Nlp Tools Python Packages

embeddingcache

Retrieve text embeddings, but cache them locally if we have already computed them.

a2t

Ask2Transformers is a library for zero-shot classification based on Transformers.

mschunker

Smart text chunker for LLM preprocessing (sections → paragraphs → sentences → hard splits).

pdf-snip

PdfSnipper is a lightweight and efficient Python package designed to simplify the management of PDF files, pages, and their conversions during various NLP, Computer Vision (CV), or other data processing tasks. The package eliminates the need for repetitive code by providing intuitive, ready-to-use functions for common PDF-related operations.