Render rich interactive visuals — SVG diagrams, HTML widgets, Chart.js charts, and interactive explainers — directly inline in chat using visualize(). Use only when the user explicitly asks for a visualization, diagram, chart, graph, drawing, map, dashboard, or similar visual artifact. Do not use for ordinary markdown, code blocks, file previews, or answer formatting
Render rich interactive visuals — SVG diagrams, HTML widgets, Chart.js charts, and interactive explainers — directly inline in chat using visualize(). Use only when the user explicitly asks for a visualization, diagram, chart, graph, drawing, map, dashboard, or similar visual artifact. Do not use for ordinary markdown, code blocks, file previews, or answer formatting
Inline Visualizer
This is the handbook/tutorial on how to use the visualizer tool.
The visualizer tool can render rich interactive visuals directly inline in chat using visualize.
How to use
you called the view_skill() tool to read the tutorial/handbook about this tool.
Read the entire handbook carefully and follow the rules closely, otherwise the visualizations might end up not rendering properly or being entirely broken.
This tutorial/handbook shows you how to actually use the tool and build beautiful visualizations.
Call visualize(title="…") - YOU MUST CALL THE TOOL, otherwise the visualization you output will not be rendered in the chat.
Calling the tool, an iFrame wrapper sandbox will immediately appear inside the chat (visible only to the user). This iFrame sandbox will AUTOMATICALLY paint/render everything you output within the tags after you called the tool.
After calling the tool, start with the opening tag @@@VIZ-START on its own line
Next, after the opening tag, emit the HTML/SVG content (no , , , )
Once you are done writing the code for the visualization, immediately close with @@@VIZ-END on its own line
Done! The visualization is complete. Continue with any follow-up text to the user.
The raw markers + SVG source are auto-hidden from the chat — users see only the rendered iframe filling in live.
Example response structure:
"""
I'll visualize the attention mechanism for you.
@@@VIZ-START
@@@VIZ-END
As you can see, each query token attends to all key tokens simultaneously.
"""
Streaming rules:
Use the delimiters EXACTLY @@@VIZ-START and @@@VIZ-END — case-sensitive, on their own lines. Do NOT put the content inside ```, ~~~, or ::: fences or any codeblock or other markdown.
Do NOT wrap in HTML tags like or — only the text markers are detected.
Emit exactly ONE @@@VIZ-START … @@@VIZ-END pair per tool call. For multiple visualizations, call the tool multiple times.
Structure the content as always: first → visible content → <script> last.
Do NOT describe the HTML source in prose — users don't see it. Describe what the visualization shows.
Requires iframe Sandbox Allow Same Origin in Open WebUI Settings → Interface. If disabled, the wrapper shows a notice — and the user won't see the visualization itself, just the notice.
Any , after the full block has streamed in.
What's auto-injected
Theme CSS, SVG classes, color ramps, height reporting, sendPrompt() bridge, and openLink() bridge
Pre-styled bare-tag form elements (see below) — saves tokens on simple forms
Consider making diagrams conversational with sendPrompt() — see the "sendPrompt bridge" section further below for patterns and examples
Pre-styled form elements
These tags get theme-aware default styling when emitted without a class or inline style attribute.
Other attributes (placeholder, value, id, aria-*, min/max, etc.) are fine — they don't disable the defaults.
Adding class or style is treated as an opt-out: the default is suppressed and you can style it from scratch.
Useful for short forms or quick UIs where the design doesn't need to deviate.
Pre-styled elements included in the tool:
— themed button. Use it for actions.
— themed text input. Use it where a user types or picks a value.
— slider. Use it for "from–to" picks, intensity dials, or any continuous value where exact precision doesn't matter.
, — multi-pick / single-pick. Self-explanatory.
— multi-line text input.
<select> — dropdown. Use it when a list of choices is too long for radios.
, , — form structure. Group related inputs and label them.
— keyboard-key cap. Use it whenever you mention a shortcut, so the key visually pops as a key.
Mac: ⌘K
Windows / Linux: CtrlK
— horizontal divider. Separate sections inside a card or between groups of content.
/ — collapsible disclosure. Use it for progressive disclosure: hide secondary detail behind a clickable summary so the surface stays clean.
— pull-quote / callout. Use it to set apart a quote, an aside, or a piece of context the reader should pause on.
(with / /
/
/
) — tabular data with multiple columns and rows. Use it when the relationship between rows and columns matters. For numeric columns add align="right" or class="num" to the cells (right-aligns + tabular-nums).
— highlighter. Use it sparingly to draw attention to a key word or number inside a sentence.
/
/
— definition lists. **Far cheaper than tables for label/value layouts**. Three modes:
- Bare
→ **stacked glossary**. Best when each term needs a sentence or two: definitions, FAQs, term-explained-below.
-
→ **two-column card**. The lightweight alternative to a table when you have key/value pairs and don't need row separators or hover: contact cards, metadata blocks, summary panels, settings rows.
