8 projects
bulk-chain
A lightweight, no-strings-attached Chain-of-Thought framework for your LLM, ensuring reliable results for bulk input requests.
arekit
Document level Attitude and Relation Extraction toolkit (AREkit) for sampling and prompting mass-media news into datasets for ML-model training
source-iter
This is a tiny Python package that serves read/write iterators for most mandatory sources via default packages like CSV / JSONL / SQLite
bulk-translate
A tiny Python no-string package for performing translation of a massive CSV/JSONL files with optionally pre-annotated object spans
bulk-ner
A no-strings inference implementation framework Named Entity Recognition (NER) service of wrapped AI models powered by AREkit and the related text-processing pipelines.
arelight
About Mass-media text processing application for your Relation Extraction task, powered by AREkit.
arekit-ss
Low Resource Context Relation Sampler for contexts with relations for fact-checking and fine-tuning your LLM models, powered by AREkit
arenets
Tensorflow-based framework which lists implementation of conventional neural network models (CNN, RNN-based) for Relation Extraction classification tasks as well as API for custom model implementation
