Text-processing Packages

Determine the East Asian Width of a Unicode character

A utility library for full-text search in TypeScript

Utility for extracting chinese characters from a string

NodeJS library that semantically chunks text and matches it against a user query using cosine similarity for precise and relevant text retrieval

A highly efficient, isomorphic, full-featured, multilingual text search engine library, providing full-text search, fuzzy matching, phonetic scoring, document indexing and more, with micro JSON state hydration/dehydration in-browser and server-side.

A powerful wrapper around the OpenAI API, providing additional features and making it easier to interact with AI models. Seamlessly chat with your AI assistant, include context strings, and manage conversation history.

Semantically create chunks from large texts. Useful for workflows involving large language models (LLMs).

Visualization of statistic peaks and valleys TE ranks

BulkAI is a powerful Node.js CLI tool designed to automate the processing of markdown and text files using OpenAI's GPT-4.

Chunked Augmented Generation (CAG) algorithm for processing large text inputs with AI models

Non linear text processing system

generate excerpt from html text while preserving html structure

A powerful TypeScript library designed to simplify a wide range of string operations and manipulations.

Encode and decode Unicode escapes in a string

A powerful React hook for text summarization using Google's Generative AI API. Easily integrate advanced text summarization capabilities into your React applications.

An innovative text processing and animation library for web applications, providing a versatile API for splitting text into HTML elements with customizable alignments, animations, and effects. Supports dynamic content updates, text randomization, and exte

One Dionys (String Utils) - Provides useful functions for manipulating strings and can be used in typescript/javascript.

A tool for semantic chunking of text

Semantically create chunks from large texts. Useful for workflows involving large language models (LLMs).

A library of stream classes for semantic text processing, including sources like Wikipedia and news articles.