AI-Powered Standard Operating Procedure Generation and Optimization Using Large Language Models and Chroma Databases in Chemistry

AI-Powered Standard Operating Procedure Generation and Optimization Using Large Language Models and Chroma Databases in Chemistry | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article AI-Powered Standard Operating Procedure Generation and Optimization Using Large Language Models and Chroma Databases in Chemistry Roxane Elias Mallouhy, Hissah AlQahtani, Shaikhah Laradhi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6699075/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Creating clear and accurate standard operating procedures is essential for safety and consistency in chemistry laboratories and industrial settings. These documents guide users through equipment handling, experimental steps, and safety protocols, but are often time-consuming to produce and update. In this article, we describe a system that uses recent advances in artificial intelligence to assist in generating these procedures. The system retrieves relevant information from a curated database of chemical manuals, regulatory guidelines, and scientific texts, and uses it to generate customized documents based on user input. Users can select which sections to include, such as calibration methods or waste disposal steps, ensuring the output aligns with specific needs. Designed to minimize errors common in automated text generation, the system helps maintain accuracy and relevance. This approach simplifies documentation tasks in chemistry while supporting compliance and safety, offering a practical tool for researchers and professionals in laboratory. Physical sciences/Chemistry/Chemical safety Physical sciences/Chemistry/Process chemistry Standard Operating Procedure (SOP) Generative AI Retrieval-Augmented Generation (RAG) Large Language Models (LLMs) Chroma Database AI-driven Laboratory Safety Regulatory Compliance Chemistry Workflows Full Text Additional Declarations There is NO Competing Interest. Supplementary Files UpdatedMLreportingsummaryFilled.pdf ML reporting summary Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6699075","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":469829126,"identity":"8c132465-ceba-4151-830b-ed2e5f5f9caf","order_by":0,"name":"Roxane Elias Mallouhy","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYLCCBwUMDAYMzAdAbMYGorQkGIC0sCWQrIXHgDgt5g3ciR8SDGwSt0vkfJPmYbCR3XCA/eEHfFpkDvBulkgwSEvcOSN3G1BLmvGGAzzGEvi0SDDwbgBqOZy44QZYC5BxgIeBkJbNPyBacp4BtfwHamF//IOAlm1QW3LYgFoOALUwmBGyZZsF0C/GG848M7acY5BsPPMwj5kFIYfd+FABDKjjyQ9vvKmwk+073v74Bj4tDPIPoAyBBBYJBlDUMONVjwz4DzDjjY5RMApGwSgYuQAAMq1KTfOxQYcAAAAASUVORK5CYII=","orcid":"","institution":"Al Yamamah University","correspondingAuthor":true,"prefix":"","firstName":"Roxane","middleName":"Elias","lastName":"Mallouhy","suffix":""},{"id":469829127,"identity":"7ace5f52-5238-4d08-8990-0e1894c3e175","order_by":1,"name":"Hissah AlQahtani","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Hissah","middleName":"","lastName":"AlQahtani","suffix":""},{"id":469829128,"identity":"7a4edf12-975a-46d1-99db-0e74fb195014","order_by":2,"name":"Shaikhah Laradhi","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Shaikhah","middleName":"","lastName":"Laradhi","suffix":""}],"badges":[],"createdAt":"2025-05-19 12:40:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6699075/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6699075/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87172132,"identity":"7f7110d7-5bb2-49b3-85e0-c084710b3c63","added_by":"auto","created_at":"2025-07-21 07:39:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":384942,"visible":true,"origin":"","legend":"Article File","description":"","filename":"UpdatedCommunicationChemistryAutomatedStandardOperatingProcedureGenerationandOptimizationUsingAIPoweredLanguageModelsandChromaDatabases3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6699075/v1_covered_445b0f5a-1b3d-45b2-a0ad-c8f355473295.pdf"},{"id":84532951,"identity":"929269b4-f652-4829-84af-e9d2e65ac871","added_by":"auto","created_at":"2025-06-13 06:30:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":261218,"visible":true,"origin":"","legend":"\u003cp\u003eML reporting summary\u003c/p\u003e","description":"","filename":"UpdatedMLreportingsummaryFilled.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6699075/v1/b6b2aa3123d848bd16809614.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"AI-Powered Standard Operating Procedure Generation and Optimization Using Large Language Models and Chroma Databases in Chemistry","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Standard Operating Procedure (SOP), Generative AI, Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), Chroma Database, AI-driven, Laboratory Safety, Regulatory Compliance, Chemistry Workflows","lastPublishedDoi":"10.21203/rs.3.rs-6699075/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6699075/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Creating clear and accurate standard operating procedures is essential for safety and consistency in chemistry laboratories and industrial settings. These documents guide users through equipment handling, experimental steps, and safety protocols, but are often time-consuming to produce and update. In this article, we describe a system that uses recent advances in artificial intelligence to assist in generating these procedures. The system retrieves relevant information from a curated database of chemical manuals, regulatory guidelines, and scientific texts, and uses it to generate customized documents based on user input. Users can select which sections to include, such as calibration methods or waste disposal steps, ensuring the output aligns with specific needs. Designed to minimize errors common in automated text generation, the system helps maintain accuracy and relevance. This approach simplifies documentation tasks in chemistry while supporting compliance and safety, offering a practical tool for researchers and professionals in laboratory.","manuscriptTitle":"AI-Powered Standard Operating Procedure Generation and Optimization Using Large Language Models and Chroma Databases in Chemistry","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-13 06:30:19","doi":"10.21203/rs.3.rs-6699075/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"fd8f9413-389c-4db2-99c4-860f94f91b24","owner":[],"postedDate":"June 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":49889044,"name":"Physical sciences/Chemistry/Chemical safety"},{"id":49889045,"name":"Physical sciences/Chemistry/Process chemistry"}],"tags":[],"updatedAt":"2025-07-21T07:31:17+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-13 06:30:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6699075","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6699075","identity":"rs-6699075","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}