| Name | Version | Summary | date |
| jajula-chunking |
0.1.1 |
A comprehensive text chunking library for RAG applications with multiple strategies |
2025-08-26 18:54:18 |
| splurge-tools |
2025.4.3 |
Python tools for data type handling and validation |
2025-08-25 17:50:46 |
| mon-tokenizer |
0.1.3 |
A simple tokenizer for Mon text |
2025-08-23 15:45:38 |
| burmese-tokenizer |
0.1.3 |
A simple tokenizer for Burmese text |
2025-08-23 04:26:14 |
| PyTokenCounter |
1.8.2 |
A Python library for tokenizing text and counting tokens using various encoding schemes. |
2025-08-22 03:20:04 |
| yosina |
0.1.0 |
Japanese text transliteration library |
2025-08-19 18:28:38 |
| pdf-requirement-extractor |
2.0.0 |
Extract structured brand requirements from PDF documents |
2025-08-19 06:27:19 |
| contextgem |
0.16.1 |
Effortless LLM extraction from documents |
2025-08-19 01:36:16 |
| fleetfluid |
0.1.3 |
AI Agent Functions for ETL Processing |
2025-08-17 22:47:23 |
| transpolibre |
0.8.15 |
Automate translation of gettext PO files using LibreTranslate, Ollama, and local models |
2025-08-17 19:44:47 |
| turbotok |
0.2.0 |
High-performance NumPy-based tokenizer library |
2025-08-17 04:27:30 |
| reliq |
0.0.44 |
Python ctypes bindings for reliq |
2025-08-16 11:23:43 |
| lingo-nlp-toolkit |
2.3 |
Advanced NLP Toolkit - Lightweight, Fast, and Transformer-Ready |
2025-08-15 08:42:51 |
| blobify |
1.1.0 |
Package your entire codebase into a single text file for AI consumption |
2025-08-09 09:43:13 |
| docxmd-converter |
3.0.0 |
Convert between .docx and .md files with template support and advanced document post-processing |
2025-08-09 08:17:00 |
| uneff |
1.0.1 |
Remove BOM and problematic Unicode characters from text files |
2025-08-06 11:54:47 |
| hashub-vector |
1.0.0 |
Python SDK for Hashub Vector API - High-quality multilingual text embeddings |
2025-08-03 22:00:05 |
| linkai-aion |
0.1.6 |
🚀 LinkAI-Aion v0.1.6 — Enhanced AI Utilities with File Management, Code Parsing, and Real-time Monitoring |
2025-08-03 21:55:07 |
| ultranlp |
1.0.6 |
Ultra-fast, comprehensive NLP preprocessing library with advanced tokenization |
2025-08-02 10:21:43 |
| lsdembed |
0.3.0 |
Physics-inspired text embedding library |
2025-08-01 19:36:33 |