots in a video to split it into basic temporal segments.
InputType: image OutputType: text
TextToImageGenerationInputs Objects
class TextToImageGenerationInputs(Inputs)
Input parameters for TextToImageGeneration.
__init__
def __init__(node=None)
Initialize TextToImageGenerationInputs.
TextToImageGenerationOutputs Objects
class TextToImageGenerationOutputs(Outputs)
Output parameters for TextToImageGeneration.
__init__
def __init__(node=None)
Initialize TextToImageGenerationOutputs.
TextToImageGeneration Objects
class TextToImageGeneration(AssetNode[TextToImageGenerationInputs,
TextToImageGenerationOutputs])
TextToImageGeneration node.
Creates a visual representation based on textual input, turning descriptions into pictorial forms. Used in creative processes and content generation.
InputType: text OutputType: image
AutoMaskGenerationInputs Objects
class AutoMaskGenerationInputs(Inputs)
Input parameters for AutoMaskGeneration.
__init__
def __init__(node=None)
Initialize AutoMaskGenerationInputs.
AutoMaskGenerationOutputs Objects
class AutoMaskGenerationOutputs(Outputs)
Output parameters for AutoMaskGeneration.
__init__
def __init__(node=None)
Initialize AutoMaskGenerationOutputs.
AutoMaskGeneration Objects
class AutoMaskGeneration(AssetNode[AutoMaskGenerationInputs,
AutoMaskGenerationOutputs])
AutoMaskGeneration node.
Auto-mask generation refers to the automated process of creating masks in image processing or computer vision, typically for segmentation tasks. A mask is a binary or multi-class image that labels different parts of an image, usually separating the foreground (objects of interest) from the background, or identifying specific object classes in an image.
InputType: image OutputType: label
AudioLanguageIdentificationInputs Objects
class AudioLanguageIdentificationInputs(Inputs)
Input parameters for AudioLanguageIdentification.
__init__
def __init__(node=None)
Initialize AudioLanguageIdentificationInputs.
AudioLanguageIdentificationOutputs Objects
class AudioLanguageIdentificationOutputs(Outputs)
Output parameters for AudioLanguageIdentification.
__init__
def __init__(node=None)
Initialize AudioLanguageIdentificationOutputs.
AudioLanguageIdentification Objects
class AudioLanguageIdentification(AssetNode[AudioLanguageIdentificationInputs,
AudioLanguageIdentificationOutputs]
)
AudioLanguageIdentification node.
Audio Language Identification is a process that involves analyzing an audio recording to determine the language being spoken.
InputType: audio OutputType: label
FacialRecognitionInputs Objects
class FacialRecognitionInputs(Inputs)
Input parameters for FacialRecognition.
__init__
def __init__(node=None)
Initialize FacialRecognitionInputs.
FacialRecognitionOutputs Objects
class FacialRecognitionOutputs(Outputs)
Output parameters for FacialRecognition.
__init__
def __init__(node=None)
Initialize FacialRecognitionOutputs.
FacialRecognition Objects
class FacialRecognition(AssetNode[FacialRecognitionInputs,
FacialRecognitionOutputs])
FacialRecognition node.
A facial recognition system is a technology capable of matching a human face from a digital image or a video frame against a database of faces
InputType: image OutputType: label
QuestionAnsweringInputs Objects
class QuestionAnsweringInputs(Inputs)
Input parameters for QuestionAnswering.
__init__
def __init__(node=None)
Initialize QuestionAnsweringInputs.
QuestionAnsweringOutputs Objects
class QuestionAnsweringOutputs(Outputs)
Output parameters for QuestionAnswering.
__init__
def __init__(node=None)
Initialize QuestionAnsweringOutputs.
QuestionAnswering Objects
class QuestionAnswering(AssetNode[QuestionAnsweringInputs,
QuestionAnsweringOutputs])
QuestionAnswering node.
building systems that automatically answer questions posed by humans in a natural language usually from a given text
InputType: text OutputType: text
ImageImpaintingInputs Objects
class ImageImpaintingInputs(Inputs)
Input parameters for ImageImpainting.
__init__
def __init__(node=None)
Initialize ImageImpaintingInputs.
ImageImpaintingOutputs Objects
class ImageImpaintingOutputs(Outputs)
Output parameters for ImageImpainting.
__init__
def __init__(node=None)
Initialize ImageImpaintingOutputs.
ImageImpainting Objects
class ImageImpainting(AssetNode[ImageImpaintingInputs,
ImageImpaintingOutputs])
ImageImpainting node.
Image inpainting is a process that involves filling in missing or damaged parts of an image in a way that is visually coherent and seamlessly blends with the surrounding areas, often using advanced algorithms and techniques to restore the image to its original or intended appearance.
InputType: image OutputType: image
TextReconstructionInputs Objects
class TextReconstructionInputs(Inputs)
Input parameters for TextReconstruction.
__init__
def __init__(node=None)
Initialize TextReconstructionInputs.
TextReconstructionOutputs Objects
class TextReconstructionOutputs(Outputs)
Output parameters for TextReconstruction.
__init__
def __init__(node=None)
Initialize TextReconstructionOutputs.
TextReconstruction Objects
class TextReconstruction(BaseReconstructor[TextReconstructionInputs,
TextReconstructionOutputs])
TextReconstruction node.
Text Reconstruction is a process that involves piecing together fragmented or incomplete text data to restore it to its original, coherent form.
InputType: text OutputType: text
ScriptExecutionInputs Objects
class ScriptExecutionInputs(Inputs)
Input parameters for ScriptExecution.
__init__
def __init__(node=None)
Initialize ScriptExecutionInputs.
ScriptExecutionOutputs Objects
class ScriptExecutionOutputs(Outputs)
Output parameters for ScriptExecution.
__init__
def __init__(node=None)
Initialize ScriptExecutionOutputs.
ScriptExecution Objects
class ScriptExecution(AssetNode[ScriptExecutionInputs,
ScriptExecutionOutputs])
ScriptExecution node.
Script Execution refers to the process of running a set of programmed instructions or code within a computing environment, enabling the automated performance of tasks, calculations, or operations as defined by the script.
InputType: text OutputType: text
SemanticSegmentationInputs Objects
class SemanticSegmentationInputs(Inputs)
Input parameters for SemanticSegmentation.
__init__
def __init__(node=None)
Initialize SemanticSegmentationInputs.
SemanticSegmentationOutputs Objects
class SemanticSegmentationOutputs(Outputs)
Output parameters for SemanticSegmentation.
__init__
def __init__(node=None)
Initialize SemanticSegmentationOutputs.
SemanticSegmentation Objects
class SemanticSegmentation(AssetNode[SemanticSegmentationInputs,
SemanticSegmentationOutputs])
SemanticSegmentation node.
Semantic segmentation is a computer vision process that involves classifying each pixel in an image into a predefined category, effectively partitioning the image into meaningful segments based on the objects or regions they represent.
InputType: image OutputType: label
AudioEmotionDetectionInputs Objects
class AudioEmotionDetectionInputs(Inputs)
Input parameters for AudioEmotionDetection.
__init__
def __init__(node=None)
Initialize AudioEmotionDetectionInputs.
AudioEmotionDetectionOutputs Objects
class AudioEmotionDetectionOutputs(Outputs)
Output parameters for AudioEmotionDetection.
__init__
def __init__(node=None)
Initialize AudioEmotionDetectionOutputs.
AudioEmotionDetection Objects
class AudioEmotionDetection(AssetNode[AudioEmotionDetectionInputs,
AudioEmotionDetectionOutputs])
AudioEmotionDetection node.
Audio Emotion Detection is a technology that analyzes vocal characteristics and patterns in audio recordings to identify and classify the emotional state of the speaker.
InputType: audio OutputType: label
ImageCaptioningInputs Objects
class ImageCaptioningInputs(Inputs)
Input parameters for ImageCaptioning.
__init__
def __init__(node=None)
Initialize ImageCaptioningInputs.
ImageCaptioningOutputs Objects
class ImageCaptioningOutputs(Outputs)
Output parameters for ImageCaptioning.
__init__
def __init__(node=None)
Initialize ImageCaptioningOutputs.
ImageCaptioning Objects
class ImageCaptioning(AssetNode[ImageCaptioningInputs,
ImageCaptioningOutputs])
ImageCaptioning node.
Image Captioning is a process that involves generating a textual description of an image, typically using machine learning models to analyze the visual content and produce coherent and contextually relevant sentences that describe the objects, actions, and scenes depicted in the image.
InputType: image OutputType: text
SplitOnLinebreakInputs Objects
class SplitOnLinebreakInputs(Inputs)
Input parameters for SplitOnLinebreak.
__init__
def __init__(node=None)
Initialize SplitOnLinebreakInputs.
SplitOnLinebreakOutputs Objects
class SplitOnLinebreakOutputs(Outputs)
Output parameters for SplitOnLinebreak.
__init__
def __init__(node=None)
Initialize SplitOnLinebreakOutputs.
SplitOnLinebreak Objects
class SplitOnLinebreak(BaseSegmentor[SplitOnLinebreakInputs,
SplitOnLinebreakOutputs])
SplitOnLinebreak node.
The "Split On Linebreak" function divides a given string into a list of substrings, using linebreaks (newline characters) as the points of separation.
InputType: text OutputType: text
StyleTransferInputs Objects
class StyleTransferInputs(Inputs)
Input parameters for StyleTransfer.
__init__
def __init__(node=None)
Initialize StyleTransferInputs.
StyleTransferOutputs Objects
class StyleTransferOutputs(Outputs)
Output parameters for StyleTransfer.
__init__
def __init__(node=None)
Initialize StyleTransferOutputs.
StyleTransfer Objects
class StyleTransfer(AssetNode[StyleTransferInputs, StyleTransferOutputs])
StyleTransfer node.
Style Transfer is a technique in artificial intelligence that applies the visual style of one image (such as the brushstrokes of a famous painting) to the content of another image, effectively blending the artistic elements of the first image with the subject matter of the second.
InputType: image OutputType: image
BaseModelInputs Objects
class BaseModelInputs(Inputs)
Input parameters for BaseModel.
__init__
def __init__(node=None)
Initialize BaseModelInputs.
BaseModelOutputs Objects
class BaseModelOutputs(Outputs)
Output parameters for BaseModel.
__init__
def __init__(node=None)
Initialize BaseModelOutputs.
BaseModel Objects
class BaseModel(AssetNode[BaseModelInputs, BaseModelOutputs])
BaseModel node.
The Base-Model function serves as a foundational framework designed to provide essential features and capabilities upon which more specialized or advanced models can be built and customized.
InputType: text OutputType: text
ImageManipulationInputs Objects
class ImageManipulationInputs(Inputs)
Input parameters for ImageManipulation.
__init__
def __init__(node=None)
Initialize ImageManipulationInputs.
ImageManipulationOutputs Objects
class ImageManipulationOutputs(Outputs)
Output parameters for ImageManipulation.
__init__
def __init__(node=None)
Initialize ImageManipulationOutputs.
ImageManipulation Objects
class ImageManipulation(AssetNode[ImageManipulationInputs,
ImageManipulationOutputs])
ImageManipulation node.
Image Manipulation refers to the process of altering or enhancing digital images using various techniques and tools to achieve desired visual effects, correct imperfections, or transform the image's appearance.
InputType: image OutputType: image
VideoEmbeddingInputs Objects
class VideoEmbeddingInputs(Inputs)
Input parameters for VideoEmbedding.
__init__
def __init__(node=None)
Initialize VideoEmbeddingInputs.
