🌿 DocViz
← Login
01 / 12
Knowledge cartography for text

See the whole picture
of any document.

DocViz turns any text — a paper, a report, a blog post — into an interactive map of its structure, meaning, and connections. Stop reading linearly. Start seeing.

Local-LLM powered Lossless & granular 7 visual lenses Autonomous cloud worker
The problem

Reading is linear.
Understanding is structural.

A document is a graph wearing the disguise of a straight line. Its real shape — which claims support which, where the evidence lives, how concepts interlock — is invisible when you read top to bottom.

🐌Slow ingest

A 30-page paper costs an hour just to learn whether it's relevant. Most of that hour is navigation, not insight.

🌫️Hidden structure

Arguments, citations and key concepts are buried in prose. You can't see the skeleton until you've read the skin.

🧩No comparison

Twenty documents become twenty silos. There's no shared map to see how a whole field — or your whole inbox — fits together.

The core idea

Every document
is already a network.

Sections contain paragraphs. Paragraphs contain statements. Statements cite references and share concepts with one another. That hierarchy plus those cross-links is a graph.

DocViz extracts it losslessly — every statement preserved, nothing summarized away — then lets you fly through it at any altitude.

Document § Section § Section statements · concepts · refs
How it works

A four-stage granular pipeline

The same lossless logic runs locally or on the cloud worker — only the LLM's location changes.

1
✂️

Parse

Split into sections, paragraphs, statements & references — verbatim.

2
🤖

Enrich

An LLM annotates each unit: one-liner, summary, key points, concepts, salience.

3
🔧

Graph

Assemble the hierarchy plus citation & concept cross-links into one network.

4
🗺️

Concept map

Surface co-occurring concepts, weighted by how often they bind paragraphs.

100%
statements preserved
0
cloud LLM cost — runs on Ollama
911
nodes from one 30-page paper
Multi-resolution

Zoom from skim to deep read

One control changes the altitude. Start with the shape of the argument; descend to the exact sentence and its sources.

§ LEVEL 1

Sections

The table of contents as a living map. The 10-second overview.

¶ LEVEL 2

Paragraphs

Each idea as a node, labelled by its own first sentence.

≣ LEVEL 3

Statements

Every claim, sized by salience. The lossless core.

⁂ LEVEL 4

References

Citations as diamonds, linked to the claims that lean on them.

Plus a per-node detail slider: Skim → Summary → Analysis → Reference. Read as shallow or as deep as the moment needs.

One document, seven lenses

Because how you look changes what you see

🕸️

Force Graph

The full living network

Sunburst

Proportions at a glance

Node Tree

Strict hierarchy

Mind Map

Radial brainstorm

🗺️

Concept Map

Ideas, not structure

📄

Text Reader

Lossless, searchable

▮▮

Linear

Guided section-by-section

Yours next

The model is open

Architecture

Upload anywhere. Analyze 24/7.

An installable web app talks to Firebase; an autonomous worker on a GPU server does the thinking. Your laptop can be closed.

📲PWA Client

Installable, offline-capable. Drop a file, organize into folders, watch live progress. Network-first so every deploy lands instantly.

🔥Firebase

Auth, Firestore job queue & metadata, Storage for graph payloads. The rendezvous point — client and worker never talk directly.

⚙️AI Worker

A systemd service on the server polls for jobs, runs the pipeline on local Ollama, self-heals crashed jobs, and writes results back.

status: stored → analyzing → done live progress via Firestore snapshots ↺ re-analyze on demand
Where this goes next

From visualizing one document
to understanding all of them.

Today DocViz maps a document's content. Next, it reads a document's character — what kind of text it is, how good it is, and how it relates to everything else you've ever fed it.

① Classify the type ② Grade the quality ③ See the whole landscape
Future ① — Document DNA

Detect the type, then adapt the lens

An academic paper, a blog post and a legal contract are not read the same way. DocViz will auto-classify genre, then apply the analysis & scoring lens that fits. Tap a type:

Academic Paper
Future ② — Evaluation engine

Turn prose into
measurable signal

Every node already carries structure. Layer scoring on top and a document becomes a profile — strengths, gaps and risks you can see in one shape, compare, and track over revisions.

🔬Rigor & evidence density
💡Novelty & insight
🔗Citation health
✍️Clarity & readability
⚖️Bias & balance
🧱Structural soundness
A document's quality fingerprint —
at a glance, comparable, trackable.
Future ③ — The whole picture

Not one map. A map of maps.

When every document becomes a graph in the same space, your whole corpus becomes navigable. Concepts bridge papers; types cluster; quality colours the terrain.

🌐Cross-doc concepts

One shared concept graph spanning your library. Find every claim about a topic, across every source, instantly.

⚖️Compare & contrast

Two papers side by side: where they agree, conflict, and cite the same evidence. Literature review as a diff.

🧭Field cartography

Drop 200 papers in; get the terrain of a field — its hubs, its frontiers, its gaps worth filling.

The pitch: a fast-understanding layer for all text-based documents — read less, see more, decide faster.

The vision

Stop reading documents.
Start seeing knowledge.

DocViz began as a way to map a single paper. It's becoming an instrument for understanding text itself — its structure, its type, its quality, and its place in the bigger picture.

Understand at a glance Evaluate objectively See the whole picture
🌿 DocViz · powered by local LLMs · built to make text legible
Navigate with · F fullscreen