all_tokenized           Role Selection
count_functions         List of all feature counting functions
download_embeddings_model2vec
                        Download a Pretrained Model2Vec Model
embedding_custom        Embedding Engines for
                        'step_sentence_embeddings()'
embedding_huggingface   Hugging Face Embedding Engine
embedding_model2vec     Model2Vec Embedding Engine
embedding_ollama        Ollama Embedding Engine
emoji_samples           Sample sentences with emojis
read_embeddings_model2vec
                        Read Pretrained Static Embeddings From Files
show_tokens             Show token output of recipe
step_clean_levels       Clean Categorical Levels
step_clean_names        Clean Variable Names
step_dummy_hash         Indicator Variables via Feature Hashing
step_lda                Calculate LDA Dimension Estimates of Tokens
step_lemma              Lemmatization of Token Variables
step_ngram              Generate n-grams From Token Variables
step_pos_filter         Part of Speech Filtering of Token Variables
step_sentence_embeddings
                        Sentence Embeddings of Text
step_sequence_onehot    Positional One-Hot encoding of Tokens
step_stem               Stemming of Token Variables
step_stopwords          Filtering of Stop Words for Tokens Variables
step_text_normalization
                        Normalization of Character Variables
step_textfeature        Calculate Set of Text Features
step_texthash           Feature Hashing of Tokens
step_tf                 Term frequency of Tokens
step_tfidf              Term Frequency-Inverse Document Frequency of
                        Tokens
step_token_replace      Replace Tokens in a Token Variable
step_tokenfilter        Filter Tokens Based on Term Frequency
step_tokenize           Tokenization of Character Variables
step_tokenize_bpe       BPE Tokenization of Character Variables
step_tokenize_sentencepiece
                        Sentencepiece Tokenization of Character
                        Variables
step_tokenize_wordpiece
                        Wordpiece Tokenization of Character Variables
step_tokenmerge         Combine Multiple Token Variables Into One
step_untokenize         Untokenization of Token Variables
step_word_embeddings    Pretrained Word Embeddings of Tokens
tokenlist               Create Token Object