VideoEmbeddingOutputs Objects
class VideoEmbeddingOutputs(Outputs)
Output parameters for VideoEmbedding.
__init__
def __init__(node=None)
Initialize VideoEmbeddingOutputs.
VideoEmbedding Objects
class VideoEmbedding(AssetNode[VideoEmbeddingInputs, VideoEmbeddingOutputs])
VideoEmbedding node.
Video Embedding is a process that transforms video content into a fixed- dimensional vector representation, capturing essential features and patterns to facilitate tasks such as retrieval, classification, and recommendation.
InputType: video OutputType: embedding
DialectDetectionInputs Objects
class DialectDetectionInputs(Inputs)
Input parameters for DialectDetection.
__init__
def __init__(node=None)
Initialize DialectDetectionInputs.
DialectDetectionOutputs Objects
class DialectDetectionOutputs(Outputs)
Output parameters for DialectDetection.
__init__
def __init__(node=None)
Initialize DialectDetectionOutputs.
DialectDetection Objects
class DialectDetection(AssetNode[DialectDetectionInputs,
DialectDetectionOutputs])
DialectDetection node.
Identifies specific dialects within a language, aiding in localized content creation or user experience personalization.
InputType: audio OutputType: text
FillTextMaskInputs Objects
class FillTextMaskInputs(Inputs)
Input parameters for FillTextMask.
__init__
def __init__(node=None)
Initialize FillTextMaskInputs.
FillTextMaskOutputs Objects
class FillTextMaskOutputs(Outputs)
Output parameters for FillTextMask.
__init__
def __init__(node=None)
Initialize FillTextMaskOutputs.
FillTextMask Objects
class FillTextMask(AssetNode[FillTextMaskInputs, FillTextMaskOutputs])
FillTextMask node.
Completes missing parts of a text based on the context, ideal for content generation or data augmentation tasks.
InputType: text OutputType: text
ActivityDetectionInputs Objects
class ActivityDetectionInputs(Inputs)
Input parameters for ActivityDetection.
__init__
def __init__(node=None)
Initialize ActivityDetectionInputs.
ActivityDetectionOutputs Objects
class ActivityDetectionOutputs(Outputs)
Output parameters for ActivityDetection.
__init__
def __init__(node=None)
Initialize ActivityDetectionOutputs.
ActivityDetection Objects
class ActivityDetection(AssetNode[ActivityDetectionInputs,
ActivityDetectionOutputs])
ActivityDetection node.
detection of the presence or absence of human speech, used in speech processing.
InputType: audio OutputType: label
SelectSupplierForTranslationInputs Objects
class SelectSupplierForTranslationInputs(Inputs)
Input parameters for SelectSupplierForTranslation.
__init__
def __init__(node=None)
Initialize SelectSupplierForTranslationInputs.
SelectSupplierForTranslationOutputs Objects
class SelectSupplierForTranslationOutputs(Outputs)
Output parameters for SelectSupplierForTranslation.
__init__
def __init__(node=None)
Initialize SelectSupplierForTranslationOutputs.
SelectSupplierForTranslation Objects
class SelectSupplierForTranslation(
AssetNode[SelectSupplierForTranslationInputs,
SelectSupplierForTranslationOutputs])
SelectSupplierForTranslation node.
Supplier For Translation
InputType: text OutputType: label
ExpressionDetectionInputs Objects
class ExpressionDetectionInputs(Inputs)
Input parameters for ExpressionDetection.
__init__
def __init__(node=None)
Initialize ExpressionDetectionInputs.
ExpressionDetectionOutputs Objects
class ExpressionDetectionOutputs(Outputs)
Output parameters for ExpressionDetection.
__init__
def __init__(node=None)
Initialize ExpressionDetectionOutputs.
ExpressionDetection Objects
class ExpressionDetection(AssetNode[ExpressionDetectionInputs,
ExpressionDetectionOutputs])
ExpressionDetection node.
Expression Detection is the process of identifying and analyzing facial expressions to interpret emotions or intentions using AI and computer vision techniques.
InputType: text OutputType: label
VideoGenerationInputs Objects
class VideoGenerationInputs(Inputs)
Input parameters for VideoGeneration.
__init__
def __init__(node=None)
Initialize VideoGenerationInputs.
VideoGenerationOutputs Objects
class VideoGenerationOutputs(Outputs)
Output parameters for VideoGeneration.
__init__
def __init__(node=None)
Initialize VideoGenerationOutputs.
VideoGeneration Objects
class VideoGeneration(AssetNode[VideoGenerationInputs,
VideoGenerationOutputs])
VideoGeneration node.
Produces video content based on specific inputs or datasets. Can be used for simulations, animations, or even deepfake detection.
InputType: text OutputType: video
ImageAnalysisInputs Objects
class ImageAnalysisInputs(Inputs)
Input parameters for ImageAnalysis.
__init__
def __init__(node=None)
Initialize ImageAnalysisInputs.
ImageAnalysisOutputs Objects
class ImageAnalysisOutputs(Outputs)
Output parameters for ImageAnalysis.
__init__
def __init__(node=None)
Initialize ImageAnalysisOutputs.
ImageAnalysis Objects
class ImageAnalysis(AssetNode[ImageAnalysisInputs, ImageAnalysisOutputs])
ImageAnalysis node.
Image analysis is the extraction of meaningful information from images
InputType: image OutputType: label
NoiseRemovalInputs Objects
class NoiseRemovalInputs(Inputs)
Input parameters for NoiseRemoval.
__init__
def __init__(node=None)
Initialize NoiseRemovalInputs.
NoiseRemovalOutputs Objects
class NoiseRemovalOutputs(Outputs)
Output parameters for NoiseRemoval.
__init__
def __init__(node=None)
Initialize NoiseRemovalOutputs.
NoiseRemoval Objects
class NoiseRemoval(AssetNode[NoiseRemovalInputs, NoiseRemovalOutputs])
NoiseRemoval node.
Noise Removal is a process that involves identifying and eliminating unwanted random variations or disturbances from an audio signal to enhance the clarity and quality of the underlying information.
InputType: audio OutputType: audio
ImageAndVideoAnalysisInputs Objects
class ImageAndVideoAnalysisInputs(Inputs)
Input parameters for ImageAndVideoAnalysis.
__init__
def __init__(node=None)
Initialize ImageAndVideoAnalysisInputs.
ImageAndVideoAnalysisOutputs Objects
class ImageAndVideoAnalysisOutputs(Outputs)
Output parameters for ImageAndVideoAnalysis.
__init__
def __init__(node=None)
Initialize ImageAndVideoAnalysisOutputs.
ImageAndVideoAnalysis Objects
class ImageAndVideoAnalysis(AssetNode[ImageAndVideoAnalysisInputs,
ImageAndVideoAnalysisOutputs])
ImageAndVideoAnalysis node.
InputType: image OutputType: text
KeywordExtractionInputs Objects
class KeywordExtractionInputs(Inputs)
Input parameters for KeywordExtraction.
__init__
def __init__(node=None)
Initialize KeywordExtractionInputs.
KeywordExtractionOutputs Objects
class KeywordExtractionOutputs(Outputs)
Output parameters for KeywordExtraction.
__init__
def __init__(node=None)
Initialize KeywordExtractionOutputs.
KeywordExtraction Objects
class KeywordExtraction(AssetNode[KeywordExtractionInputs,
KeywordExtractionOutputs])
KeywordExtraction node.
It helps concise the text and obtain relevant keywords Example use-cases are finding topics of interest from a news article and identifying the problems based on customer reviews and so.
InputType: text OutputType: label
SplitOnSilenceInputs Objects
class SplitOnSilenceInputs(Inputs)
Input parameters for SplitOnSilence.
__init__
def __init__(node=None)
Initialize SplitOnSilenceInputs.
SplitOnSilenceOutputs Objects
class SplitOnSilenceOutputs(Outputs)
Output parameters for SplitOnSilence.
__init__
def __init__(node=None)
Initialize SplitOnSilenceOutputs.
SplitOnSilence Objects
class SplitOnSilence(AssetNode[SplitOnSilenceInputs, SplitOnSilenceOutputs])
SplitOnSilence node.
The "Split On Silence" function divides an audio recording into separate segments based on periods of silence, allowing for easier editing and analysis of individual sections.
InputType: audio OutputType: audio
IntentRecognitionInputs Objects
class IntentRecognitionInputs(Inputs)
Input parameters for IntentRecognition.
__init__
def __init__(node=None)
Initialize IntentRecognitionInputs.
IntentRecognitionOutputs Objects
class IntentRecognitionOutputs(Outputs)
Output parameters for IntentRecognition.
__init__
def __init__(node=None)
Initialize IntentRecognitionOutputs.
IntentRecognition Objects
class IntentRecognition(AssetNode[IntentRecognitionInputs,
IntentRecognitionOutputs])
IntentRecognition node.
classify the user's utterance (provided in varied natural language) or text into one of several predefined classes, that is, intents.
InputType: audio OutputType: text
DepthEstimationInputs Objects
class DepthEstimationInputs(Inputs)
Input parameters for DepthEstimation.
__init__
def __init__(node=None)
Initialize DepthEstimationInputs.
DepthEstimationOutputs Objects
class DepthEstimationOutputs(Outputs)
Output parameters for DepthEstimation.
__init__
def __init__(node=None)
Initialize DepthEstimationOutputs.
DepthEstimation Objects
class DepthEstimation(AssetNode[DepthEstimationInputs,
DepthEstimationOutputs])
DepthEstimation node.
Depth estimation is a computational process that determines the distance of objects from a viewpoint, typically using visual data from cameras or sensors to create a three-dimensional understanding of a scene.
InputType: image OutputType: text
ConnectorInputs Objects
class ConnectorInputs(Inputs)
Input parameters for Connector.
__init__
def __init__(node=None)
Initialize ConnectorInputs.
ConnectorOutputs Objects
class ConnectorOutputs(Outputs)
Output parameters for Connector.
__init__
def __init__(node=None)
Initialize ConnectorOutputs.
Connector Objects
class Connector(AssetNode[ConnectorInputs, ConnectorOutputs])
Connector node.
Connectors are integration that allow you to connect your AI agents to external tools
InputType: text OutputType: text
SpeakerRecognitionInputs Objects
class SpeakerRecognitionInputs(Inputs)
Input parameters for SpeakerRecognition.
__init__
def __init__(node=None)
Initialize SpeakerRecognitionInputs.
SpeakerRecognitionOutputs Objects
class SpeakerRecognitionOutputs(Outputs)
Output parameters for SpeakerRecognition.
__init__
def __init__(node=None)
Initialize SpeakerRecognitionOutputs.
SpeakerRecognition Objects
class SpeakerRecognition(AssetNode[SpeakerRecognitionInputs,
SpeakerRecognitionOutputs])
SpeakerRecognition node.
In speaker identification, an utterance from an unknown speaker is analyzed and compared with speech models of known speakers.
InputType: audio OutputType: label
SyntaxAnalysisInputs Objects
class SyntaxAnalysisInputs(Inputs)
Input parameters for SyntaxAnalysis.
__init__
def __init__(node=None)
Initialize SyntaxAnalysisInputs.
SyntaxAnalysisOutputs Objects
class SyntaxAnalysisOutputs(Outputs)
Output parameters for SyntaxAnalysis.
__init__
def __init__(node=None)
Initialize SyntaxAnalysisOutputs.
SyntaxAnalysis Objects
class SyntaxAnalysis(AssetNode[SyntaxAnalysisInputs, SyntaxAnalysisOutputs])
SyntaxAnalysis node.
