JSPM

Found 184 results for text-processing

@elpassion/semantic-chunking

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

  • v3.0.2
  • 19.14
  • Published

conversation-engine

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.

  • v0.0.4
  • 18.39
  • Published

fibrio

Server-side DOM text manipulator (Node.js).

  • v0.1.2
  • 17.42
  • Published

llm-distillery

Use LLMs to run map-reduce summarization tasks on large documents until a target token size is met.

  • v1.2.0
  • 16.97
  • Published

rag-module

A TypeScript/JavaScript module for implementing Retrieval-Augmented Generation (RAG) using Qdrant vector database, Google's Generative AI embeddings, and Groq LLM.

    • v1.4.1
    • 16.44
    • Published

    @md2docx/core

    Core engine to convert extended MDAST to DOCX. Supports plugins for footnotes, images, lists, tables, and more. Designed for seamless Markdown-to-DOCX conversion.

    • v1.5.0
    • 16.29
    • Published

    matter-json

    JSON front-matter parser and combiner. Minimal and perfect

    • v1.0.0
    • 16.08
    • Published

    @md2docx/remark-docx

    A unified plugin to prepare MDAST trees for DOCX conversion using mdast2docx.

    • v0.1.0
    • 15.63
    • Published

    @mdast2docx/core

    Core engine to convert extended MDAST to DOCX. Supports plugins for footnotes, images, lists, tables, and more. Designed for seamless Markdown-to-DOCX conversion.

    • v1.5.0
    • 15.03
    • Published

    trace.ai-cli

    A powerful AI-powered CLI tool

    • v1.1.8
    • 14.92
    • Published

    stringzy

    A versatile string manipulation library providing a range of text utilities for JavaScript and Node.js applications.

    • v3.0.0
    • 14.82
    • Published

    turkish-tools

    Kapsamlı Türkçe veri işleme, doğrulama, formatlama ve sahte Türkçe veri üretme araçları kütüphanesi

    • v1.1.0
    • 14.46
    • Published

    cparse

    一个基于 Cheerio 的 HTML 解析和数据提取工具库

    • v2.2.0
    • 14.26
    • Published

    sim-ph

    Talk to Sim with Teach Feature

      • v1.0.2
      • 13.91
      • Published

      txtzip

      Text file bundling tool that preserves file structure. Nice for sending multiple files in one shot to large language models.

      • v1.7.0
      • 13.43
      • Published

      chunk-match

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

      • v1.1.6
      • 13.39
      • Published

      thai-address-splitter

      Split long Thai address strings into structured components (name, phone, address, subdistrict, district, province, zipcode). Handles names without title prefixes, location name conflicts, and province abbreviations.

      • v1.0.0
      • 13.25
      • Published

      lycy

      Uzbek to Cyrillic transliterator

      • v1.0.0
      • 13.22
      • Published

      @mdast2docx/remark-docx

      A unified plugin to prepare MDAST trees for DOCX conversion using mdast2docx.

      • v0.1.0
      • 13.11
      • Published

      semantic-stream

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

      • v3.0.0
      • 12.69
      • Published

      @dezren39/chunk-text

      🔪 chunk/split a string by length without cutting/truncating words.

      • v2.3.12
      • 12.41
      • Published

      thai-keyboard-corrector

      Corrects text typed with the wrong Thai/English keyboard layout

      • v1.0.1
      • 11.60
      • Published

      @mdast2docx/mdast

      Extended MDAST types and custom node data for mdast2docx with support for DOCX formatting.

      • v0.2.4
      • 11.56
      • Published

      split-tracklist

      split tracklist text to object contains artist and title of each track

      • v1.1.1
      • 11.45
      • Published

      damkar-ui-components

      React components for DamkarAI - AI-powered text and code assistant

      • v1.0.1
      • 11.10
      • Published

      use-react-summary

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

      • v1.1.8
      • 11.10
      • Published

      @js-utility/string

      A lightweight and powerful collection of string utility functions for Node.js - trimming, casing, formatting, and more.

      • v1.0.1
      • 11.10
      • Published

      @mdast2docx/image

      MDAST to DOCX plugin for resolving and embedding images. Supports base64, URLs, and custom resolvers for seamless DOCX image integration.

      • v1.3.1
      • 11.08
      • Published

      @basd/search

      A powerful and flexible text search library for JavaScript that enables you to build a simple text search engine.

      • v0.0.5
      • 10.97
      • Published

      ba-linkify

      Process links in text. Ben Alman's linkify.js adaptation

      • v1.0.1
      • 10.74
      • Published

      @md2docx/math

      Plugin to convert mathematical expressions in Markdown (MDAST) to DOCX using LaTeX-style syntax. Integrates seamlessly with mdast2docx.

