Unsupervised text tokenizer for Neural Network-based text generation.

A port of biocommons/hgvs to the Rust programming language

HGVS Nomenclature website

AICI: Prompts as (Wasm) Programs

Repository for G-Retriever

Pydantic extension for annotating autocorrecting fields.

Rapid fuzzy string matching in Python using various string metrics

A fast and modern parser combinator library for Scala

the AI-native open-source embedding database

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Structured Text Generation

OCR, layout analysis, reading order, line detection in 90+ languages

LLM Chain for answering questions from documents with citations

read, write, and view HTML tables in Julia.