Is the process of analyzing natural language with the rules of a formal grammar. Grammatical rules are applied to categories and groups of words, not individual words. Syntactic analysis basically assigns a semantic structure to text.
InputType: text OutputType: text
EntitySentimentAnalysisInputs Objects
class EntitySentimentAnalysisInputs(Inputs)
Input parameters for EntitySentimentAnalysis.
__init__
def __init__(node=None)
Initialize EntitySentimentAnalysisInputs.
EntitySentimentAnalysisOutputs Objects
class EntitySentimentAnalysisOutputs(Outputs)
Output parameters for EntitySentimentAnalysis.
__init__
def __init__(node=None)
Initialize EntitySentimentAnalysisOutputs.
EntitySentimentAnalysis Objects
class EntitySentimentAnalysis(AssetNode[EntitySentimentAnalysisInputs,
EntitySentimentAnalysisOutputs])
EntitySentimentAnalysis node.
Entity Sentiment Analysis combines both entity analysis and sentiment analysis and attempts to determine the sentiment (positive or negative) expressed about entities within the text.
InputType: text OutputType: label
ClassificationMetricInputs Objects
class ClassificationMetricInputs(Inputs)
Input parameters for ClassificationMetric.
__init__
def __init__(node=None)
Initialize ClassificationMetricInputs.
ClassificationMetricOutputs Objects
class ClassificationMetricOutputs(Outputs)
Output parameters for ClassificationMetric.
__init__
def __init__(node=None)
Initialize ClassificationMetricOutputs.
ClassificationMetric Objects
class ClassificationMetric(BaseMetric[ClassificationMetricInputs,
ClassificationMetricOutputs])
ClassificationMetric node.
A Classification Metric is a quantitative measure used to evaluate the quality and effectiveness of classification models.
InputType: text OutputType: text
TextDetectionInputs Objects
class TextDetectionInputs(Inputs)
Input parameters for TextDetection.
__init__
def __init__(node=None)
Initialize TextDetectionInputs.
TextDetectionOutputs Objects
class TextDetectionOutputs(Outputs)
Output parameters for TextDetection.
__init__
def __init__(node=None)
Initialize TextDetectionOutputs.
TextDetection Objects
class TextDetection(AssetNode[TextDetectionInputs, TextDetectionOutputs])
TextDetection node.
detect text regions in the complex background and label them with bounding boxes.
InputType: image OutputType: text
GuardrailsInputs Objects
class GuardrailsInputs(Inputs)
Input parameters for Guardrails.
__init__
def __init__(node=None)
Initialize GuardrailsInputs.
GuardrailsOutputs Objects
class GuardrailsOutputs(Outputs)
Output parameters for Guardrails.
__init__
def __init__(node=None)
Initialize GuardrailsOutputs.
Guardrails Objects
class Guardrails(AssetNode[GuardrailsInputs, GuardrailsOutputs])
Guardrails node.
Guardrails are governance rules that enforce security, compliance, and operational best practices, helping prevent mistakes and detect suspicious activity
InputType: text OutputType: text
EmotionDetectionInputs Objects
class EmotionDetectionInputs(Inputs)
Input parameters for EmotionDetection.
__init__
def __init__(node=None)
Initialize EmotionDetectionInputs.
EmotionDetectionOutputs Objects
class EmotionDetectionOutputs(Outputs)
Output parameters for EmotionDetection.
__init__
def __init__(node=None)
Initialize EmotionDetectionOutputs.
EmotionDetection Objects
class EmotionDetection(AssetNode[EmotionDetectionInputs,
EmotionDetectionOutputs])
EmotionDetection node.
Identifies human emotions from text or audio, enhancing user experience in chatbots or customer feedback analysis.
InputType: text OutputType: label
VideoForcedAlignmentInputs Objects
class VideoForcedAlignmentInputs(Inputs)
Input parameters for VideoForcedAlignment.
__init__
def __init__(node=None)
Initialize VideoForcedAlignmentInputs.
VideoForcedAlignmentOutputs Objects
class VideoForcedAlignmentOutputs(Outputs)
Output parameters for VideoForcedAlignment.
__init__
def __init__(node=None)
Initialize VideoForcedAlignmentOutputs.
VideoForcedAlignment Objects
class VideoForcedAlignment(AssetNode[VideoForcedAlignmentInputs,
VideoForcedAlignmentOutputs])
VideoForcedAlignment node.
Aligns the transcription of spoken content in a video with its corresponding timecodes, facilitating subtitle creation.
InputType: video OutputType: video
ImageContentModerationInputs Objects
class ImageContentModerationInputs(Inputs)
Input parameters for ImageContentModeration.
__init__
def __init__(node=None)
Initialize ImageContentModerationInputs.
ImageContentModerationOutputs Objects
class ImageContentModerationOutputs(Outputs)
Output parameters for ImageContentModeration.
__init__
def __init__(node=None)
Initialize ImageContentModerationOutputs.
ImageContentModeration Objects
class ImageContentModeration(AssetNode[ImageContentModerationInputs,
ImageContentModerationOutputs])
ImageContentModeration node.
Detects and filters out inappropriate or harmful images, essential for platforms with user-generated visual content.
InputType: image OutputType: label
TextSummarizationInputs Objects
class TextSummarizationInputs(Inputs)
Input parameters for TextSummarization.
__init__
def __init__(node=None)
Initialize TextSummarizationInputs.
TextSummarizationOutputs Objects
class TextSummarizationOutputs(Outputs)
Output parameters for TextSummarization.
__init__
def __init__(node=None)
Initialize TextSummarizationOutputs.
TextSummarization Objects
class TextSummarization(AssetNode[TextSummarizationInputs,
TextSummarizationOutputs])
TextSummarization node.
Extracts the main points from a larger body of text, producing a concise summary without losing the primary message.
InputType: text OutputType: text
ImageToVideoGenerationInputs Objects
class ImageToVideoGenerationInputs(Inputs)
Input parameters for ImageToVideoGeneration.
__init__
def __init__(node=None)
Initialize ImageToVideoGenerationInputs.
ImageToVideoGenerationOutputs Objects
class ImageToVideoGenerationOutputs(Outputs)
Output parameters for ImageToVideoGeneration.
__init__
def __init__(node=None)
Initialize ImageToVideoGenerationOutputs.
ImageToVideoGeneration Objects
class ImageToVideoGeneration(AssetNode[ImageToVideoGenerationInputs,
ImageToVideoGenerationOutputs])
ImageToVideoGeneration node.
The Image To Video Generation function transforms a series of static images into a cohesive, dynamic video sequence, often incorporating transitions, effects, and synchronization with audio to create a visually engaging narrative.
InputType: image OutputType: video
VideoUnderstandingInputs Objects
class VideoUnderstandingInputs(Inputs)
Input parameters for VideoUnderstanding.
__init__
def __init__(node=None)
Initialize VideoUnderstandingInputs.
VideoUnderstandingOutputs Objects
class VideoUnderstandingOutputs(Outputs)
Output parameters for VideoUnderstanding.
__init__
def __init__(node=None)
Initialize VideoUnderstandingOutputs.
VideoUnderstanding Objects
class VideoUnderstanding(AssetNode[VideoUnderstandingInputs,
VideoUnderstandingOutputs])
VideoUnderstanding node.
Video Understanding is the process of analyzing and interpreting video content to extract meaningful information, such as identifying objects, actions, events, and contextual relationships within the footage.
InputType: video OutputType: text
TextGenerationMetricDefaultInputs Objects
class TextGenerationMetricDefaultInputs(Inputs)
Input parameters for TextGenerationMetricDefault.
__init__
def __init__(node=None)
Initialize TextGenerationMetricDefaultInputs.
TextGenerationMetricDefaultOutputs Objects
class TextGenerationMetricDefaultOutputs(Outputs)
Output parameters for TextGenerationMetricDefault.
__init__
def __init__(node=None)
Initialize TextGenerationMetricDefaultOutputs.
TextGenerationMetricDefault Objects
class TextGenerationMetricDefault(
BaseMetric[TextGenerationMetricDefaultInputs,
TextGenerationMetricDefaultOutputs])
TextGenerationMetricDefault node.
The "Text Generation Metric Default" function provides a standard set of evaluation metrics for assessing the quality and performance of text generation models.
InputType: text OutputType: text
TextToVideoGenerationInputs Objects
class TextToVideoGenerationInputs(Inputs)
Input parameters for TextToVideoGeneration.
__init__
def __init__(node=None)
Initialize TextToVideoGenerationInputs.
TextToVideoGenerationOutputs Objects
class TextToVideoGenerationOutputs(Outputs)
Output parameters for TextToVideoGeneration.
__init__
def __init__(node=None)
Initialize TextToVideoGenerationOutputs.
TextToVideoGeneration Objects
class TextToVideoGeneration(AssetNode[TextToVideoGenerationInputs,
TextToVideoGenerationOutputs])
TextToVideoGeneration node.
Text To Video Generation is a process that converts written descriptions or scripts into dynamic, visual video content using advanced algorithms and artificial intelligence.
InputType: text OutputType: video
VideoLabelDetectionInputs Objects
class VideoLabelDetectionInputs(Inputs)
Input parameters for VideoLabelDetection.
__init__
def __init__(node=None)
Initialize VideoLabelDetectionInputs.
VideoLabelDetectionOutputs Objects
class VideoLabelDetectionOutputs(Outputs)
Output parameters for VideoLabelDetection.
__init__
def __init__(node=None)
Initialize VideoLabelDetectionOutputs.
VideoLabelDetection Objects
class VideoLabelDetection(AssetNode[VideoLabelDetectionInputs,
VideoLabelDetectionOutputs])
VideoLabelDetection node.
Identifies and tags objects, scenes, or activities within a video. Useful for content indexing and recommendation systems.
InputType: video OutputType: label
TextSpamDetectionInputs Objects
class TextSpamDetectionInputs(Inputs)
Input parameters for TextSpamDetection.
__init__
def __init__(node=None)
Initialize TextSpamDetectionInputs.
TextSpamDetectionOutputs Objects
class TextSpamDetectionOutputs(Outputs)
Output parameters for TextSpamDetection.
__init__
def __init__(node=None)
Initialize TextSpamDetectionOutputs.
TextSpamDetection Objects
class TextSpamDetection(AssetNode[TextSpamDetectionInputs,
TextSpamDetectionOutputs])
TextSpamDetection node.
Identifies and filters out unwanted or irrelevant text content, ideal for moderating user-generated content or ensuring quality in communication platforms.
InputType: text OutputType: label
TextContentModerationInputs Objects
class TextContentModerationInputs(Inputs)
Input parameters for TextContentModeration.
__init__
def __init__(node=None)
Initialize TextContentModerationInputs.
TextContentModerationOutputs Objects
class TextContentModerationOutputs(Outputs)
Output parameters for TextContentModeration.
__init__
def __init__(node=None)
Initialize TextContentModerationOutputs.
TextContentModeration Objects
class TextContentModeration(AssetNode[TextContentModerationInputs,
TextContentModerationOutputs])
TextContentModeration node.
Scans and identifies potentially harmful, offensive, or inappropriate textual content, ensuring safer user environments.
InputType: text OutputType: label
AudioTranscriptImprovementInputs Objects
class AudioTranscriptImprovementInputs(Inputs)
Input parameters for AudioTranscriptImprovement.
__init__
def __init__(node=None)
Initialize AudioTranscriptImprovementInputs.
AudioTranscriptImprovementOutputs Objects
class AudioTranscriptImprovementOutputs(Outputs)
Output parameters for AudioTranscriptImprovement.