      • v0.0.6
      • 10.69
      • Published

      @mdast2docx/table

      Plugin to convert Markdown tables (MDAST) to DOCX with support for rich formatting and seamless integration into mdast2docx.

      • v0.0.7
      • 10.69
      • Published

      @md2docx/list

      Plugin to convert ordered and unordered lists from Markdown (MDAST) to DOCX. Supports nesting, custom bullets, and numbering styles.

      • v0.0.8
      • 10.69
      • Published

      @callmedayz/ai-prompt-toolkit

      Professional AI prompt engineering toolkit with advanced template features, real-time dashboards, conditional logic, template inheritance, live monitoring, OpenRouter integration, and 310+ model support

      • v2.6.2
      • 10.64
      • Published

      @md2docx/image

      MDAST to DOCX plugin for resolving and embedding images. Supports base64, URLs, and custom resolvers for seamless DOCX image integration.

      • v1.3.1
      • 10.64
      • Published

      @md2docx/table

      Plugin to convert Markdown tables (MDAST) to DOCX with support for rich formatting and seamless integration into mdast2docx.

      • v0.0.7
      • 10.55
      • Published

      mdast-to-docx

      Convert Markdown Abstract Syntax Tree (MDAST) to DOCX seamlessly. Supports footnotes, images, links, and customizable document properties.

      • v1.4.1
      • 10.31
      • Published

      @md2docx/mdast

      Extended MDAST types and custom node data for mdast2docx with support for DOCX formatting.

      • v0.2.4
      • 10.28
      • Published

      bulkai

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

        • v1.2.5
        • 10.20
        • Published

        @md2docx/emoji

        A plugin for @m2d/core that parses emoji shortcodes like :smile: and replaces them with their corresponding Unicode emoji characters for DOCX output.

        • v0.1.3
        • 10.20
        • Published

        string-master

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

        • v1.0.2
        • 10.17
        • Published

        @oxog/string

        Comprehensive string manipulation utilities with zero dependencies

        • v1.0.0
        • 10.10
        • Published

        strip-diacritics

        Remove diacritics (accents, special characters, and marks) from text, making it easier to normalize, search, and process text across multiple languages.

        • v1.0.0
        • 10.10
        • Published

        sentiment-analyze

        A lightweight and easy-to-use npm package for performing sentiment analysis on text. Analyze the positivity, negativity, or neutrality of any string input with ease, and process multiple texts in batch for more efficient analysis.

        • v2.0.3
        • 9.78
        • Published

        ai-dataset-generator

        A tool to generate AI fine-tuning datasets from text files

        • v1.0.9
        • 9.46
        • Published

        @jlhv/string-helper

        A simple utility library for string manipulation.

        • v1.0.7
        • 9.45
        • Published

        @mdast2docx/emoji

        A plugin for @m2d/core that parses emoji shortcodes like :smile: and replaces them with their corresponding Unicode emoji characters for DOCX output.

        • v0.1.3
        • 9.45
        • Published

        shibal

        <h1 align="center">Welcome to Shiba - your strings helper! 👋 </h1>

        • v1.0.2
        • 9.39
        • Published

        cag-js

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

        • v1.0.4
        • 9.19
        • Published

        @azizbecha/strkit

        strkit is a utility library offering a collection of essential string functions including validation, case conversion, truncation, and more. Ideal for both JavaScript and TypeScript developers to simplify string operations in their applications.

        • v1.1.1
        • 9.16
        • Published

        block-page

        Non linear text processing system

        • v1.0.8
        • 9.00
        • Published

        @cangokceaslan/padder

        A template for padding utils function for Strings in JavaScript / NodeJs

        • v1.0.3
        • 9.00
        • Published

        id-auto-formalizer

        Konversi teks Bahasa Indonesia dari kasual ke formal untuk surat, email, dan laporan resmi

        • v0.1.0
        • 9.00
        • Published

        matter-toml

        TOML front-matter parser and combiner. Minimal and perfect

        • v1.0.0
        • 8.83
        • Published

        better-excerpt-html

        generate excerpt from html text while preserving html structure

        • v1.0.4
        • 8.83
        • Published

        vietnamese-search

        Slugify and search Vietnamese text with diacritics support

        • v1.0.0
        • 8.59
        • Published

        @mdast2docx/list

        Plugin to convert ordered and unordered lists from Markdown (MDAST) to DOCX. Supports nesting, custom bullets, and numbering styles.

        • v0.0.8
        • 8.56
        • Published

        @a95z/slugify

        A utility function to convert a string into a URL-friendly slug, with support for string sanitization, normalization, and transformation.