-
→ **pill row** of label: value pairs (wrap each
/
in a
). Best for a tight strip of facts at the top of a card or near a chart: small numbers, status flags, tags. Colon separator is added automatically via CSS.
Bonus on bare elements:
aria-invalid="true" paints a danger-colored border on input/textarea/select
:focus-visible keyboard focus draws a clear --accent outline (mouse focus stays subtle)
Accent color palette
The default accent is purple. Switch to one of the other ramps via the data-accent attribute.
The chosen color drives --accent and --accent-foreground, which in turn power focus rings, checkbox/radio fills, and any var(--accent) reference you write yourself.
The same nine names match the chart color ramps, so a teal-accented form sits naturally next to a teal-accented chart.
Available values: purple (default), teal, coral, pink, gray, blue, green, amber, red
To apply an accent color globally to the whole visualization: wrap the entire content in a single root
.
Every supported element inside inherits the chosen accent.
/* CSS */
…all focus rings, checkboxes, and var(--accent) consumers go teal…
To apply an accent color to a specific section: set data-accent on any inner container to recolor just its subtree:
Save
Cancel
To apply an accent color to a single element: set directly on an element to recolor just it:
Approve
Reject
Both light and dark themes are handled — accent values track per-theme ramp stops automatically, and foreground text color flips for legibility in dark mode.
No manual override needed.
Pick an accent that matches the topic: green for finance/positive, red for warnings/critical actions, blue for informational dashboards, amber for attention/caution, etc.
Default to purple for neutral or multi-purpose visualizations.
Output rules
These rules keep visuals clean, accessible, and consistent with the host UI:
Flat design — no gradients, drop shadows, blur, glow, or noise textures (the host UI is flat; matching it prevents visual jarring)
Prefer no emojis, instead use CSS shapes or SVG paths for icons (emoji render inconsistently across platforms)
Sentence case — all labels and headings
Round displayed numbers — use Math.round, toLocaleString, or Intl.NumberFormat
Min font size 11px — smaller becomes unreadable on most screens
Text weights — 400 regular, 500 for emphasis only
Keep long-form explanation in the prose response. Use concise labels, captions, legends, helper text, and short annotations inside the visual when they improve comprehension.
Build ambitiously when the topic supports it. Treat each visualization like a small product surface, not a single static graphic. Combine multiple elements: a chart paired with a metric strip, a diagram with collapsible deep-dives, a comparison card with sliders that let the user explore tradeoffs. Use animation, hover, and click interactions where they help the reader notice or explore something — not for decoration. If the user asked for "a chart" and the topic naturally extends into a small dashboard, build the dashboard. Restraint is for cases where extra structure would distract; default to richness, not minimalism.
Design system
CSS variables (auto-injected — prefer these so light/dark mode just works)
The tool injects theme-aware CSS variables that adapt to light/dark mode automatically. Use them by default for text, surface, and border colors; reach for a specific hex only when the design genuinely calls for a fixed color (a brand mark, a deliberate accent that shouldn't track the theme).
Token
Purpose
--color-text-primary
Main text
--color-text-secondary
Labels, muted text
--color-text-tertiary
Hints, placeholders
--color-text-info/success/warning/danger
Semantic text
--color-bg-primary
Main background
--color-bg-secondary
Cards, surfaces
--color-bg-tertiary
Page background
--color-border-tertiary
Default borders (0.15 alpha)
--color-border-secondary
Hover borders (0.3 alpha)
--font-sans
Default font
--font-mono
Code font
--radius-md / --radius-lg / --radius-xl
8px / 12px / 16px
Color ramps (9 ramps, auto light/dark)
Each ramp provides fill, stroke, and text variants that adapt to the theme automatically via CSS classes.
Ramp
50 (light fill)
200
400
600 (light stroke)
800 (light title)
purple
#EEEDFE
#AFA9EC
#7F77DD
#534AB7
#3C3489
teal
#E1F5EE
#5DCAA5
#1D9E75
#0F6E56
#085041
coral
#FAECE7
#F0997B
#D85A30
#993C1D
#712B13
pink
#FBEAF0
#ED93B1
#D4537E
#993556
#72243E
gray
#F1EFE8
#B4B2A9
#888780
#5F5E5A
#444441
blue
#E6F1FB
#85B7EB
#378ADD
#185FA5
#0C447C
green
#EAF3DE
#97C459
#639922
#3B6D11
#27500A
amber
#FAEEDA
#EF9F27
#BA7517
#854F0B
#633806
red
#FCEBEB
#F09595
#E24B4A
#A32D2D
#791F1F
Chart dataset colors (use 400 stops)
Series
Color
Hex
1
teal-400
#1D9E75
2
purple-400
#7F77DD
3
coral-400
#D85A30
4
blue-400
#378ADD
5
amber-400
#BA7517
For area/line fills, use same color at 20% opacity.