__init__
def __init__(node=None)
Initialize AudioTranscriptImprovementOutputs.
AudioTranscriptImprovement Objects
class AudioTranscriptImprovement(AssetNode[AudioTranscriptImprovementInputs,
AudioTranscriptImprovementOutputs])
AudioTranscriptImprovement node.
Refines and corrects transcriptions generated from audio data, improving readability and accuracy.
InputType: audio OutputType: text
AudioTranscriptAnalysisInputs Objects
class AudioTranscriptAnalysisInputs(Inputs)
Input parameters for AudioTranscriptAnalysis.
__init__
def __init__(node=None)
Initialize AudioTranscriptAnalysisInputs.
AudioTranscriptAnalysisOutputs Objects
class AudioTranscriptAnalysisOutputs(Outputs)
Output parameters for AudioTranscriptAnalysis.
__init__
def __init__(node=None)
Initialize AudioTranscriptAnalysisOutputs.
AudioTranscriptAnalysis Objects
class AudioTranscriptAnalysis(AssetNode[AudioTranscriptAnalysisInputs,
AudioTranscriptAnalysisOutputs])
AudioTranscriptAnalysis node.
Analyzes transcribed audio data for insights, patterns, or specific information extraction.
InputType: audio OutputType: text
SpeechNonSpeechClassificationInputs Objects
class SpeechNonSpeechClassificationInputs(Inputs)
Input parameters for SpeechNonSpeechClassification.
__init__
def __init__(node=None)
Initialize SpeechNonSpeechClassificationInputs.
SpeechNonSpeechClassificationOutputs Objects
class SpeechNonSpeechClassificationOutputs(Outputs)
Output parameters for SpeechNonSpeechClassification.
__init__
def __init__(node=None)
Initialize SpeechNonSpeechClassificationOutputs.
SpeechNonSpeechClassification Objects
class SpeechNonSpeechClassification(
AssetNode[SpeechNonSpeechClassificationInputs,
SpeechNonSpeechClassificationOutputs])
SpeechNonSpeechClassification node.
Differentiates between speech and non-speech audio segments. Great for editing software and transcription services to exclude irrelevant audio.
InputType: audio OutputType: label
AudioGenerationMetricInputs Objects
class AudioGenerationMetricInputs(Inputs)
Input parameters for AudioGenerationMetric.
__init__
def __init__(node=None)
Initialize AudioGenerationMetricInputs.
AudioGenerationMetricOutputs Objects
class AudioGenerationMetricOutputs(Outputs)
Output parameters for AudioGenerationMetric.
__init__
def __init__(node=None)
Initialize AudioGenerationMetricOutputs.
AudioGenerationMetric Objects
class AudioGenerationMetric(BaseMetric[AudioGenerationMetricInputs,
AudioGenerationMetricOutputs])
AudioGenerationMetric node.
The Audio Generation Metric is a quantitative measure used to evaluate the quality, accuracy, and overall performance of audio generated by artificial intelligence systems, often considering factors such as fidelity, intelligibility, and similarity to human-produced audio.
InputType: text OutputType: text
NamedEntityRecognitionInputs Objects
class NamedEntityRecognitionInputs(Inputs)
Input parameters for NamedEntityRecognition.
__init__
def __init__(node=None)
Initialize NamedEntityRecognitionInputs.
NamedEntityRecognitionOutputs Objects
class NamedEntityRecognitionOutputs(Outputs)
Output parameters for NamedEntityRecognition.
__init__
def __init__(node=None)
Initialize NamedEntityRecognitionOutputs.
NamedEntityRecognition Objects
class NamedEntityRecognition(AssetNode[NamedEntityRecognitionInputs,
NamedEntityRecognitionOutputs])
NamedEntityRecognition node.
Identifies and classifies named entities (e.g., persons, organizations, locations) within text. Useful for information extraction, content tagging, and search enhancements.
InputType: text OutputType: label
SpeechSynthesisInputs Objects
class SpeechSynthesisInputs(Inputs)
Input parameters for SpeechSynthesis.
__init__
def __init__(node=None)
Initialize SpeechSynthesisInputs.
SpeechSynthesisOutputs Objects
class SpeechSynthesisOutputs(Outputs)
Output parameters for SpeechSynthesis.
__init__
def __init__(node=None)
Initialize SpeechSynthesisOutputs.
SpeechSynthesis Objects
class SpeechSynthesis(AssetNode[SpeechSynthesisInputs,
SpeechSynthesisOutputs])
SpeechSynthesis node.
Generates human-like speech from written text. Ideal for text-to-speech applications, audiobooks, and voice assistants.
InputType: text OutputType: audio
DocumentInformationExtractionInputs Objects
class DocumentInformationExtractionInputs(Inputs)
Input parameters for DocumentInformationExtraction.
__init__
def __init__(node=None)
Initialize DocumentInformationExtractionInputs.
DocumentInformationExtractionOutputs Objects
class DocumentInformationExtractionOutputs(Outputs)
Output parameters for DocumentInformationExtraction.
__init__
def __init__(node=None)
Initialize DocumentInformationExtractionOutputs.
DocumentInformationExtraction Objects
class DocumentInformationExtraction(
AssetNode[DocumentInformationExtractionInputs,
DocumentInformationExtractionOutputs])
DocumentInformationExtraction node.
Document Information Extraction is the process of automatically identifying, extracting, and structuring relevant data from unstructured or semi-structured documents, such as invoices, receipts, contracts, and forms, to facilitate easier data management and analysis.
InputType: image OutputType: text
OcrInputs Objects
class OcrInputs(Inputs)
Input parameters for Ocr.
__init__
def __init__(node=None)
Initialize OcrInputs.
OcrOutputs Objects
class OcrOutputs(Outputs)
Output parameters for Ocr.
__init__
def __init__(node=None)
Initialize OcrOutputs.
Ocr Objects
class Ocr(AssetNode[OcrInputs, OcrOutputs])
Ocr node.
Converts images of typed, handwritten, or printed text into machine-encoded text. Used in digitizing printed texts for data retrieval.
InputType: image OutputType: text
SubtitlingTranslationInputs Objects
class SubtitlingTranslationInputs(Inputs)
Input parameters for SubtitlingTranslation.
__init__
def __init__(node=None)
Initialize SubtitlingTranslationInputs.
SubtitlingTranslationOutputs Objects
class SubtitlingTranslationOutputs(Outputs)
Output parameters for SubtitlingTranslation.
__init__
def __init__(node=None)
Initialize SubtitlingTranslationOutputs.
SubtitlingTranslation Objects
class SubtitlingTranslation(AssetNode[SubtitlingTranslationInputs,
SubtitlingTranslationOutputs])
SubtitlingTranslation node.
Converts the text of subtitles from one language to another, ensuring context and cultural nuances are maintained. Essential for global content distribution.
InputType: text OutputType: text
TextToAudioInputs Objects
class TextToAudioInputs(Inputs)
Input parameters for TextToAudio.
__init__
def __init__(node=None)
Initialize TextToAudioInputs.
TextToAudioOutputs Objects
class TextToAudioOutputs(Outputs)
Output parameters for TextToAudio.
__init__
def __init__(node=None)
Initialize TextToAudioOutputs.
TextToAudio Objects
class TextToAudio(AssetNode[TextToAudioInputs, TextToAudioOutputs])
TextToAudio node.
The Text to Audio function converts written text into spoken words, allowing users to listen to the content instead of reading it.
InputType: text OutputType: audio
MultilingualSpeechRecognitionInputs Objects
class MultilingualSpeechRecognitionInputs(Inputs)
Input parameters for MultilingualSpeechRecognition.
__init__
def __init__(node=None)
Initialize MultilingualSpeechRecognitionInputs.
MultilingualSpeechRecognitionOutputs Objects
class MultilingualSpeechRecognitionOutputs(Outputs)
Output parameters for MultilingualSpeechRecognition.
__init__
def __init__(node=None)
Initialize MultilingualSpeechRecognitionOutputs.
MultilingualSpeechRecognition Objects
class MultilingualSpeechRecognition(
AssetNode[MultilingualSpeechRecognitionInputs,
MultilingualSpeechRecognitionOutputs])
MultilingualSpeechRecognition node.
Multilingual Speech Recognition is a technology that enables the automatic transcription of spoken language into text across multiple languages, allowing for seamless communication and understanding in diverse linguistic contexts.
InputType: audio OutputType: text
OffensiveLanguageIdentificationInputs Objects
class OffensiveLanguageIdentificationInputs(Inputs)
Input parameters for OffensiveLanguageIdentification.
__init__
def __init__(node=None)
Initialize OffensiveLanguageIdentificationInputs.
OffensiveLanguageIdentificationOutputs Objects
class OffensiveLanguageIdentificationOutputs(Outputs)
Output parameters for OffensiveLanguageIdentification.
__init__
def __init__(node=None)
Initialize OffensiveLanguageIdentificationOutputs.
OffensiveLanguageIdentification Objects
class OffensiveLanguageIdentification(
AssetNode[OffensiveLanguageIdentificationInputs,
OffensiveLanguageIdentificationOutputs])
OffensiveLanguageIdentification node.
Detects language or phrases that might be considered offensive, aiding in content moderation and creating respectful user interactions.
InputType: text OutputType: label
BenchmarkScoringMtInputs Objects
class BenchmarkScoringMtInputs(Inputs)
Input parameters for BenchmarkScoringMt.
__init__
def __init__(node=None)
Initialize BenchmarkScoringMtInputs.
BenchmarkScoringMtOutputs Objects
class BenchmarkScoringMtOutputs(Outputs)
Output parameters for BenchmarkScoringMt.
__init__
def __init__(node=None)
Initialize BenchmarkScoringMtOutputs.
BenchmarkScoringMt Objects
class BenchmarkScoringMt(AssetNode[BenchmarkScoringMtInputs,
BenchmarkScoringMtOutputs])
BenchmarkScoringMt node.
Benchmark Scoring MT is a function designed to evaluate and score machine translation systems by comparing their output against a set of predefined benchmarks, thereby assessing their accuracy and performance.
InputType: text OutputType: label
SpeakerDiarizationAudioInputs Objects
class SpeakerDiarizationAudioInputs(Inputs)
Input parameters for SpeakerDiarizationAudio.
__init__
def __init__(node=None)
Initialize SpeakerDiarizationAudioInputs.
SpeakerDiarizationAudioOutputs Objects
class SpeakerDiarizationAudioOutputs(Outputs)
Output parameters for SpeakerDiarizationAudio.
__init__
def __init__(node=None)
Initialize SpeakerDiarizationAudioOutputs.
SpeakerDiarizationAudio Objects
class SpeakerDiarizationAudio(BaseSegmentor[SpeakerDiarizationAudioInputs,
SpeakerDiarizationAudioOutputs])
SpeakerDiarizationAudio node.
Identifies individual speakers and their respective speech segments within an audio clip. Ideal for multi-speaker recordings or conference calls.
InputType: audio OutputType: label
VoiceCloningInputs Objects
class VoiceCloningInputs(Inputs)
Input parameters for VoiceCloning.
__init__
def __init__(node=None)
Initialize VoiceCloningInputs.
VoiceCloningOutputs Objects
class VoiceCloningOutputs(Outputs)
Output parameters for VoiceCloning.
__init__
def __init__(node=None)
Initialize VoiceCloningOutputs.
VoiceCloning Objects
class VoiceCloning(AssetNode[VoiceCloningInputs, VoiceCloningOutputs])
VoiceCloning node.
Replicates a person's voice based on a sample, allowing for the generation of speech in that person's tone and style. Used cautiously due to ethical considerations.
