Observations on Building RAG Systems for Technical Documents

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 technic...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-03
Main Authors: Soman, Sumit, Roychowdhury, Sujoy
Format: Article
Language:English
Subjects:
Best practice
Documents
Technical information
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422