Skip to content
FlowHub
FluxonLab
Document AI & Extractionfree

Segment PDFs by Table of Contents with Gemini AI

by Lukas KunhardtUpdated Aug 2026
RequiresGoogle GeminiGoogle DriveGoogle Drive
Share Post Share
MaWhen clicking ‘Execute workflow’When clicking ‘…SwStatus is:Google Gemini Chat ModelGoogle Gemini C…OPStructured Output ParserStructured Outp…OPAuto-fixing Output ParserAuto-fixing Out…SeSet File NameEWWhen Executed by Another WorkflowWhen Executed b…CoExtract Sections headers as fallbackExtract Section…CoTake beginning of Document to look for Table of contentsTake beginning …SAStop and ErrorGoogle Gemini Chat Model1Google Gemini C…EFConvert the PDF to base64Convert the PDF…HRDownload PDF from URLDownload PDF fr…Download PDF from Google DriveDownload PDF fr…WaWait Before Polling the Chunkr ResultWait Before Pol…CoReturn each section individuallyReturn each sec…AgTable of Content AgentTable of Conten…CoReturn the whole documentReturn the whol…CoCreate HTML documentCreate HTML doc…HtHTMLMBMove Binary DataCoCreate Markdown DocumentCreate Markdown…CTConvert to FileHRGET Chunkr TaskHRPOST Chunkr TaskMeMerge1234567891011121314151617181920212223242526
1/5
STEPS · 26
Run manually by an operator

On manual trigger, extracts a PDF's table of contents with Gemini and splits it into sections saved to Google Drive.

Tags

manualadvancedGoogle GeminiGoogle DriveDocument ExtractionAI Summarizationdiscoveredpending-review
Connects
Google GeminigoogledriveGoogle Drive
CategoryDocument AI & Extraction
Triggermanual
Complexityadvanced
Nodes26
AddedJun 27, 2026