InputType: text OutputType: audio
SearchInputs Objects
class SearchInputs(Inputs)
Input parameters for Search.
__init__
def __init__(node=None)
Initialize SearchInputs.
SearchOutputs Objects
class SearchOutputs(Outputs)
Output parameters for Search.
__init__
def __init__(node=None)
Initialize SearchOutputs.
Search Objects
class Search(AssetNode[SearchInputs, SearchOutputs])
Search node.
An algorithm that identifies and returns data or items that match particular keywords or conditions from a dataset. A fundamental tool for databases and websites.
InputType: text OutputType: text
ObjectDetectionInputs Objects
class ObjectDetectionInputs(Inputs)
Input parameters for ObjectDetection.
__init__
def __init__(node=None)
Initialize ObjectDetectionInputs.
ObjectDetectionOutputs Objects
class ObjectDetectionOutputs(Outputs)
Output parameters for ObjectDetection.
__init__
def __init__(node=None)
Initialize ObjectDetectionOutputs.
ObjectDetection Objects
class ObjectDetection(AssetNode[ObjectDetectionInputs,
ObjectDetectionOutputs])
ObjectDetection node.
Object Detection is a computer vision technology that identifies and locates objects within an image, typically by drawing bounding boxes around the detected objects and classifying them into predefined categories.
InputType: video OutputType: text
DiacritizationInputs Objects
class DiacritizationInputs(Inputs)
Input parameters for Diacritization.
__init__
def __init__(node=None)
Initialize DiacritizationInputs.
DiacritizationOutputs Objects
class DiacritizationOutputs(Outputs)
Output parameters for Diacritization.
__init__
def __init__(node=None)
Initialize DiacritizationOutputs.
Diacritization Objects
class Diacritization(AssetNode[DiacritizationInputs, DiacritizationOutputs])
Diacritization node.
Adds diacritical marks to text, essential for languages where meaning can change based on diacritics.
InputType: text OutputType: text
SpeakerDiarizationVideoInputs Objects
class SpeakerDiarizationVideoInputs(Inputs)
Input parameters for SpeakerDiarizationVideo.
__init__
def __init__(node=None)
Initialize SpeakerDiarizationVideoInputs.
SpeakerDiarizationVideoOutputs Objects
class SpeakerDiarizationVideoOutputs(Outputs)
Output parameters for SpeakerDiarizationVideo.
__init__
def __init__(node=None)
Initialize SpeakerDiarizationVideoOutputs.
SpeakerDiarizationVideo Objects
class SpeakerDiarizationVideo(AssetNode[SpeakerDiarizationVideoInputs,
SpeakerDiarizationVideoOutputs])
SpeakerDiarizationVideo node.
Segments a video based on different speakers, identifying when each individual speaks. Useful for transcriptions and understanding multi-person conversations.
InputType: video OutputType: label
AudioForcedAlignmentInputs Objects
class AudioForcedAlignmentInputs(Inputs)
Input parameters for AudioForcedAlignment.
__init__
def __init__(node=None)
Initialize AudioForcedAlignmentInputs.
AudioForcedAlignmentOutputs Objects
class AudioForcedAlignmentOutputs(Outputs)
Output parameters for AudioForcedAlignment.
__init__
def __init__(node=None)
Initialize AudioForcedAlignmentOutputs.
AudioForcedAlignment Objects
class AudioForcedAlignment(AssetNode[AudioForcedAlignmentInputs,
AudioForcedAlignmentOutputs])
AudioForcedAlignment node.
Synchronizes phonetic and phonological text with the corresponding segments in an audio file. Useful in linguistic research and detailed transcription tasks.
InputType: audio OutputType: audio
TokenClassificationInputs Objects
class TokenClassificationInputs(Inputs)
Input parameters for TokenClassification.
__init__
def __init__(node=None)
Initialize TokenClassificationInputs.
TokenClassificationOutputs Objects
class TokenClassificationOutputs(Outputs)
Output parameters for TokenClassification.
__init__
def __init__(node=None)
Initialize TokenClassificationOutputs.
TokenClassification Objects
class TokenClassification(AssetNode[TokenClassificationInputs,
TokenClassificationOutputs])
TokenClassification node.
Token-level classification means that each token will be given a label, for example a part-of-speech tagger will classify each word as one particular part of speech.
InputType: text OutputType: label
TopicClassificationInputs Objects
class TopicClassificationInputs(Inputs)
Input parameters for TopicClassification.
__init__
def __init__(node=None)
Initialize TopicClassificationInputs.
TopicClassificationOutputs Objects
class TopicClassificationOutputs(Outputs)
Output parameters for TopicClassification.
__init__
def __init__(node=None)
Initialize TopicClassificationOutputs.
TopicClassification Objects
class TopicClassification(AssetNode[TopicClassificationInputs,
TopicClassificationOutputs])
TopicClassification node.
Assigns categories or topics to a piece of text based on its content, facilitating content organization and retrieval.
InputType: text OutputType: label
IntentClassificationInputs Objects
class IntentClassificationInputs(Inputs)
Input parameters for IntentClassification.
__init__
def __init__(node=None)
Initialize IntentClassificationInputs.
IntentClassificationOutputs Objects
class IntentClassificationOutputs(Outputs)
Output parameters for IntentClassification.
__init__
def __init__(node=None)
Initialize IntentClassificationOutputs.
IntentClassification Objects
class IntentClassification(AssetNode[IntentClassificationInputs,
IntentClassificationOutputs])
IntentClassification node.
Intent Classification is a natural language processing task that involves analyzing and categorizing user text input to determine the underlying purpose or goal behind the communication, such as booking a flight, asking for weather information, or setting a reminder.
InputType: text OutputType: label
VideoContentModerationInputs Objects
class VideoContentModerationInputs(Inputs)
Input parameters for VideoContentModeration.
__init__
def __init__(node=None)
Initialize VideoContentModerationInputs.
VideoContentModerationOutputs Objects
class VideoContentModerationOutputs(Outputs)
Output parameters for VideoContentModeration.
__init__
def __init__(node=None)
Initialize VideoContentModerationOutputs.
VideoContentModeration Objects
class VideoContentModeration(AssetNode[VideoContentModerationInputs,
VideoContentModerationOutputs])
VideoContentModeration node.
Automatically reviews video content to detect and possibly remove inappropriate or harmful material. Essential for user-generated content platforms.
InputType: video OutputType: label
TextGenerationMetricInputs Objects
class TextGenerationMetricInputs(Inputs)
Input parameters for TextGenerationMetric.
__init__
def __init__(node=None)
Initialize TextGenerationMetricInputs.
TextGenerationMetricOutputs Objects
class TextGenerationMetricOutputs(Outputs)
Output parameters for TextGenerationMetric.
__init__
def __init__(node=None)
Initialize TextGenerationMetricOutputs.
TextGenerationMetric Objects
class TextGenerationMetric(BaseMetric[TextGenerationMetricInputs,
TextGenerationMetricOutputs])
TextGenerationMetric node.
A Text Generation Metric is a quantitative measure used to evaluate the quality and effectiveness of text produced by natural language processing models, often assessing aspects such as coherence, relevance, fluency, and adherence to given prompts or instructions.
InputType: text OutputType: text
ImageEmbeddingInputs Objects
class ImageEmbeddingInputs(Inputs)
Input parameters for ImageEmbedding.
__init__
def __init__(node=None)
Initialize ImageEmbeddingInputs.
ImageEmbeddingOutputs Objects
class ImageEmbeddingOutputs(Outputs)
Output parameters for ImageEmbedding.
__init__
def __init__(node=None)
Initialize ImageEmbeddingOutputs.
ImageEmbedding Objects
class ImageEmbedding(AssetNode[ImageEmbeddingInputs, ImageEmbeddingOutputs])
ImageEmbedding node.
Image Embedding is a process that transforms an image into a fixed-dimensional vector representation, capturing its essential features and enabling efficient comparison, retrieval, and analysis in various machine learning and computer vision tasks.
InputType: image OutputType: text
ImageLabelDetectionInputs Objects
class ImageLabelDetectionInputs(Inputs)
Input parameters for ImageLabelDetection.
__init__
def __init__(node=None)
Initialize ImageLabelDetectionInputs.
ImageLabelDetectionOutputs Objects
class ImageLabelDetectionOutputs(Outputs)
Output parameters for ImageLabelDetection.
__init__
def __init__(node=None)
Initialize ImageLabelDetectionOutputs.
ImageLabelDetection Objects
class ImageLabelDetection(AssetNode[ImageLabelDetectionInputs,
ImageLabelDetectionOutputs])
ImageLabelDetection node.
Identifies objects, themes, or topics within images, useful for image categorization, search, and recommendation systems.
InputType: image OutputType: label
ImageColorizationInputs Objects
class ImageColorizationInputs(Inputs)
Input parameters for ImageColorization.
__init__
def __init__(node=None)
Initialize ImageColorizationInputs.
ImageColorizationOutputs Objects
class ImageColorizationOutputs(Outputs)
Output parameters for ImageColorization.
__init__
def __init__(node=None)
Initialize ImageColorizationOutputs.
ImageColorization Objects
class ImageColorization(AssetNode[ImageColorizationInputs,
ImageColorizationOutputs])
ImageColorization node.
Image colorization is a process that involves adding color to grayscale images, transforming them from black-and-white to full-color representations, often using advanced algorithms and machine learning techniques to predict and apply the appropriate hues and shades.
InputType: image OutputType: image
MetricAggregationInputs Objects
class MetricAggregationInputs(Inputs)
Input parameters for MetricAggregation.
__init__
def __init__(node=None)
Initialize MetricAggregationInputs.
MetricAggregationOutputs Objects
class MetricAggregationOutputs(Outputs)
Output parameters for MetricAggregation.
__init__
def __init__(node=None)
Initialize MetricAggregationOutputs.
MetricAggregation Objects
class MetricAggregation(BaseMetric[MetricAggregationInputs,
MetricAggregationOutputs])
MetricAggregation node.
Metric Aggregation is a function that computes and summarizes numerical data by applying statistical operations, such as averaging, summing, or finding the minimum and maximum values, to provide insights and facilitate analysis of large datasets.
InputType: text OutputType: text
InstanceSegmentationInputs Objects
class InstanceSegmentationInputs(Inputs)
Input parameters for InstanceSegmentation.
__init__
def __init__(node=None)
Initialize InstanceSegmentationInputs.
InstanceSegmentationOutputs Objects
class InstanceSegmentationOutputs(Outputs)
Output parameters for InstanceSegmentation.
__init__
def __init__(node=None)
Initialize InstanceSegmentationOutputs.
InstanceSegmentation Objects
class InstanceSegmentation(AssetNode[InstanceSegmentationInputs,
InstanceSegmentationOutputs])
InstanceSegmentation node.
Instance segmentation is a computer vision task that involves detecting and delineating each distinct object within an image, assigning a unique label and precise boundary to every individual instance of objects, even if they belong to the same category.
InputType: image OutputType: label
OtherMultipurposeInputs Objects
class OtherMultipurposeInputs(Inputs)
Input parameters for OtherMultipurpose.
__init__
def __init__(node=None)
Initialize OtherMultipurposeInputs.
OtherMultipurposeOutputs Objects
class OtherMultipurposeOutputs(Outputs)
Output parameters for OtherMultipurpose.
__init__
def __init__(node=None)
Initialize OtherMultipurposeOutputs.
OtherMultipurpose Objects
class OtherMultipurpose(AssetNode[OtherMultipurposeInputs,
OtherMultipurposeOutputs])
OtherMultipurpose node.
