Győző Csóka: Rényi AI at DLM Forum Copenhagen: Semi-Agentic RAG for Archival Access

At the DLM Forum in Copenhagen, Rényi AI presented its joint work with the Historical Archives of the Hungarian State Security and the National Archives of Hungary to speed up archival processes and make historical collections more accessible and reliable.

We showcased a trustworthy, semi-agentic Retrieval-Augmented Generation (RAG) system developed on the Council of Ministers’ meeting minutes from the first Imre Nagy government.

The solution combines high-quality transcriptions with the original scans and uses a hybrid search pipeline to find the most relevant sources.

A conversational, ChatGPT-like interface lets historians and the public “chat with the documents”, while every answer comes with precise citations back to the original pages for easy verification.

We also highlighted supporting applications already running in the State Security Archives, including neural enhancement of scanned document quality, automated text extraction and summarization, and sensitive-data detection.