        • v1.0.1
        • 8.50
        • Published

        turkce-js

        TDK (Türk Dil Kurumu) sözlüğünden kelime anlamlarını, köken bilgilerini ve atasözlerini getiren Node.js paketi.

        • v1.2.5
        • 8.50
        • Published

        n8n-nodes-arabicedita

        ArabicEdita is n8n community node to fix the arabic writing problem in editimage builin node in n8n

        • v0.1.1
        • 8.48
        • Published

        contacted-chunking

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

        • v2.4.1
        • 8.28
        • Published

        cyprinq

        Visualization of statistic peaks and valleys TE ranks

        • v1.0.6
        • 7.94
        • Published

        unimodaly-ingest

        A unified data-ingestion CLI that auto-detects and converts text, image, audio and tabular sources into standardized training datasets

        • v1.0.0
        • 7.89
        • Published

        matter-yaml

        YAML front-matter parser and combiner. Minimal and perfect

        • v1.1.0
        • 7.64
        • Published

        extract-zhongwen

        Utility for extracting chinese characters from a string

        • v1.1.2
        • 7.32
        • Published

        pure-flow-ai

        🤖 Smart text analysis package for detecting positive and negative words with AI support. Features customizable word lists, multiple languages, and AI-powered sentiment analysis. Perfect for content moderation, sentiment analysis, and text filtering in an

        • v1.1.0
        • 7.19
        • Published

        str-hex-utils

        A simple utility library for string manipulations including case transformations and hexadecimal conversions.

        • v1.0.1
        • 7.16
        • Published

        gbdetector

        GbDetector is an advanced text analysis module designed to identify gambling-related content through sophisticated pattern matching and text processing techniques.

        • v1.1.2
        • 7.13
        • Published

        punctuation-restore

        🧑‍🏭 Node.js package for restoring punctuation and casing to strings via ONNX Model `punctuation_fullstop_truecase_english`

        • v0.1.0
        • 6.90
        • Published

        onedionys-string-utils

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

        • v1.0.1
        • 6.45
        • Published

        text-pipe

        Transform stream enumeratee generators for stream-driven data extract and transformation (i.e. ETL).

        • v0.8.0
        • 6.30
        • Published

        anonymizer-tool

        A powerful tool to anonymize sensitive data, allowing reversible decoding.

        • v1.0.3
        • 6.19
        • Published

        slug-press

        A library for generating slug based on the input string and the ability to configure parameters

        • v1.0.1
        • 6.05
        • Published

        @mdast2docx/math

        Plugin to convert mathematical expressions in Markdown (MDAST) to DOCX using LaTeX-style syntax. Integrates seamlessly with mdast2docx.

        • v0.0.6
        • 5.23
        • Published

        js-string-toolkit

        A simple Node.js utility module for common string operations.

        • v0.0.3
        • 5.22
        • Published

        possessive-js

        A JavaScript library for handling singular possessive apostrophes with support for international names

        • v0.1.0
        • 3.66
        • Published

        @lerypapa/clean-text

        Batch process text files using OpenAI API to clean and transform content

          • v1.0.0
          • 2.38
          • Published

          live-word-count

          A real-time word counting utility for text input

          • v1.0.4
          • 2.29
          • Published

          skyliner

          Universal outlining engine. Generate an outline of any text-based document! CLI included.

          • v0.3.1
          • 2.14
          • Published

          @bakemono-san/utilities

          this is a lightweight and modular library providing a comprehensive set of utility functions to streamline development workflows. It is designed to simplify common tasks in software projects, including string manipulation, array operations, date handling,

          • v1.0.0
          • 0.00
          • Published

          unique-title-extractor

          A Node.js package to extract unique titles based on cosine similarity.

          • v1.0.1
          • 0.00
          • Published

          @tsports/uniseg

          Complete TypeScript port of rivo/uniseg with 100% API compatibility. Unicode text segmentation for grapheme clusters, word boundaries, and text width calculation.

          • v0.4.7-tsport
          • 0.00
          • Published

          deslopify

          Utility to clean up text by removing or translating common 'slop' patterns

          • v0.1.2
          • 0.00
          • Published

          @vipulc/line-match

          Returns lines matching a pattern in a string. Supports inverse operation as well, to exclude lines with matches.

          • v1.0.3
          • 0.00
          • Published

          @viettv/universal-utils

          A comprehensive utility library for file operations, HTTP requests, data processing, and more

          • v1.1.0
          • 0.00
          • Published

          antiemdash

          Remove or replace em dashes (—) in strings with a simple boolean parameter

          • v1.0.1
          • 0.00
          • Published

          zodtractor

          AI-powered text extraction using Zod schemas

          • v1.0.3
          • 0.00
          • Published