← toolkit.bot

Tana and PDF to EPUB — How to Build a Supertag Knowledge Graph from Your Academic Reading (2026)

Tana is a modern PKM app that combines an outliner interface with a powerful supertag system — every bullet node can be given a type with structured fields, turning your notes into queryable structured data. For researchers, this means your reading notes on academic papers can become a semantic database: filterable by author, year, methodology, or finding type.

The reading phase is better on an e-reader than in a browser. Converting your academic PDFs to EPUB lets you read comfortably on a Kindle or Kobo, build up highlights, and then bring those highlights into Tana via Readwise — where they become typed, connected knowledge nodes.

PKM Apps with Structured Data Support

AppPrimary modelStructured dataQueriesE-reader syncBest for
TanaOutliner + supertagsExcellent (typed nodes)Inline queriesVia ReadwiseSemantic knowledge graph
NotionBlocks + databasesGood (database views)Filtered viewsVia ReadwiseTeam wikis, databases
ObsidianLinked markdownPlugin (Dataview)Dataview queriesVia ReadwiseLong-term knowledge graph
LogseqOutliner + graphProperties (YAML)Limited queriesVia ReadwiseDaily notes + PKM
Roam ResearchOutliner + linksAttributes (limited)LimitedVia ReadwiseDense networked thinking
HeptabaseWhiteboard + cardsNo (visual only)NoVia ReadwiseVisual synthesis

Designing a #paper Supertag in Tana

Before starting your reading workflow, define a #paper supertag in Tana with these fields:

Every paper you add to Tana becomes a structured record with these fields populated, enabling powerful queries across your literature.

The EPUB → Tana Workflow

  1. Download the PDF from your database (arXiv, PubMed, JSTOR, institutional library).
  2. Convert to EPUB via toolkit.bot.
  3. Read on Kindle or Kobo — highlight key findings, methodology notes, and memorable quotes.
  4. Sync highlights to Readwise — Kindle highlights sync automatically; Kobo via USB or the Kobo Readwise integration.
  5. Push to Tana via Readwise — in Readwise Export settings, connect Tana and enable the sync. Highlights arrive in your Tana inbox as nodes.
  6. Tag with #paper supertag — fill in the structured fields for the paper.
  7. Connect to concepts — reference existing #concept nodes or create new ones from the highlights.
  8. Query your literature — use Tana's inline search to filter papers by methodology, year, journal, or quality rating.

Frequently Asked Questions

What is Tana and how does its supertag system work?

Tana is a modern outliner-based PKM app where every bullet point can be tagged with a 'supertag' — a user-defined type that adds structured fields to the node. For example, tagging a node as #paper adds fields for Author, Year, DOI, and Summary automatically. This turns your notes into a structured database: you can query 'all papers tagged #neuroscience published after 2020' directly in the outliner. For academic reading, this means your highlights and notes become typed, queryable data — not just raw text.

Can Tana import EPUB files or PDF annotations directly?

Tana does not have a native PDF viewer or EPUB importer. The recommended workflow is: convert PDF to EPUB → read on Kindle or Kobo → export highlights (via Readwise, which has a Tana integration) → highlights arrive in Tana as structured nodes tagged with the paper's supertag, ready for you to annotate and connect. Readwise's Tana integration is the smoothest bridge between e-reader highlights and the Tana knowledge graph.

How does Tana compare to Obsidian for academic literature management?

Tana's primary strength over Obsidian is structured data: supertags create a typed schema for your notes, so you can query and filter papers, authors, and concepts as database records. Obsidian's strength is its link graph and plugin ecosystem. For researchers who want database-style queries over their literature (e.g., 'show all papers by Author X that I've rated 5 stars'), Tana is more powerful. For long-form writing and graph visualisation, Obsidian has the edge.

What is the Readwise → Tana integration?

Readwise (readwise.io) syncs highlights from Kindle, Kobo, and other reading apps and can push them to Tana via an official integration. In Readwise's Export settings, connect your Tana account and enable the Tana sync. Highlights appear in Tana as supertag-typed nodes under a designated inbox node, ready for you to tag with additional supertags (#paper, #concept, #author) and connect to your knowledge graph.

Is Tana suitable for a systematic literature review?

Yes, especially if you define a consistent #paper supertag schema upfront (fields: Title, Author, Year, Journal, DOI, Key finding, Methodology, Quality rating). Each paper becomes a structured record. You can then create Tana views that filter and sort papers by methodology, quality, or finding type — similar to a systematic review evidence table, but built interactively as you read.

Related: Obsidian + EPUB · Heptabase + EPUB · RemNote + EPUB · PDF to EPUB for researchers