The "Other (Multipurpose)" function serves as a versatile category designed to accommodate a wide range of tasks and activities that do not fit neatly into predefined classifications, offering flexibility and adaptability for various needs.
InputType: text OutputType: text
SpeechTranslationInputs Objects
class SpeechTranslationInputs(Inputs)
Input parameters for SpeechTranslation.
__init__
def __init__(node=None)
Initialize SpeechTranslationInputs.
SpeechTranslationOutputs Objects
class SpeechTranslationOutputs(Outputs)
Output parameters for SpeechTranslation.
__init__
def __init__(node=None)
Initialize SpeechTranslationOutputs.
SpeechTranslation Objects
class SpeechTranslation(AssetNode[SpeechTranslationInputs,
SpeechTranslationOutputs])
SpeechTranslation node.
Speech Translation is a technology that converts spoken language in real-time from one language to another, enabling seamless communication between speakers of different languages.
InputType: audio OutputType: text
ReferencelessTextGenerationMetricDefaultInputs Objects
class ReferencelessTextGenerationMetricDefaultInputs(Inputs)
Input parameters for ReferencelessTextGenerationMetricDefault.
__init__
def __init__(node=None)
Initialize ReferencelessTextGenerationMetricDefaultInputs.
ReferencelessTextGenerationMetricDefaultOutputs Objects
class ReferencelessTextGenerationMetricDefaultOutputs(Outputs)
Output parameters for ReferencelessTextGenerationMetricDefault.
__init__
def __init__(node=None)
Initialize ReferencelessTextGenerationMetricDefaultOutputs.
ReferencelessTextGenerationMetricDefault Objects
class ReferencelessTextGenerationMetricDefault(
BaseMetric[ReferencelessTextGenerationMetricDefaultInputs,
ReferencelessTextGenerationMetricDefaultOutputs])
ReferencelessTextGenerationMetricDefault node.
The Referenceless Text Generation Metric Default is a function designed to evaluate the quality of generated text without relying on reference texts for comparison.
InputType: text OutputType: text
ReferencelessTextGenerationMetricInputs Objects
class ReferencelessTextGenerationMetricInputs(Inputs)
Input parameters for ReferencelessTextGenerationMetric.
__init__
def __init__(node=None)
Initialize ReferencelessTextGenerationMetricInputs.
ReferencelessTextGenerationMetricOutputs Objects
class ReferencelessTextGenerationMetricOutputs(Outputs)
Output parameters for ReferencelessTextGenerationMetric.
__init__
def __init__(node=None)
Initialize ReferencelessTextGenerationMetricOutputs.
ReferencelessTextGenerationMetric Objects
class ReferencelessTextGenerationMetric(
BaseMetric[ReferencelessTextGenerationMetricInputs,
ReferencelessTextGenerationMetricOutputs])
ReferencelessTextGenerationMetric node.
The Referenceless Text Generation Metric is a method for evaluating the quality of generated text without requiring a reference text for comparison, often leveraging models or algorithms to assess coherence, relevance, and fluency based on intrinsic properties of the text itself.
InputType: text OutputType: text
TextDenormalizationInputs Objects
class TextDenormalizationInputs(Inputs)
Input parameters for TextDenormalization.
__init__
def __init__(node=None)
Initialize TextDenormalizationInputs.
TextDenormalizationOutputs Objects
class TextDenormalizationOutputs(Outputs)
Output parameters for TextDenormalization.
__init__
def __init__(node=None)
Initialize TextDenormalizationOutputs.
TextDenormalization Objects
class TextDenormalization(AssetNode[TextDenormalizationInputs,
TextDenormalizationOutputs])
TextDenormalization node.
Converts standardized or normalized text into its original, often more readable, form. Useful in natural language generation tasks.
InputType: text OutputType: label
ImageCompressionInputs Objects
class ImageCompressionInputs(Inputs)
Input parameters for ImageCompression.
__init__
def __init__(node=None)
Initialize ImageCompressionInputs.
ImageCompressionOutputs Objects
class ImageCompressionOutputs(Outputs)
Output parameters for ImageCompression.
__init__
def __init__(node=None)
Initialize ImageCompressionOutputs.
ImageCompression Objects
class ImageCompression(AssetNode[ImageCompressionInputs,
ImageCompressionOutputs])
ImageCompression node.
Reduces the size of image files without significantly compromising their visual quality. Useful for optimizing storage and improving webpage load times.
InputType: image OutputType: image
TextClassificationInputs Objects
class TextClassificationInputs(Inputs)
Input parameters for TextClassification.
__init__
def __init__(node=None)
Initialize TextClassificationInputs.
TextClassificationOutputs Objects
class TextClassificationOutputs(Outputs)
Output parameters for TextClassification.
__init__
def __init__(node=None)
Initialize TextClassificationOutputs.
TextClassification Objects
class TextClassification(AssetNode[TextClassificationInputs,
TextClassificationOutputs])
TextClassification node.
Categorizes text into predefined groups or topics, facilitating content organization and targeted actions.
InputType: text OutputType: label
AsrAgeClassificationInputs Objects
class AsrAgeClassificationInputs(Inputs)
Input parameters for AsrAgeClassification.
__init__
def __init__(node=None)
Initialize AsrAgeClassificationInputs.
AsrAgeClassificationOutputs Objects
class AsrAgeClassificationOutputs(Outputs)
Output parameters for AsrAgeClassification.
__init__
def __init__(node=None)
Initialize AsrAgeClassificationOutputs.
AsrAgeClassification Objects
class AsrAgeClassification(AssetNode[AsrAgeClassificationInputs,
AsrAgeClassificationOutputs])
AsrAgeClassification node.
The ASR Age Classification function is designed to analyze audio recordings of speech to determine the speaker's age group by leveraging automatic speech recognition (ASR) technology and machine learning algorithms.
InputType: audio OutputType: label
AsrQualityEstimationInputs Objects
class AsrQualityEstimationInputs(Inputs)
Input parameters for AsrQualityEstimation.
__init__
def __init__(node=None)
Initialize AsrQualityEstimationInputs.
AsrQualityEstimationOutputs Objects
class AsrQualityEstimationOutputs(Outputs)
Output parameters for AsrQualityEstimation.
__init__
def __init__(node=None)
Initialize AsrQualityEstimationOutputs.
AsrQualityEstimation Objects
class AsrQualityEstimation(AssetNode[AsrQualityEstimationInputs,
AsrQualityEstimationOutputs])
AsrQualityEstimation node.
ASR Quality Estimation is a process that evaluates the accuracy and reliability of automatic speech recognition systems by analyzing their performance in transcribing spoken language into text.
InputType: text OutputType: label
Pipeline Objects
class Pipeline(DefaultPipeline)
Pipeline class for creating and managing AI processing pipelines.
text_normalization
def text_normalization(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextNormalization
Create a TextNormalization node.
Converts unstructured or non-standard textual data into a more readable and uniform format, dealing with abbreviations, numerals, and other non-standard words.
paraphrasing
def paraphrasing(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> Paraphrasing
Create a Paraphrasing node.
Express the meaning of the writer or speaker or something written or spoken using different words.
language_identification
def language_identification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> LanguageIdentification
Create a LanguageIdentification node.
Detects the language in which a given text is written, aiding in multilingual platforms or content localization.
benchmark_scoring_asr
def benchmark_scoring_asr(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> BenchmarkScoringAsr
Create a BenchmarkScoringAsr node.
Benchmark Scoring ASR is a function that evaluates and compares the performance of automatic speech recognition systems by analyzing their accuracy, speed, and other relevant metrics against a standardized set of benchmarks.
multi_class_text_classification
def multi_class_text_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> MultiClassTextClassification
Create a MultiClassTextClassification node.
Multi Class Text Classification is a natural language processing task that involves categorizing a given text into one of several predefined classes or categories based on its content.
speech_embedding
def speech_embedding(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SpeechEmbedding
Create a SpeechEmbedding node.
Transforms spoken content into a fixed-size vector in a high-dimensional space that captures the content's essence. Facilitates tasks like speech recognition and speaker verification.
document_image_parsing
def document_image_parsing(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> DocumentImageParsing
Create a DocumentImageParsing node.
Document Image Parsing is the process of analyzing and converting scanned or photographed images of documents into structured, machine-readable formats by identifying and extracting text, layout, and other relevant information.
translation
def translation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> Translation
Create a Translation node.
Converts text from one language to another while maintaining the original message's essence and context. Crucial for global communication.
audio_source_separation
def audio_source_separation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AudioSourceSeparation
Create a AudioSourceSeparation node.
Audio Source Separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals).
speech_recognition
def speech_recognition(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SpeechRecognition
Create a SpeechRecognition node.
Converts spoken language into written text. Useful for transcription services, voice assistants, and applications requiring voice-to-text capabilities.
keyword_spotting
def keyword_spotting(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> KeywordSpotting
Create a KeywordSpotting node.
Keyword Spotting is a function that enables the detection and identification of specific words or phrases within a stream of audio, often used in voice- activated systems to trigger actions or commands based on recognized keywords.
part_of_speech_tagging
def part_of_speech_tagging(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> PartOfSpeechTagging
Create a PartOfSpeechTagging node.
Part of Speech Tagging is a natural language processing task that involves assigning each word in a sentence its corresponding part of speech, such as noun, verb, adjective, or adverb, based on its role and context within the sentence.
referenceless_audio_generation_metric
def referenceless_audio_generation_metric(
asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ReferencelessAudioGenerationMetric
Create a ReferencelessAudioGenerationMetric node.
The Referenceless Audio Generation Metric is a tool designed to evaluate the quality of generated audio content without the need for a reference or original audio sample for comparison.
voice_activity_detection
def voice_activity_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VoiceActivityDetection
Create a VoiceActivityDetection node.
Determines when a person is speaking in an audio clip. It's an essential preprocessing step for other audio-related tasks.
sentiment_analysis
def sentiment_analysis(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SentimentAnalysis
Create a SentimentAnalysis node.
Determines the sentiment or emotion (e.g., positive, negative, neutral) of a piece of text, aiding in understanding user feedback or market sentiment.
subtitling
def subtitling(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> Subtitling
Create a Subtitling node.
Generates accurate subtitles for videos, enhancing accessibility for diverse audiences.
multi_label_text_classification
def multi_label_text_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> MultiLabelTextClassification
Create a MultiLabelTextClassification node.
Multi Label Text Classification is a natural language processing task where a given text is analyzed and assigned multiple relevant labels or categories from a predefined set, allowing for the text to belong to more than one category simultaneously.
viseme_generation
def viseme_generation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VisemeGeneration
Create a VisemeGeneration node.
Viseme Generation is the process of creating visual representations of phonemes, which are the distinct units of sound in speech, to synchronize lip movements with spoken words in animations or virtual avatars.
text_segmenation
def text_segmenation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextSegmenation
Create a TextSegmenation node.
Text Segmentation is the process of dividing a continuous text into meaningful units, such as words, sentences, or topics, to facilitate easier analysis and understanding.
zero_shot_classification
def zero_shot_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ZeroShotClassification
Create a ZeroShotClassification node.
text_generation
def text_generation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextGeneration
Create a TextGeneration node.
Creates coherent and contextually relevant textual content based on prompts or certain parameters. Useful for chatbots, content creation, and data augmentation.
audio_intent_detection
def audio_intent_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AudioIntentDetection
Create a AudioIntentDetection node.
Audio Intent Detection is a process that involves analyzing audio signals to identify and interpret the underlying intentions or purposes behind spoken words, enabling systems to understand and respond appropriately to human speech.
entity_linking
def entity_linking(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> EntityLinking
Create a EntityLinking node.
