Skip to content

@scientist-labs Scientist Labs

Change the repository type filter

All

    Repositories list

    16 repositories

    • parsekit

      Public
      Ruby document parsing toolkit with zero runtime dependencies. Parse PDFs, DOCX, XLSX, and images (with OCR) using a single, lightweight gem. Statically links MuPDF and Tesseract at compile time for hassle-free installation - no system libraries or external tools required.
      rubymetadatacontentextraction
      Ruby
      •
      MIT License
      •1•40•0•1•Updated Oct 13, 2025Oct 13, 2025

    • fastsheet

      Public
      FastSheet is the fastest XLSX file parser for Ruby (at the time of release). It leverages a Rust library for high-performance parsing, making it significantly faster than other available solutions.
      Ruby
      •
      MIT License
      •7•0•0•0•Updated Oct 9, 2025Oct 9, 2025

    • scientist-labs.github.io

      Public
      Scientist-labs portfolio page.
      TypeScript
      •
      MIT License
      •2k•0•0•0•Updated Sep 30, 2025Sep 30, 2025

    • tokenkit

      Public
      Fast, Rust-backed word-level tokenization for Ruby. Unlike subword tokenizers (BPE, WordPiece) designed for LLMs, TokenKit provides linguistic tokenization for search engines, text mining, and NLP pipelines—preserving domain-specific patterns like gene names, measurements, and technical terms while handling Unicode correctly.
      rubynlptokenizer
      Ruby
      •
      MIT License
      •0•3•0•0•Updated Sep 29, 2025Sep 29, 2025

    • spellkit

      Public
      Fast, safe typo correction for Ruby. SymSpell-based spell checker with Rust performance, term protection via regex patterns, and hot-reloadable dictionaries. Sub-millisecond latency, zero dependencies.
      rubynlpspellcheck
      Ruby
      •
      MIT License
      •0•6•0•0•Updated Sep 28, 2025Sep 28, 2025

    • phrasekit

      Public
      Weak supervision for NER: mine domain-specific phrases from unlabeled corpora, score by salience, and auto-generate training labels. Ruby gem with high-performance Rust engines.
      rubynlplabelingner
      Rust
      •
      MIT License
      •0•0•0•1•Updated Sep 28, 2025Sep 28, 2025

    • indradb

      Public
      A graph database written in rust
      Rust
      •
      Mozilla Public License 2.0
      •130•1•0•1•Updated Sep 25, 2025Sep 25, 2025

    • ragnar-cli

      Public
      Ragnar is a pure Ruby command-line RAG (Retrieval-Augmented Generation) tool with zero external dependencies. It provides local document indexing, semantic search, and LLM-powered query processing. Built to be hackable, it lets Ruby developers experiment with agentic workflows and RAG pipelines natively in Ruby.
      rubycliairag
      Ruby
      •
      MIT License
      •1•7•0•1•Updated Sep 15, 2025Sep 15, 2025

    • red-candle

      Public
      Ruby gem for running state-of-the-art language models locally. Access LLMs, embeddings, rerankers, and NER models directly from Ruby using Rust-powered Candle with Metal/CUDA acceleration.
      rubymagnushuggingface-candle
      Rust
      •
      MIT License
      •6•184•3•1•Updated Sep 13, 2025Sep 13, 2025

    • thor-interactive

      Public
      Turn any Thor CLI into an interactive REPL with persistent state, auto-completion, and configurable default handlers for unrecognized input.
      rubyclithor
      Ruby
      •
      MIT License
      •0•2•0•2•Updated Sep 8, 2025Sep 8, 2025

    • lancelot

      Public
      Ruby bindings for the Lance columnar data format. Built on the Lance Rust crate, Lancelot brings high-performance vector search, full-text search, and hybrid retrieval to Ruby applications with a native, idiomatic API.
      rubyaiembeddingsvector-databasellm
      Ruby
      •
      MIT License
      •0•7•0•0•Updated Sep 8, 2025Sep 8, 2025

    • clusterkit

      Public
      High-performance UMAP dimensionality reduction for Ruby, powered by the annembed Rust crate. Fast, memory-efficient manifold learning with model persistence.
      rubyaiclusteringembeddingsumapllm
      Ruby
      •
      MIT License
      •1•5•0•0•Updated Sep 6, 2025Sep 6, 2025

    • topical

      Public
      Ruby library for fast, flexible topic modeling — built on modern embeddings and clustering techniques to uncover themes in text.
      rubynlprubygemaitopic-modeling
      Ruby
      •
      MIT License
      •0•10•1•0•Updated Sep 6, 2025Sep 6, 2025

    • annembed

      Public
      data embedding based on approximate nearest neighbour
      Rust
      •
      Other
      •8•0•0•3•Updated Sep 6, 2025Sep 6, 2025

    • hnswlib-rs

      Public
      Rust implementation of the HNSW algorithm (Malkov-Yashunin)
      Rust
      •
      Other
      •38•0•0•1•Updated Aug 19, 2025Aug 19, 2025

    • rrf

      Public
      Reciprocal Rank Fusion for Ruby
      Ruby
      •
      MIT License
      •0•5•1•1•Updated Jul 18, 2025Jul 18, 2025