PDF and Knowledge: Manual Splitter to Collection Template

Run this template by hand against a long, multi-section PDF manual: Spojit splits it into chapters and embeds each one into a searchable knowledge collection.

What It Builds

A Manual trigger lets you launch the run on demand and hand it a large PDF. The pdf connector splits the document into its sections, a Loop node walks each section, and a Knowledge node in Embed mode writes every chapter into a persistent collection. Once the run finishes, readers can query individual chapters of the manual instead of scrolling the whole file.

The Prompt

Paste this into Miraxa and it builds the workflow, connecting the tools for you:

Build a workflow I start manually with a large multi-section PDF manual. Split the PDF into its sections, then loop over each section and embed it into a persistent knowledge collection called "product-manual" so readers can later query individual chapters by name.

Connectors Used

Manual trigger - you start the run and supply the PDF file.
pdf - splits the manual into per-section documents.
Knowledge (Embed mode) - writes each section into a persistent, reusable collection.

Customize It

Change the collection name in the prompt to keep manuals separate, or ask Miraxa to split by page range instead of section headings. You can also tell it to tag each chapter with the manual title so a later Knowledge Query node can filter results by source.

Tips

Use a persistent collection (not Transient) so the embedded chapters survive after the run and stay queryable.
Scanned manuals work too: the Knowledge node runs OCR on image-based pages before embedding.
Re-running with the same collection name appends new chapters, so version your collection name when the manual changes.