Back to directory

Resin

A language-model search engine built as a reboot of an older project, combining a vector-space search engine, a vector database, and a general-purpose key-value store.

Resin

Resin is a search engine and machine-learning project, rebooted from an earlier version of itself, that combines vector-space search, vector storage, and a key-value store meant for arbitrary byte data as well as strings. It can produce language models from strings and general models from byte arrays using its own storage primitives.

Its key-value layer stores data in pages and columns with dedicated readers and writers, supports inserting a value only if its key does not already exist or appending additional values onto an existing key as a linked list, and includes command-line tools for building and validating lexicons and comparing strings.

It is written in C#.

More in Databases

See all 294
  • SQLBraid

    clickin.github.io

    A SQL-first data-access toolkit for TypeScript that keeps ordinary SQL visible in tagged template literals, binds interpolated values safely by default, supports readable conditional SQL directives, and lets a schema validate the returned rows.

  • A SQL-style query language and toolchain for the Qdrant vector database, covering dense, sparse and hybrid search, filtering and multitenancy, with the same grammar running from a CLI, Python, Node.js, Rust, WebAssembly and an in-process edge engine.

  • Fast Knowledge

    github.com

    A self-hosted, Java-based knowledge base for small and mid-sized organizations, turning internal documents into a searchable, question-answerable and audit-exportable knowledge asset with hybrid retrieval and Docker deployment.