Enhancing automatic context-driven image description for Retrieval-Augmented Generation (RAG) pipelines in the manufacturing industry.

Research unit

INNOSUISSE

Project number

132.030 INNO-ICT

Project title

Enhancing automatic context-driven image description for Retrieval-Augmented Generation (RAG) pipelines in the manufacturing industry.

Texts for this project

	German	French	Italian	English
Key words	-	-	-
Abstract	-	-	-

Category	Text
Key words (English)	ICT, Artificial/local/extended/networked intelligence
Abstract (English)	The project focuses on enhancing RAG pipelines in manufacturing by improving multi-modal capabilities. Specifically, generating context-aware image descriptions from technical documents with textual design requirements, screenshots/UIs, diagrams, and technical drawings.