mnl-ws-norm
Light-weight tool for normalizing whitespace, splitting lines, and accurately tokenizing words (no regex). Multiple natural languages supported.
Light-weight tool for normalizing whitespace, splitting lines, and accurately tokenizing words (no regex). Multiple natural languages supported.
Nuxt SplitType
Tools to process text from pdfs for splitting, etc for use with AI and LLMs
A utility for compressing and splitting PDF files using Ghostscript and PDF-Lib.
Semantically create chunks from large texts. Useful for workflows involving large language models (LLMs).
Split Salesforce metadata files
A React Package For Splitting Text Into Characters, Words And Lines.
Use promisises and asynchronous component loading hook for React.js
Semantically create chunks from large texts. Useful for workflows involving large language models (LLMs).
Implementation of particular tar streaming use cases