Index

B

BaseLanguageDetector (class in chunkipy) (class in chunkipy.language_detectors) (class in chunkipy.language_detectors.base_language_detector) BaseOverlapTextChunker (class in chunkipy.text_chunker) (class in chunkipy.text_chunker.base_overlap_text_chunker) BaseSemanticTextSplitter (class in chunkipy.text_splitters.semantic.base_semantic_text_splitter)

BaseSizeEstimator (class in chunkipy.size_estimators) (class in chunkipy.size_estimators.base_size_estimator) BaseTextChunker (class in chunkipy) (class in chunkipy.text_chunker) (class in chunkipy.text_chunker.base_text_chunker) BaseTextSplitter (class in chunkipy.text_splitters) (class in chunkipy.text_splitters.base_text_splitter)

C

CharSizeEstimator (class in chunkipy.size_estimators) (class in chunkipy.size_estimators.char_size_estimator) Chunk (class in chunkipy) (class in chunkipy.text_chunker) (class in chunkipy.text_chunker.data_models) chunk() (chunkipy.BaseTextChunker method) (chunkipy.text_chunker.base_overlap_text_chunker.BaseOverlapTextChunker method) (chunkipy.text_chunker.base_text_chunker.BaseTextChunker method) (chunkipy.text_chunker.BaseOverlapTextChunker method) (chunkipy.text_chunker.BaseTextChunker method) chunkipy module chunkipy.language_detectors module chunkipy.language_detectors.base_language_detector module chunkipy.language_detectors.fasttext_language_detector module chunkipy.language_detectors.langdetect_language_detector module chunkipy.size_estimators module chunkipy.size_estimators.base_size_estimator module chunkipy.size_estimators.char_size_estimator module chunkipy.size_estimators.openai_size_estimator module chunkipy.size_estimators.word_size_estimator module chunkipy.text_chunker module chunkipy.text_chunker.base_overlap_text_chunker module chunkipy.text_chunker.base_text_chunker module chunkipy.text_chunker.data_models module

chunkipy.text_chunker.fixed_size module chunkipy.text_chunker.fixed_size.fixed_size_text_chunker module chunkipy.text_chunker.recursive module chunkipy.text_chunker.recursive.recursive_text_chunker module chunkipy.text_splitters module chunkipy.text_splitters.base_text_splitter module chunkipy.text_splitters.basic_text_splitters module chunkipy.text_splitters.semantic module chunkipy.text_splitters.semantic.base_semantic_text_splitter module chunkipy.text_splitters.semantic.sentences module chunkipy.text_splitters.semantic.sentences.spacy_sentence_text_splitter module chunkipy.text_splitters.semantic.sentences.stanza_sentence_text_splitter module chunkipy.utils module Chunks (class in chunkipy) (class in chunkipy.text_chunker) (class in chunkipy.text_chunker.data_models) ColonTextSplitter (class in chunkipy.text_splitters) (class in chunkipy.text_splitters.basic_text_splitters) CommaTextSplitter (class in chunkipy.text_splitters) (class in chunkipy.text_splitters.basic_text_splitters) content (chunkipy.Chunk attribute) (chunkipy.text_chunker.Chunk attribute) (chunkipy.text_chunker.data_models.Chunk attribute)

D

DEFAULT_LANG (chunkipy.text_splitters.semantic.sentences.spacy_sentence_text_splitter.SpacySentenceTextSplitter attribute) (chunkipy.text_splitters.semantic.sentences.SpacySentenceTextSplitter attribute) DEFAULT_MODELS_MAP (chunkipy.text_splitters.semantic.sentences.spacy_sentence_text_splitter.SpacySentenceTextSplitter attribute) (chunkipy.text_splitters.semantic.sentences.SpacySentenceTextSplitter attribute) DEFAULT_TEXT_LIMIT (chunkipy.text_splitters.semantic.base_semantic_text_splitter.BaseSemanticTextSplitter attribute), [1] detect() (chunkipy.BaseLanguageDetector method) (chunkipy.FastTextLanguageDetector method) (chunkipy.LangdetectLanguageDetector method) (chunkipy.language_detectors.base_language_detector.BaseLanguageDetector method) (chunkipy.language_detectors.BaseLanguageDetector method) (chunkipy.language_detectors.fasttext_language_detector.FastTextLanguageDetector method) (chunkipy.language_detectors.FastTextLanguageDetector method) (chunkipy.language_detectors.langdetect_language_detector.LangdetectLanguageDetector method) (chunkipy.language_detectors.LangdetectLanguageDetector method)

