DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models
ExtractThinker is a Document Intelligence library for LLMs
Extract schema, statistics and entities from datasets
A natural language interface for computers
Obsei is a low code AI powered automation tool
An open-source NLP research library, built on PyTorch
A model library for exploring state-of-the-art deep learning
A Chinese information extraction tool
Library to scrape and clean web pages to create massive datasets
Lexicon and rule-based sentiment analysis tool