Skip to content

@stanford-oval Stanford Open Virtual Assistant Lab

All

    Repositories list

    118 repositories

    • clinical-trial-matching

      Public
      Stanford OVAL Clinical Trial Matcher, developed with Mayo Clinic, combines SatIR and VERDICT for scalable, high-recall trial retrieval and accountable eligibili…
      Python
      •
      Apache License 2.0
      •0•4•0•0•Updated Sep 14, 2026Sep 14, 2026

    • oval-website

      Public
      The new OVAL website
      Astro
      •4•8•0•0•Updated Sep 4, 2026Sep 4, 2026

    • DataSTORM

      Public
      DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling https://arxiv.org/abs/2604.06474
      Python
      •
      Apache License 2.0
      •1•7•0•0•Updated Aug 19, 2026Aug 19, 2026

    • suql

      Public
      SUQL: Conversational Search over Structured and Unstructured Data with LLMs
      Python
      •
      Apache License 2.0
      •39•308•5•2•Updated Aug 11, 2026Aug 11, 2026

    • pyalmond

      Public
      Python client for the Almond API
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •3•5•0•2•Updated Jul 21, 2026Jul 21, 2026

    • sliders

      Public
      Repository for paper: Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets
      agentsdocument-ailong-context
      agentsdocument-ailong-context
      Python
      •
      MIT License
      •3•29•1•0•Updated Apr 27, 2026Apr 27, 2026

    • Churro

      Public
      CHURRO is an OCR toolkit for historical document transcription, built to make handwritten and printed sources readable at high accuracy and lower cost.
      markdownpdfocr
      markdownpdfocraipdf-converterdocumentspdf-to-textdocument-parserlarge-language-modelsdocument-parsing
      Python
      •
      Apache License 2.0
      •5•74•4•1•Updated Apr 18, 2026Apr 18, 2026

    • spinach

      Public
      SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions
      Jupyter Notebook
      •
      Apache License 2.0
      •26•77•4•0•Updated Feb 26, 2026Feb 26, 2026

    • WikiChat

      Public
      WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
      nlpnatural-language-processingchatbot
      nlpnatural-language-processingchatbotragfactualityllmemnlp2023
      Python
      •
      Apache License 2.0
      •147•1.6k•8•2•Updated Jan 31, 2026Jan 31, 2026

    • Lemonade

      Public
      LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World
      Python
      •
      Apache License 2.0
      •4•22•1•0•Updated Nov 8, 2025Nov 8, 2025

    • genie-worksheets

      Public
      Specification for creating reliable LLM-based conversational agents
      HTML
      •29•69•4•0•Updated Oct 20, 2025Oct 20, 2025

    • storm

      Public
      An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
      nlpnaaclreport-generation
      nlpnaaclreport-generationknowledge-curationlarge-language-modelsretrieval-augmented-generationagentic-ragemnlp2024deep-research
      Python
      •
      MIT License
      •2.9k•31k•59•49•Updated Sep 30, 2025Sep 30, 2025

    • inconsistency-detection

      Public
      Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models
      Python
      •
      Apache License 2.0
      •6•19•1•0•Updated Sep 30, 2025Sep 30, 2025

    • wikidata-emnlp23

      Public
      WikiSP, a semantic parser for Wikidata. WikiWebQuestions, a SPARQL-annotated dataset on Wikidata
      Python
      •10•102•0•0•Updated Sep 15, 2025Sep 15, 2025

    • datatalk

      Public
      Agentic system for real-world SQL databases
      Python
      •5•14•1•0•Updated Sep 1, 2025Sep 1, 2025

    • chainlite

      Public archive
      LangChain + LiteLLM that works
      agentopenaigpt
      agentopenaigptmistralllmlangchainllmopsanthropiclitellm
      Python
      •
      Apache License 2.0
      •8•49•4•0•Updated Sep 1, 2025Sep 1, 2025

    • novel

      Public
      TypeScript
      •
      Apache License 2.0
      •1•2•0•0•Updated Jul 13, 2025Jul 13, 2025

    • hassio-addons

      Public
      :heavy_plus_sign: Docker add-ons for Hass.io
      Shell
      •
      Apache License 2.0
      •1.9k•2•0•3•Updated Mar 21, 2025Mar 21, 2025

    • worksheets_assignment

      Public archive
      Python
      •1•0•0•0•Updated Oct 6, 2024Oct 6, 2024

    • almond-gnome

      Public
      The Almond Virtual Assistant, Linux desktop version
      JavaScript
      •
      Apache License 2.0
      •11•96•22•15•Updated Apr 14, 2024Apr 14, 2024

    • genie-server

      Public
      The home server version of Almond
      nlpraspberrypivoice
      nlpraspberrypivoicehacktoberfest
      JavaScript
      •
      Apache License 2.0
      •43•274•25•22•Updated Apr 14, 2024Apr 14, 2024

    • pyGenieScript

      Public
      A packaged GenieScript in Python
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •1•6•2•0•Updated Apr 7, 2024Apr 7, 2024

    • genienlp

      Public
      GenieNLP: A versatile codebase for any NLP task
      nlpnatural-language-processingtranslation
      nlpnatural-language-processingtranslationdeep-learningdialoguequestion-answeringseq2seqsemantic-parsingparaphrasing
      Python
      •
      Other
      •25•90•12•6•Updated Mar 16, 2024Mar 16, 2024

    • wikipedia-dip

      Public
      Parse a wikipedia dump into tiny files
      JavaScript
      •
      MIT License
      •12•0•0•0•Updated Mar 1, 2024Mar 1, 2024

    • gpt_paper_assistant

      Public
      GPT4 based personalized ArXiv paper assistant bot
      Python
      •
      Apache License 2.0
      •139•12•1•0•Updated Mar 1, 2024Mar 1, 2024

    • ovalchat

      Public
      OVALChat is a customizable Web app aimed at conducting user studies with chatbots
      reactnlpnextjs
      reactnlpnextjschatbotscrowdsourcingtailwindcss
      TypeScript
      •7•29•6•0•Updated Jan 9, 2024Jan 9, 2024

    • dialogues

      Public
      A unified versatile interface for dialogue datasets
      Python
      •
      Other
      •9•19•0•1•Updated Dec 9, 2023Dec 9, 2023

    • cs224v-fall23-hw2

      Public
      Python
      •0•0•0•0•Updated Oct 6, 2023Oct 6, 2023

    • genie_open_text

      Public
      Python
      •1•3•0•0•Updated Oct 5, 2023Oct 5, 2023

    • wwq

      Public
      0•0•0•0•Updated Aug 16, 2023Aug 16, 2023
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.