E

estimate_size() (chunkipy.size_estimators.base_size_estimator.BaseSizeEstimator method) (chunkipy.size_estimators.BaseSizeEstimator method) (chunkipy.size_estimators.char_size_estimator.CharSizeEstimator method) (chunkipy.size_estimators.CharSizeEstimator method) (chunkipy.size_estimators.openai_size_estimator.OpenAISizeEstimator method) (chunkipy.size_estimators.OpenAISizeEstimator method) (chunkipy.size_estimators.word_size_estimator.WordSizeEstimator method) (chunkipy.size_estimators.WordSizeEstimator method)

F

FastTextLanguageDetector (class in chunkipy) (class in chunkipy.language_detectors) (class in chunkipy.language_detectors.fasttext_language_detector) FixedSizeTextChunker (class in chunkipy) (class in chunkipy.text_chunker) (class in chunkipy.text_chunker.fixed_size) (class in chunkipy.text_chunker.fixed_size.fixed_size_text_chunker)

format_instructions() (in module chunkipy.utils) FullStopTextSplitter (class in chunkipy.text_splitters) (class in chunkipy.text_splitters.basic_text_splitters)

G

get_all_text() (chunkipy.Chunks method) (chunkipy.text_chunker.Chunks method) (chunkipy.text_chunker.data_models.Chunks method)

get_all_text_parts() (chunkipy.Chunks method) (chunkipy.text_chunker.Chunks method) (chunkipy.text_chunker.data_models.Chunks method)

I

import_dependencies() (in module chunkipy.utils)

L

langdetect_stanza_mapping (chunkipy.text_splitters.semantic.sentences.stanza_sentence_text_splitter.StanzaSentenceTextSplitter attribute) (chunkipy.text_splitters.semantic.sentences.StanzaSentenceTextSplitter attribute)

LangdetectLanguageDetector (class in chunkipy) (class in chunkipy.language_detectors) (class in chunkipy.language_detectors.langdetect_language_detector)

M

MissingDependencyError models (chunkipy.text_splitters.semantic.sentences.spacy_sentence_text_splitter.SpacySentenceTextSplitter attribute) (chunkipy.text_splitters.semantic.sentences.SpacySentenceTextSplitter attribute) models_map (chunkipy.text_splitters.semantic.sentences.spacy_sentence_text_splitter.SpacySentenceTextSplitter attribute) (chunkipy.text_splitters.semantic.sentences.SpacySentenceTextSplitter attribute) module chunkipy chunkipy.language_detectors chunkipy.language_detectors.base_language_detector chunkipy.language_detectors.fasttext_language_detector chunkipy.language_detectors.langdetect_language_detector chunkipy.size_estimators chunkipy.size_estimators.base_size_estimator chunkipy.size_estimators.char_size_estimator chunkipy.size_estimators.openai_size_estimator chunkipy.size_estimators.word_size_estimator chunkipy.text_chunker chunkipy.text_chunker.base_overlap_text_chunker chunkipy.text_chunker.base_text_chunker chunkipy.text_chunker.data_models chunkipy.text_chunker.fixed_size chunkipy.text_chunker.fixed_size.fixed_size_text_chunker chunkipy.text_chunker.recursive chunkipy.text_chunker.recursive.recursive_text_chunker chunkipy.text_splitters chunkipy.text_splitters.base_text_splitter chunkipy.text_splitters.basic_text_splitters chunkipy.text_splitters.semantic chunkipy.text_splitters.semantic.base_semantic_text_splitter chunkipy.text_splitters.semantic.sentences chunkipy.text_splitters.semantic.sentences.spacy_sentence_text_splitter chunkipy.text_splitters.semantic.sentences.stanza_sentence_text_splitter chunkipy.utils

N

NewlineTextSplitter (class in chunkipy.text_splitters) (class in chunkipy.text_splitters.basic_text_splitters)

O

OpenAISizeEstimator (class in chunkipy.size_estimators) (class in chunkipy.size_estimators.openai_size_estimator) overlap (chunkipy.Chunk attribute) (chunkipy.text_chunker.Chunk attribute) (chunkipy.text_chunker.data_models.Chunk attribute)

Overlap (class in chunkipy) (class in chunkipy.text_chunker) (class in chunkipy.text_chunker.data_models)

R

RecursiveTextChunker (class in chunkipy) (class in chunkipy.text_chunker) (class in chunkipy.text_chunker.recursive) (class in chunkipy.text_chunker.recursive.recursive_text_chunker)

