Goto

Collaborating Authors

 indication subfield


Observations on Building RAG Systems for Technical Documents

Soman, Sumit, Roychowdhury, Sujoy

arXiv.org Artificial Intelligence

Retrieval augmented generation (RAG) for technical documents creates challenges as embeddings do not often capture domain information. We review prior art for important factors affecting RAG and perform experiments to highlight best practices and potential challenges to build RAG systems for technical documents.