NLP

Django application to build and maintain chatbots that combine the best of LLMs and rule-based engines to truly assist your users instead of manipulating them.

Your very own Assistant. Because you deserve it.

Terminal Chat Completion client for OpenAI LLM models written in Go

Command Line Interface for developers of qary -- the open source, teachable AI assistant that truly assists, rather than manipulating you.

Resources for interns and new team members at Tangible AI

Le Mot Diplomatique trace l'historique de la première apparition d'un mot dans Le Monde Diplomatique.

viky.ai is a Natural Language Processing platform. It allows you to extract information from unstructured text contents.

Spelling numbers in Ukrainian

Multi-agent system that can be used to predict movie score using contents of its review.

replicated sentiment analysis https://github.com/bentrevett/pytorch-sentiment-analysis/blob/master/1%20-%20Simple%20Sentiment%20Analysis.ipynb

Bug fixes for the abandoned python Wikipedia project to warn the user when the Wikpedia suggestion engine is corrupting the titles of valid Wikipedia articles. Required for the examples in Natural Language Processing in Action, 2nd Edition by Maria Dyshel and Hobson Lane (and a community of more than 30 contributing authors and editors).

Natural Language Understanding for math symbols, digits, and words with a Gradio user interface and REST API.

Conversational math active learning for K-12 students (chatbot math tutor).

This is is the working repository for text style transfer survey.

Code and data for Natural Language Processing in Action, 2nd Edition, by Maria Dyshel and Hobson Lane for Manning Publications

Fork of Rubrix for natural language processing machine learning dataset labeling and RLHF (reinforcement learning human feedback) and active learning. Original license was Apache 2.0 which allows Argilla.io to modify the software without sharing it with the community.

Word2vec, FastText, GloVE embedding accuracy comparison using analogy, vector-oriented reasoning, synonym and conjugation datasets from multiple sources.

NLP pipelines to extract aligned triples from snippets of text