S

segment() (chunkipy.size_estimators.base_size_estimator.BaseSizeEstimator method) (chunkipy.size_estimators.BaseSizeEstimator method) (chunkipy.size_estimators.char_size_estimator.CharSizeEstimator method) (chunkipy.size_estimators.CharSizeEstimator method) (chunkipy.size_estimators.openai_size_estimator.OpenAISizeEstimator method) (chunkipy.size_estimators.OpenAISizeEstimator method) (chunkipy.size_estimators.word_size_estimator.WordSizeEstimator method) (chunkipy.size_estimators.WordSizeEstimator method) SemicolonTextSplitter (class in chunkipy.text_splitters) (class in chunkipy.text_splitters.basic_text_splitters) separator (chunkipy.text_splitters.basic_text_splitters.SeparatorTextSplitter property) (chunkipy.text_splitters.SeparatorTextSplitter property) SeparatorTextSplitter (class in chunkipy.text_splitters) (class in chunkipy.text_splitters.basic_text_splitters) size (chunkipy.Chunk property) (chunkipy.text_chunker.Chunk property) (chunkipy.text_chunker.data_models.Chunk property) (chunkipy.text_chunker.data_models.TextPart attribute) (chunkipy.text_chunker.data_models.TextPartsMixin property) (chunkipy.text_chunker.TextPart attribute) (chunkipy.TextPart attribute)

SpacySentenceTextSplitter (class in chunkipy.text_splitters.semantic.sentences) (class in chunkipy.text_splitters.semantic.sentences.spacy_sentence_text_splitter) split() (chunkipy.text_splitters.base_text_splitter.BaseTextSplitter method) (chunkipy.text_splitters.BaseTextSplitter method) (chunkipy.text_splitters.semantic.base_semantic_text_splitter.BaseSemanticTextSplitter method) split_text() (chunkipy.FixedSizeTextChunker method) (chunkipy.RecursiveTextChunker method) (chunkipy.text_chunker.base_overlap_text_chunker.BaseOverlapTextChunker method) (chunkipy.text_chunker.BaseOverlapTextChunker method) (chunkipy.text_chunker.fixed_size.fixed_size_text_chunker.FixedSizeTextChunker method) (chunkipy.text_chunker.fixed_size.FixedSizeTextChunker method) (chunkipy.text_chunker.FixedSizeTextChunker method) (chunkipy.text_chunker.recursive.recursive_text_chunker.RecursiveTextChunker method) (chunkipy.text_chunker.recursive.RecursiveTextChunker method) (chunkipy.text_chunker.RecursiveTextChunker method) StanzaSentenceTextSplitter (class in chunkipy.text_splitters.semantic.sentences) (class in chunkipy.text_splitters.semantic.sentences.stanza_sentence_text_splitter)

T

text (chunkipy.Chunk property) (chunkipy.text_chunker.Chunk property) (chunkipy.text_chunker.data_models.Chunk property) (chunkipy.text_chunker.data_models.TextPart attribute) (chunkipy.text_chunker.data_models.TextPartsMixin property) (chunkipy.text_chunker.TextPart attribute) (chunkipy.TextPart attribute) text_limit (chunkipy.text_splitters.semantic.base_semantic_text_splitter.BaseSemanticTextSplitter attribute) (chunkipy.text_splitters.semantic.sentences.spacy_sentence_text_splitter.SpacySentenceTextSplitter attribute) (chunkipy.text_splitters.semantic.sentences.SpacySentenceTextSplitter attribute) (chunkipy.text_splitters.semantic.sentences.stanza_sentence_text_splitter.StanzaSentenceTextSplitter attribute) (chunkipy.text_splitters.semantic.sentences.StanzaSentenceTextSplitter attribute)

text_parts (chunkipy.Chunk property) (chunkipy.text_chunker.Chunk property) (chunkipy.text_chunker.data_models.Chunk property) TextPart (class in chunkipy) (class in chunkipy.text_chunker) (class in chunkipy.text_chunker.data_models) TextParts (class in chunkipy.text_chunker.data_models) TextPartsMixin (class in chunkipy.text_chunker.data_models)

W

WordSizeEstimator (class in chunkipy.size_estimators) (class in chunkipy.size_estimators.word_size_estimator)

WordTextSplitter (class in chunkipy.text_splitters) (class in chunkipy.text_splitters.basic_text_splitters)