Search results
225 packages found
Sort by: Default
- Default
- Most downloaded this week
- Most downloaded this month
- Most dependents
- Recently published
A pure JavaScript implementation of a BPE tokenizer (Encoder/Decoder) for GPT-2 / GPT-3 / GPT-4 and other OpenAI models
- BPE
- encoder
- decoder
- tokenizer
- GPT
- GPT-2
- GPT-3
- GPT-3.5
- GPT-4
- GPT-4o
- NLP
- Natural Language Processing
- Text Generation
- OpenAI
- View more
Talk to Sim with Teach Feature
- sim
- sim-ph
- simsimi api
- teach
- chatbot
- simsimi
- API
- wrapper
- conversation
- bot
- artificial-intelligence
- AI
- machine-learning
- natural-language
- View more
Developer friendly Natural Language Processing ✨
- NLP
- natural language processing
- tokenize
- SBD
- sentence boundary detection
- negation handling
- sentiment analysis
- POS Tagging
- NER
- named entity extraction
- custom entity detection
- word vectors
- visualization
- pattern matching
- View more
Recall-Oriented Understudy for Gisting Evaluation (ROUGE) Evaluation Functions with TypeScript support
Wink's English Language Light Web Model for Web Browsers
An Implementation of Jaro Distance Algorithm by Matthew A. Jaro
- Jaro
- Jaro Distance
- Jaro Similarity
- String Matching
- String Similarity
- NLP
- Natural Language Processing
- Similarity
- wink
Implementation of Porter Stemmer Algorithm V2 by Dr Martin F Porter
Multilingual tokenizer that automatically tags each token with its type
Library for NLU (Natural Language Understanding) done in Node.js
- natural language processing
- artifical intelligence
- natural language understanding
- natural language generation
- NLP
- NLU
- NLG
- sentiment analysis
- classifier
- logistic regression
- Natural
- entity extraction
- named entity recognition
- chatbot
Distance/Similarity functions for Bag of Words, Strings, Numbers, Dates and Vectors.
- Distance
- Similarity
- NLP
- Bag of Words
- Strings
- Vectors
- Chebyshev
- Cosine
- Hamming
- Jaccard
- Jaro
- Manhattan
- Soundex
- Tversky
- View more
NLP Functions for amplifying negations, managing elisions, creating ngrams, stems, phonetic codes to tokens and more.
- Tokenize
- Stem
- NGrams
- Bag of Words
- Phonetize
- Soundex
- Stop Words
- Sentence Breaking
- Regex
- NLP
- Natural Language Processing
Count the number of OpenAI tokens in a string. Supports all OpenAI Text models (text-davinci-003, gpt-3.5-turbo, gpt-4)
- openai
- gpt
- gpt3
- openai tokens
- tokens
- gpt3 tokens
- gpt3 token counter
- openai token counter
- token gpt3
- gpt4
- gpt4 tokens
- gpt4 token counter
- openai gpt4
- gpt-3.5-turbo
- View more
Recall-Oriented Understudy for Gisting Evaluation (ROUGE) Evaluation Functions
English lemmatizer
novel-segment segment data
- NLP
- PanGuSegment
- PoS tagging
- analyzer
- async
- chinese
- chinese segmentation
- data
- dict
- dictionary
- file
- hanzi
- jieba
- load
- View more
Chinese word segmentation 簡繁中文分词模块 以網路小說為樣本
- NLP
- PanGuSegment
- PoS tagging
- analyzer
- async
- chinese
- chinese segmentation
- data
- dict
- dictionary
- file
- hanzi
- jieba
- load
- View more
Natural-language event parser for Javascript.
Calculate BLEU score for reference and candidate sentences.
Configurable BM25 Text Search Engine with simple semantic search support
- BM25
- BM25F
- TFIDF
- TF-IDF
- In Memory Search
- Semantic Search
- Full Text Search
- NLP
- Natural Language Processing
- wink
- NLP
- PanGuSegment
- PoS tagging
- analyzer
- async
- chinese
- chinese segmentation
- data
- dict
- dictionary
- file
- hanzi
- jieba
- load
- View more