Latham’s Scrudato Creates OpenContracts – Open-Source Doc AI Tool

John Scrudato, the recently hired Director of Artificial Intelligence and Innovation at Latham & Watkins, has been busy in his spare time and created OpenContracts, a free to use, open-source AI system that allows you to analyze and annotate documents.

Scrudato explained that it’s genAI native, and uses LlamaIndex on both the query-side and data extraction side. It ‘allows end users to manage, process, and ask questions over contracts, corporate legal docs, and more’, he added.

And if you are wondering what LlamaIndex is, it is ‘a central interface toolkit designed to augment LLM applications with external data. The company’s toolkit offers a flexible data framework for connecting custom data sources to large language models that connect unstructured, structured, or semi-structured data sources, enabling businesses to easily build powerful end-user applications’. So there you go.  

Any road, as mentioned it’s free and here are the things it can do:

  • Manage Documents – Manage document collections (Corpuses)
  • Layout Parser – Automatically extracts layout features from PDFs
  • Automatic Vector Embeddings – generated for uploaded PDFs and extracted layout blocks
  • Pluggable microservice analyzer architecture – to let you analyze documents and automatically annotate them
  • Human Annotation Interface – to manually annotated documents, including multi-page annotations.
  • LlamaIndex Integration – Use our vector stores (powered by pgvector) and any manual or automatically annotated features to let an LLM intelligently answer questions.
  • Data Extract – ask multiple questions across hundreds of documents using complex LLM-powered querying behavior. Our sample implementation uses LlamaIndex + Marvin.
  • Custom Data Extract – Custom data extract pipelines can be used on the frontend to query documents in bulk.

And you can find out more here.

Great to see folks at law firms building products for the market. Also see for example the story before this one about CompetitionAI, built by a lawyer who is still at Clifford Chance.

P.S. if you have a project you’re working on, whether for your own firm’s use, or for the market, drop AL a line.