Back to directory

typeagent

An experimental Python translation of Microsoft's TypeAgent KnowPro project, aimed at structured retrieval-augmented generation: ingesting, indexing and querying data through an LLM.

typeagent

typeagent is an experimental, in-progress Python package that ports TypeAgent KnowPro and related packages from TypeScript, working toward a shared understanding of what a minimum viable structured RAG system looks like. The project is explicitly described by its authors as sample code rather than a finished library.

It installs with pip, and its documentation, including slides and a recorded talk from a conference, lives in the project's docs directory. Because the library sends input to a third-party-hosted LLM, its authors warn against using it to index confidential information.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.