Associates identified entities in the text with specific entries in a knowledge base or database.
connection
def connection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> Connection
Create a Connection node.
Connections are integration that allow you to connect your AI agents to external tools
visual_question_answering
def visual_question_answering(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VisualQuestionAnswering
Create a VisualQuestionAnswering node.
Visual Question Answering (VQA) is a task in artificial intelligence that involves analyzing an image and providing accurate, contextually relevant answers to questions posed about the visual content of that image.
loglikelihood
def loglikelihood(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> Loglikelihood
Create a Loglikelihood node.
The Log Likelihood function measures the probability of observing the given data under a specific statistical model by taking the natural logarithm of the likelihood function, thereby transforming the product of probabilities into a sum, which simplifies the process of optimization and parameter estimation.
language_identification_audio
def language_identification_audio(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> LanguageIdentificationAudio
Create a LanguageIdentificationAudio node.
The Language Identification Audio function analyzes audio input to determine and identify the language being spoken.
fact_checking
def fact_checking(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> FactChecking
Create a FactChecking node.
Fact Checking is the process of verifying the accuracy and truthfulness of information, statements, or claims by cross-referencing with reliable sources and evidence.
table_question_answering
def table_question_answering(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TableQuestionAnswering
Create a TableQuestionAnswering node.
The task of question answering over tables is given an input table (or a set of tables) T and a natural language question Q (a user query), output the correct answer A
speech_classification
def speech_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SpeechClassification
Create a SpeechClassification node.
Categorizes audio clips based on their content, aiding in content organization and targeted actions.
inverse_text_normalization
def inverse_text_normalization(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> InverseTextNormalization
Create a InverseTextNormalization node.
Inverse Text Normalization is the process of converting spoken or written language in its normalized form, such as numbers, dates, and abbreviations, back into their original, more complex or detailed textual representations.
multi_class_image_classification
def multi_class_image_classification(
asset_id: Union[str, asset.Asset], *args,
**kwargs) -> MultiClassImageClassification
Create a MultiClassImageClassification node.
Multi Class Image Classification is a machine learning task where an algorithm is trained to categorize images into one of several predefined classes or categories based on their visual content.
asr_gender_classification
def asr_gender_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AsrGenderClassification
Create a AsrGenderClassification node.
The ASR Gender Classification function analyzes audio recordings to determine and classify the speaker's gender based on their voice characteristics.
summarization
def summarization(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> Summarization
Create a Summarization node.
Text summarization is the process of distilling the most important information from a source (or sources) to produce an abridged version for a particular user (or users) and task (or tasks)
topic_modeling
def topic_modeling(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TopicModeling
Create a TopicModeling node.
Topic modeling is a type of statistical modeling for discovering the abstract “topics” that occur in a collection of documents.
audio_reconstruction
def audio_reconstruction(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AudioReconstruction
Create a AudioReconstruction node.
Audio Reconstruction is the process of restoring or recreating audio signals from incomplete, damaged, or degraded recordings to achieve a high-quality, accurate representation of the original sound.
text_embedding
def text_embedding(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextEmbedding
Create a TextEmbedding node.
Text embedding is a process that converts text into numerical vectors, capturing the semantic meaning and contextual relationships of words or phrases, enabling machines to understand and analyze natural language more effectively.
detect_language_from_text
def detect_language_from_text(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> DetectLanguageFromText
Create a DetectLanguageFromText node.
Detect Language From Text
extract_audio_from_video
def extract_audio_from_video(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ExtractAudioFromVideo
Create a ExtractAudioFromVideo node.
Isolates and extracts audio tracks from video files, aiding in audio analysis or transcription tasks.
scene_detection
def scene_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SceneDetection
Create a SceneDetection node.
Scene detection is used for detecting transitions between shots in a video to split it into basic temporal segments.
text_to_image_generation
def text_to_image_generation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextToImageGeneration
Create a TextToImageGeneration node.
Creates a visual representation based on textual input, turning descriptions into pictorial forms. Used in creative processes and content generation.
auto_mask_generation
def auto_mask_generation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AutoMaskGeneration
Create a AutoMaskGeneration node.
Auto-mask generation refers to the automated process of creating masks in image processing or computer vision, typically for segmentation tasks. A mask is a binary or multi-class image that labels different parts of an image, usually separating the foreground (objects of interest) from the background, or identifying specific object classes in an image.
audio_language_identification
def audio_language_identification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AudioLanguageIdentification
Create a AudioLanguageIdentification node.
Audio Language Identification is a process that involves analyzing an audio recording to determine the language being spoken.
facial_recognition
def facial_recognition(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> FacialRecognition
Create a FacialRecognition node.
A facial recognition system is a technology capable of matching a human face from a digital image or a video frame against a database of faces
question_answering
def question_answering(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> QuestionAnswering
Create a QuestionAnswering node.
building systems that automatically answer questions posed by humans in a natural language usually from a given text
image_impainting
def image_impainting(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageImpainting
Create a ImageImpainting node.
Image inpainting is a process that involves filling in missing or damaged parts of an image in a way that is visually coherent and seamlessly blends with the surrounding areas, often using advanced algorithms and techniques to restore the image to its original or intended appearance.
text_reconstruction
def text_reconstruction(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextReconstruction
Create a TextReconstruction node.
Text Reconstruction is a process that involves piecing together fragmented or incomplete text data to restore it to its original, coherent form.
script_execution
def script_execution(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ScriptExecution
Create a ScriptExecution node.
Script Execution refers to the process of running a set of programmed instructions or code within a computing environment, enabling the automated performance of tasks, calculations, or operations as defined by the script.
semantic_segmentation
def semantic_segmentation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SemanticSegmentation
Create a SemanticSegmentation node.
Semantic segmentation is a computer vision process that involves classifying each pixel in an image into a predefined category, effectively partitioning the image into meaningful segments based on the objects or regions they represent.
audio_emotion_detection
def audio_emotion_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AudioEmotionDetection
Create a AudioEmotionDetection node.
Audio Emotion Detection is a technology that analyzes vocal characteristics and patterns in audio recordings to identify and classify the emotional state of the speaker.
image_captioning
def image_captioning(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageCaptioning
Create a ImageCaptioning node.
Image Captioning is a process that involves generating a textual description of an image, typically using machine learning models to analyze the visual content and produce coherent and contextually relevant sentences that describe the objects, actions, and scenes depicted in the image.
split_on_linebreak
def split_on_linebreak(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SplitOnLinebreak
Create a SplitOnLinebreak node.
The "Split On Linebreak" function divides a given string into a list of substrings, using linebreaks (newline characters) as the points of separation.
style_transfer
def style_transfer(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> StyleTransfer
Create a StyleTransfer node.
Style Transfer is a technique in artificial intelligence that applies the visual style of one image (such as the brushstrokes of a famous painting) to the content of another image, effectively blending the artistic elements of the first image with the subject matter of the second.
base_model
def base_model(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> BaseModel
Create a BaseModel node.
The Base-Model function serves as a foundational framework designed to provide essential features and capabilities upon which more specialized or advanced models can be built and customized.
image_manipulation
def image_manipulation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageManipulation
Create a ImageManipulation node.
Image Manipulation refers to the process of altering or enhancing digital images using various techniques and tools to achieve desired visual effects, correct imperfections, or transform the image's appearance.
video_embedding
def video_embedding(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VideoEmbedding
Create a VideoEmbedding node.
Video Embedding is a process that transforms video content into a fixed- dimensional vector representation, capturing essential features and patterns to facilitate tasks such as retrieval, classification, and recommendation.
dialect_detection
def dialect_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> DialectDetection
Create a DialectDetection node.
Identifies specific dialects within a language, aiding in localized content creation or user experience personalization.
fill_text_mask
def fill_text_mask(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> FillTextMask
Create a FillTextMask node.
Completes missing parts of a text based on the context, ideal for content generation or data augmentation tasks.
activity_detection
def activity_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ActivityDetection
Create a ActivityDetection node.
detection of the presence or absence of human speech, used in speech processing.
select_supplier_for_translation
def select_supplier_for_translation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SelectSupplierForTranslation
Create a SelectSupplierForTranslation node.
Supplier For Translation
expression_detection
def expression_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ExpressionDetection
Create a ExpressionDetection node.
Expression Detection is the process of identifying and analyzing facial expressions to interpret emotions or intentions using AI and computer vision techniques.
video_generation
def video_generation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VideoGeneration
Create a VideoGeneration node.
Produces video content based on specific inputs or datasets. Can be used for simulations, animations, or even deepfake detection.
image_analysis
def image_analysis(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageAnalysis
Create a ImageAnalysis node.
Image analysis is the extraction of meaningful information from images
noise_removal
def noise_removal(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> NoiseRemoval
Create a NoiseRemoval node.
Noise Removal is a process that involves identifying and eliminating unwanted random variations or disturbances from an audio signal to enhance the clarity and quality of the underlying information.
image_and_video_analysis
def image_and_video_analysis(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageAndVideoAnalysis
Create a ImageAndVideoAnalysis node.
keyword_extraction
def keyword_extraction(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> KeywordExtraction
Create a KeywordExtraction node.
It helps concise the text and obtain relevant keywords Example use-cases are finding topics of interest from a news article and identifying the problems based on customer reviews and so.
split_on_silence
def split_on_silence(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SplitOnSilence
Create a SplitOnSilence node.
The "Split On Silence" function divides an audio recording into separate segments based on periods of silence, allowing for easier editing and analysis of individual sections.
intent_recognition
def intent_recognition(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> IntentRecognition
Create a IntentRecognition node.
classify the user's utterance (provided in varied natural language) or text into one of several predefined classes, that is, intents.
depth_estimation
def depth_estimation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> DepthEstimation
Create a DepthEstimation node.
Depth estimation is a computational process that determines the distance of objects from a viewpoint, typically using visual data from cameras or sensors to create a three-dimensional understanding of a scene.
connector
def connector(asset_id: Union[str, asset.Asset], *args, **kwargs) -> Connector
Create a Connector node.
Connectors are integration that allow you to connect your AI agents to external tools
speaker_recognition
def speaker_recognition(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SpeakerRecognition
Create a SpeakerRecognition node.
In speaker identification, an utterance from an unknown speaker is analyzed and compared with speech models of known speakers.
syntax_analysis
def syntax_analysis(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SyntaxAnalysis
Create a SyntaxAnalysis node.
Is the process of analyzing natural language with the rules of a formal grammar. Grammatical rules are applied to categories and groups of words, not individual words. Syntactic analysis basically assigns a semantic structure to text.
entity_sentiment_analysis
def entity_sentiment_analysis(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> EntitySentimentAnalysis
Create a EntitySentimentAnalysis node.
Entity Sentiment Analysis combines both entity analysis and sentiment analysis and attempts to determine the sentiment (positive or negative) expressed about entities within the text.
classification_metric
def classification_metric(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ClassificationMetric
Create a ClassificationMetric node.
A Classification Metric is a quantitative measure used to evaluate the quality and effectiveness of classification models.
text_detection
def text_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextDetection
Create a TextDetection node.
detect text regions in the complex background and label them with bounding boxes.
guardrails
def guardrails(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> Guardrails
Create a Guardrails node.
Guardrails are governance rules that enforce security, compliance, and operational best practices, helping prevent mistakes and detect suspicious activity
emotion_detection
def emotion_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> EmotionDetection
Create a EmotionDetection node.
Identifies human emotions from text or audio, enhancing user experience in chatbots or customer feedback analysis.
video_forced_alignment
def video_forced_alignment(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VideoForcedAlignment
Create a VideoForcedAlignment node.
