The Narsil search engine works inside a Python process, with full-text, vector, and hybrid search through the Rust implementation, a blocking API, and an asyncio API.
Library designed as a python wrapper to unleash Rust text processing power combined with Python
Sculpt: Structuring unstructured data with LLMs
This module assist with providing a text model for processing command line arguments. See jk_argparsing for details.
Fast, typed Python library for Persian language localization
The best open-source Russian text normalization for TTS and NLP: numbers, dates, abbreviations, Roman numerals, CAPS, and Latin-to-Cyrillic transliteration
Parses unstructured recipe ingredient text into standardized quantities, units, and foods
Latin and Ancient Greek text preprocessing: U/V normalization, long-s correction, elision canonicalization, and more
Natural, queryable access to Quranic text and morphology
A powerful tool for transforming documents into graph-based structures using Large Language Models (LLMs).
Convert raw documents into AI-understandable context with intelligent text extraction, table detection, and semantic chunking
A lightweight Python library for common text-processing operations.
Parse, analyse, and transform G-code files — plain-text .gcode and Prusa .bgcode
A lightweight Python library for common text-processing operations.
Open-source tool for exploring, labeling, and monitoring data for NLP projects.
pre-processing package for text strings
A lightweight library with useful tools for common text-processing operations.
Generates a shortest edit script (Myers' diff algorithm) to indicate how to get from the strings in column A to the strings in column B. Also provides the edit distance (levenshtein). This is the Python binding.
High-performance C implementation of BPE tokenizer
Croatian language stemmer based on the Ljubešić-Pandžić algorithm
tok: a plain-text language for process models (BPMN 2.0, DMN, forms, simulation)
A lightweight Python library for common text-processing operations
Text processing tool, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting hashtags) and spell correction.
A Model Context Protocol server for Amazon Translate to provide text translation, custom terminology management, and batch translation processing
Snips Natural Language Understanding library
Generalist model for NER (Extract any entity types from texts). Fork of the original project to relax the strict Transformers version requirement.
Tools, wrappers, etc... for data science with a concentration on text processing
ArchiTXT is a tool for structuring textual data into a valid database model. It is guided by a meta-grammar and uses an iterative process of tree rewriting.
A Python stream editor for command-line calls or integration into Python programs.
An Arabic text processing library intended for use in NLP applications.
A blazing fast Byte Pair Encoding (BPE) tokenizer library with Python bindings
Text2Text Language Modeling Toolkit
fenic is a Python DataFrame library for processing text data with APIs inspired by PySpark.
Pyline is a grep-like, sed-like, awk-like command-line tool for line-based text processing in Python.
NLP text processing toolkit for Deep Learning
Detect dirty slang in russian texts and process it
PyThaiNLP For spaCy
Educational Python tools and library helpers for Network Operations automation
A forum scraper library
Melusine is a high-level library for emails processing
Sockit is a natural-language processing toolkit for modeling structured occupation information and Standard Occupational Classification (SOC) codes in unstructured text from job titles, job postings, and resumes.
Tools for Arabic script
A modern, high-performance image processing library for Python, powered by Rust.
easily bult LDA Topic Models with just a list of docs (e.g. a list of twitter posts in CSV/TXT
Cleans messy data files: turns list strings into NumPy arrays, fixes mixed types and numbers stored as text, removes outliers, selects features, and reads or saves any common format.
High-performance n-gram generation for Polars