001     606679
005     20240519015425.0
024 7 _ |a Mayet:2024ypj
|2 INSPIRETeX
024 7 _ |a inspire:2782994
|2 inspire
024 7 _ |a arXiv:2405.01359
|2 arXiv
024 7 _ |a altmetric:163096475
|2 altmetric
037 _ _ |a PUBDB-2024-01615
041 _ _ |a English
088 _ _ |a arXiv:2405.01359
|2 arXiv
100 1 _ |a Mayet, Frank
|0 P:(DE-H253)PIP1014786
|b 0
|e Corresponding author
|u desy
245 _ _ |a GAIA: A General AI Assistant for Intelligent Accelerator Operations
260 _ _ |c 2024
336 7 _ |a Preprint
|b preprint
|m preprint
|0 PUB:(DE-HGF)25
|s 1715771359_3662736
|2 PUB:(DE-HGF)
336 7 _ |a WORKING_PAPER
|2 ORCID
336 7 _ |a Electronic Article
|0 28
|2 EndNote
336 7 _ |a preprint
|2 DRIVER
336 7 _ |a ARTICLE
|2 BibTeX
336 7 _ |a Output Types/Working Paper
|2 DataCite
520 _ _ |a Large-scale machines like particle accelerators are usually run by a team of experienced operators. In case of a particle accelerator, these operators possess suitable background knowledge on both accelerator physics and the technology comprising the machine. Due to the complexity of the machine, particular subsystems of the machine are taken care of by experts, who the operators can turn to. In this work the reasoning and action (ReAct) prompting paradigm is used to couple an open-weights large language model (LLM) with a high-level machine control system framework and other tools, e.g. the electronic logbook or machine design documentation. By doing so, a multi-expert retrieval augmented generation (RAG) system is implemented, which assists operators in knowledge retrieval tasks, interacts with the machine directly if needed, or writes high level control system scripts. This consolidation of expert knowledge and machine interaction can simplify and speed up machine operation tasks for both new and experienced human operators.
536 _ _ |a 621 - Accelerator Research and Development (POF4-621)
|0 G:(DE-HGF)POF4-621
|c POF4-621
|f POF IV
|x 0
588 _ _ |a Dataset connected to INSPIRE
693 _ _ |a SINBAD
|e Accelerator Research Experiment at SINBAD
|1 EXP:(DE-H253)SINBAD-20200101
|0 EXP:(DE-H253)ARES-20200101
|5 EXP:(DE-H253)ARES-20200101
|x 0
856 4 _ |u https://bib-pubdb1.desy.de/record/606679/files/HTML-Approval_of_scientific_publication.html
856 4 _ |u https://bib-pubdb1.desy.de/record/606679/files/PDF-Approval_of_scientific_publication.pdf
856 4 _ |u https://bib-pubdb1.desy.de/record/606679/files/2405.01359v1.pdf
|y Restricted
856 4 _ |u https://bib-pubdb1.desy.de/record/606679/files/2405.01359v1.pdf?subformat=pdfa
|x pdfa
|y Restricted
909 C O |o oai:bib-pubdb1.desy.de:606679
|p VDB
910 1 _ |a Deutsches Elektronen-Synchrotron
|0 I:(DE-588b)2008985-5
|k DESY
|b 0
|6 P:(DE-H253)PIP1014786
910 1 _ |a External Institute
|0 I:(DE-HGF)0
|k Extern
|b 0
|6 P:(DE-H253)PIP1014786
913 1 _ |a DE-HGF
|b Forschungsbereich Materie
|l Materie und Technologie
|1 G:(DE-HGF)POF4-620
|0 G:(DE-HGF)POF4-621
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-600
|4 G:(DE-HGF)POF
|v Accelerator Research and Development
|x 0
914 1 _ |y 2024
920 1 _ |0 I:(DE-H253)MPY1-20170908
|k MPY1
|l Beschleunigerphysik Fachgruppe MPY1
|x 0
980 _ _ |a preprint
980 _ _ |a VDB
980 _ _ |a I:(DE-H253)MPY1-20170908
980 _ _ |a UNRESTRICTED


LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21