Aligns the transcription of spoken content in a video with its corresponding timecodes, facilitating subtitle creation.
image_content_moderation
def image_content_moderation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageContentModeration
Create a ImageContentModeration node.
Detects and filters out inappropriate or harmful images, essential for platforms with user-generated visual content.
text_summarization
def text_summarization(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextSummarization
Create a TextSummarization node.
Extracts the main points from a larger body of text, producing a concise summary without losing the primary message.
image_to_video_generation
def image_to_video_generation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageToVideoGeneration
Create a ImageToVideoGeneration node.
The Image To Video Generation function transforms a series of static images into a cohesive, dynamic video sequence, often incorporating transitions, effects, and synchronization with audio to create a visually engaging narrative.
video_understanding
def video_understanding(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VideoUnderstanding
Create a VideoUnderstanding node.
Video Understanding is the process of analyzing and interpreting video content to extract meaningful information, such as identifying objects, actions, events, and contextual relationships within the footage.
text_generation_metric_default
def text_generation_metric_default(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextGenerationMetricDefault
Create a TextGenerationMetricDefault node.
The "Text Generation Metric Default" function provides a standard set of evaluation metrics for assessing the quality and performance of text generation models.
text_to_video_generation
def text_to_video_generation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextToVideoGeneration
Create a TextToVideoGeneration node.
Text To Video Generation is a process that converts written descriptions or scripts into dynamic, visual video content using advanced algorithms and artificial intelligence.
video_label_detection
def video_label_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VideoLabelDetection
Create a VideoLabelDetection node.
Identifies and tags objects, scenes, or activities within a video. Useful for content indexing and recommendation systems.
text_spam_detection
def text_spam_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextSpamDetection
Create a TextSpamDetection node.
Identifies and filters out unwanted or irrelevant text content, ideal for moderating user-generated content or ensuring quality in communication platforms.
text_content_moderation
def text_content_moderation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextContentModeration
Create a TextContentModeration node.
Scans and identifies potentially harmful, offensive, or inappropriate textual content, ensuring safer user environments.
audio_transcript_improvement
def audio_transcript_improvement(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AudioTranscriptImprovement
Create a AudioTranscriptImprovement node.
Refines and corrects transcriptions generated from audio data, improving readability and accuracy.
audio_transcript_analysis
def audio_transcript_analysis(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AudioTranscriptAnalysis
Create a AudioTranscriptAnalysis node.
Analyzes transcribed audio data for insights, patterns, or specific information extraction.
speech_non_speech_classification
def speech_non_speech_classification(
asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SpeechNonSpeechClassification
Create a SpeechNonSpeechClassification node.
Differentiates between speech and non-speech audio segments. Great for editing software and transcription services to exclude irrelevant audio.
audio_generation_metric
def audio_generation_metric(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AudioGenerationMetric
Create a AudioGenerationMetric node.
The Audio Generation Metric is a quantitative measure used to evaluate the quality, accuracy, and overall performance of audio generated by artificial intelligence systems, often considering factors such as fidelity, intelligibility, and similarity to human-produced audio.
named_entity_recognition
def named_entity_recognition(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> NamedEntityRecognition
Create a NamedEntityRecognition node.
Identifies and classifies named entities (e.g., persons, organizations, locations) within text. Useful for information extraction, content tagging, and search enhancements.
speech_synthesis
def speech_synthesis(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SpeechSynthesis
Create a SpeechSynthesis node.
Generates human-like speech from written text. Ideal for text-to-speech applications, audiobooks, and voice assistants.
document_information_extraction
def document_information_extraction(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> DocumentInformationExtraction
Create a DocumentInformationExtraction node.
Document Information Extraction is the process of automatically identifying, extracting, and structuring relevant data from unstructured or semi-structured documents, such as invoices, receipts, contracts, and forms, to facilitate easier data management and analysis.
ocr
def ocr(asset_id: Union[str, asset.Asset], *args, **kwargs) -> Ocr
Create a Ocr node.
Converts images of typed, handwritten, or printed text into machine-encoded text. Used in digitizing printed texts for data retrieval.
subtitling_translation
def subtitling_translation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SubtitlingTranslation
Create a SubtitlingTranslation node.
Converts the text of subtitles from one language to another, ensuring context and cultural nuances are maintained. Essential for global content distribution.
text_to_audio
def text_to_audio(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextToAudio
Create a TextToAudio node.
The Text to Audio function converts written text into spoken words, allowing users to listen to the content instead of reading it.
multilingual_speech_recognition
def multilingual_speech_recognition(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> MultilingualSpeechRecognition
Create a MultilingualSpeechRecognition node.
Multilingual Speech Recognition is a technology that enables the automatic transcription of spoken language into text across multiple languages, allowing for seamless communication and understanding in diverse linguistic contexts.
offensive_language_identification
def offensive_language_identification(
asset_id: Union[str, asset.Asset], *args,
**kwargs) -> OffensiveLanguageIdentification
Create a OffensiveLanguageIdentification node.
Detects language or phrases that might be considered offensive, aiding in content moderation and creating respectful user interactions.
benchmark_scoring_mt
def benchmark_scoring_mt(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> BenchmarkScoringMt
Create a BenchmarkScoringMt node.
Benchmark Scoring MT is a function designed to evaluate and score machine translation systems by comparing their output against a set of predefined benchmarks, thereby assessing their accuracy and performance.
speaker_diarization_audio
def speaker_diarization_audio(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SpeakerDiarizationAudio
Create a SpeakerDiarizationAudio node.
Identifies individual speakers and their respective speech segments within an audio clip. Ideal for multi-speaker recordings or conference calls.
voice_cloning
def voice_cloning(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VoiceCloning
Create a VoiceCloning node.
Replicates a person's voice based on a sample, allowing for the generation of speech in that person's tone and style. Used cautiously due to ethical considerations.
search
def search(asset_id: Union[str, asset.Asset], *args, **kwargs) -> Search
Create a Search node.
An algorithm that identifies and returns data or items that match particular keywords or conditions from a dataset. A fundamental tool for databases and websites.
object_detection
def object_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ObjectDetection
Create a ObjectDetection node.
Object Detection is a computer vision technology that identifies and locates objects within an image, typically by drawing bounding boxes around the detected objects and classifying them into predefined categories.
diacritization
def diacritization(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> Diacritization
Create a Diacritization node.
Adds diacritical marks to text, essential for languages where meaning can change based on diacritics.
speaker_diarization_video
def speaker_diarization_video(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SpeakerDiarizationVideo
Create a SpeakerDiarizationVideo node.
Segments a video based on different speakers, identifying when each individual speaks. Useful for transcriptions and understanding multi-person conversations.
audio_forced_alignment
def audio_forced_alignment(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AudioForcedAlignment
Create a AudioForcedAlignment node.
Synchronizes phonetic and phonological text with the corresponding segments in an audio file. Useful in linguistic research and detailed transcription tasks.
token_classification
def token_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TokenClassification
Create a TokenClassification node.
Token-level classification means that each token will be given a label, for example a part-of-speech tagger will classify each word as one particular part of speech.
topic_classification
def topic_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TopicClassification
Create a TopicClassification node.
Assigns categories or topics to a piece of text based on its content, facilitating content organization and retrieval.
intent_classification
def intent_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> IntentClassification
Create a IntentClassification node.
Intent Classification is a natural language processing task that involves analyzing and categorizing user text input to determine the underlying purpose or goal behind the communication, such as booking a flight, asking for weather information, or setting a reminder.
video_content_moderation
def video_content_moderation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> VideoContentModeration
Create a VideoContentModeration node.
Automatically reviews video content to detect and possibly remove inappropriate or harmful material. Essential for user-generated content platforms.
text_generation_metric
def text_generation_metric(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextGenerationMetric
Create a TextGenerationMetric node.
A Text Generation Metric is a quantitative measure used to evaluate the quality and effectiveness of text produced by natural language processing models, often assessing aspects such as coherence, relevance, fluency, and adherence to given prompts or instructions.
image_embedding
def image_embedding(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageEmbedding
Create a ImageEmbedding node.
Image Embedding is a process that transforms an image into a fixed-dimensional vector representation, capturing its essential features and enabling efficient comparison, retrieval, and analysis in various machine learning and computer vision tasks.
image_label_detection
def image_label_detection(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageLabelDetection
Create a ImageLabelDetection node.
Identifies objects, themes, or topics within images, useful for image categorization, search, and recommendation systems.
image_colorization
def image_colorization(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageColorization
Create a ImageColorization node.
Image colorization is a process that involves adding color to grayscale images, transforming them from black-and-white to full-color representations, often using advanced algorithms and machine learning techniques to predict and apply the appropriate hues and shades.
metric_aggregation
def metric_aggregation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> MetricAggregation
Create a MetricAggregation node.
Metric Aggregation is a function that computes and summarizes numerical data by applying statistical operations, such as averaging, summing, or finding the minimum and maximum values, to provide insights and facilitate analysis of large datasets.
instance_segmentation
def instance_segmentation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> InstanceSegmentation
Create a InstanceSegmentation node.
Instance segmentation is a computer vision task that involves detecting and delineating each distinct object within an image, assigning a unique label and precise boundary to every individual instance of objects, even if they belong to the same category.
other__multipurpose_
def other__multipurpose_(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> OtherMultipurpose
Create a OtherMultipurpose node.
The "Other (Multipurpose)" function serves as a versatile category designed to accommodate a wide range of tasks and activities that do not fit neatly into predefined classifications, offering flexibility and adaptability for various needs.
speech_translation
def speech_translation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> SpeechTranslation
Create a SpeechTranslation node.
Speech Translation is a technology that converts spoken language in real-time from one language to another, enabling seamless communication between speakers of different languages.
referenceless_text_generation_metric_default
def referenceless_text_generation_metric_default(
asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ReferencelessTextGenerationMetricDefault
Create a ReferencelessTextGenerationMetricDefault node.
The Referenceless Text Generation Metric Default is a function designed to evaluate the quality of generated text without relying on reference texts for comparison.
referenceless_text_generation_metric
def referenceless_text_generation_metric(
asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ReferencelessTextGenerationMetric
Create a ReferencelessTextGenerationMetric node.
The Referenceless Text Generation Metric is a method for evaluating the quality of generated text without requiring a reference text for comparison, often leveraging models or algorithms to assess coherence, relevance, and fluency based on intrinsic properties of the text itself.
text_denormalization
def text_denormalization(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextDenormalization
Create a TextDenormalization node.
Converts standardized or normalized text into its original, often more readable, form. Useful in natural language generation tasks.
image_compression
def image_compression(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> ImageCompression
Create a ImageCompression node.
Reduces the size of image files without significantly compromising their visual quality. Useful for optimizing storage and improving webpage load times.
text_classification
def text_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> TextClassification
Create a TextClassification node.
Categorizes text into predefined groups or topics, facilitating content organization and targeted actions.
asr_age_classification
def asr_age_classification(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AsrAgeClassification
Create a AsrAgeClassification node.
The ASR Age Classification function is designed to analyze audio recordings of speech to determine the speaker's age group by leveraging automatic speech recognition (ASR) technology and machine learning algorithms.
asr_quality_estimation
def asr_quality_estimation(asset_id: Union[str, asset.Asset], *args,
**kwargs) -> AsrQualityEstimation
Create a AsrQualityEstimation node.
ASR Quality Estimation is a process that evaluates the accuracy and reliability of automatic speech recognition systems by analyzing their performance in transcribing spoken language into text.