SVG setup
If you want to build a beautiful SVG to be rendered inside the chat, follow these rules too:
Always use this SVG boilerplate:
viewBox width always 680 — set H to tightly fit content (last element bottom + 40px). Never oversize — calculate the actual bottom of your last SVG element and add 40px. An SVG with content ending at y=180 must use H=220, not 500
Safe area: x=40 to x=640
Background transparent — host provides container
SVG classes (auto-injected)
Drop these on SVG elements instead of writing inline fill, stroke, or
font-size. They track the theme automatically.
Class
What it is
When to use
.t
14px primary-color text
Default for any visible label inside a node, axis tick, or callout.
.ts
12px secondary-color text
Subtitles, captions, units (e.g. "users", "ms"), supporting text under a .t label.
.th
14px primary text, 500 weight
Node titles, KPI numbers, anything that needs to read as "the headline" of a small region.
.box
Neutral rect — secondary bg, tertiary border
Default container for a labeled region. Use whenever you need a neutral chip / panel and don't have a semantic color.
.node
Cursor-pointer + hover opacity on a
Mark a as clickable. Pair with onclick="sendPrompt(...)" so a user can drill into the topic.
.arr
1.5px stroke matching theme borders
Arrow lines and connectors. Combine with marker-end="url(#arrow)".
.leader
0.5px dashed guide line
Pulling a label to a part of an illustration when the label can't sit on top of it.
.c-{ramp}
Sets fill/stroke + text colors on a whole from one of the 9 color ramps
Color a node by category — apply .c-teal (etc.) to a and every shape and text inside picks up the matching ramp. Un-classed, un-filled / children (pie wedges, areas) take the ramp's series color; on a classed or filled mark, fill="currentColor" opts back in.
Sizing text inside boxes
Browsers don't auto-size SVG boxes to text. To pick a width, estimate
the rendered glyph width per character and size the box from the
longest line.
defaults to dominant-baseline="alphabetic" — y is the text's
baseline, not its center, so a label placed at the vertical midpoint of
a box actually sits ~4 px too high. For text inside a node, callout, or
any rounded rect, add dominant-baseline="central" and put y at the
box midpoint.
Keep the default (no dominant-baseline) for text that's meant to sit
on a baseline: axis tick labels (resting on the axis line), legend labels
(aligned to the swatch baseline), and anything where the bottom edge of
the glyphs is the visual anchor. Setting central on those will make
them look ~4 px low instead.
Diagram types
Flowchart — sequential steps, decisions
Max 4–5 nodes per diagram — 6+ → decompose into overview + sub-flows
Box spacing: 60px between boxes, 24px padding inside
Single-line node: height 44px, two-line: 56px
Arrows must not cross any box — use L-bends if needed
Use marker-end="url(#arrow)" on arrow paths
Single-line node:
Label
Two-line node:
Title
Subtitle
Architecture — nested regions, layered systems
For diagrams that show what contains what: services inside zones,
modules inside layers, components inside subsystems. The nesting itself
is the information — outer regions are the system, inner regions are
the parts.
Outermost container: rx=20–24, lightest ramp fill (the 50 stop), 0.5px stroke
Inner regions: rx=8–12, a darker stop of the same ramp — or a different ramp when the inner region is semantically distinct (e.g. external service inside an internal cluster)
20px minimum padding between an inner region's bounds and its parent's edge
Max 2–3 nesting levels — beyond that, decompose into a top-level overview plus sub-diagrams
Illustrative — explain a mechanism by drawing it
For "how does this actually work" topics where the answer is spatial:
how light refracts through a prism, how a transformer attention head
weighs tokens, how a heat pump moves heat against a gradient. Draw
the thing itself, not a labeled diagram about it.
Shapes are freeform — paths, ellipses, polygons, curves — not just rounded rects
Color encodes intensity or state, not category: warm ramps for active / hot / energized, cool ramps for calm / cold / passive, gray for neutral / inert
Labels live outside the object connected via .leader lines — reserve a ~140px gutter on the side you'll label from
Strongly prefer interactive illustrative diagrams: if the real system has a knob, a slider, or a phase, expose it. A prism with a draggable angle slider teaches refraction better than five static frames.
Charts (Chart.js)
Load Chart.js in your HTML fragment:
Setup pattern:
Chart rules:
Wrap canvas in container with position: relative and explicit height — without it, maintainAspectRatio: false collapses the canvas to zero
Always pass responsive: true, maintainAspectRatio: false in options — without maintainAspectRatio: false, Chart.js locks the canvas to a 2:1 aspect and ignores the container height; without responsive: true, it won't redraw when the iframe re-measures. You have to set them explicitly on every new Chart(...) call (Chart.js reads options at construction time, so there's no global default we could pre-set for you).
Read CSS variables for text/border colors so the chart tracks the theme
borderRadius: 4 on bars
Line charts: tension: 0.3 for smooth curves
Doughnut: cutout: '60%' — never use pie
Chart type selection:
Data shape
Type
Notes
Categories + values (a few items, comparable magnitudes)
Bar
Default for "compare values across labels". Switch to a horizontal bar (indexAxis: 'y') when labels are long, when there are 8+ categories, or when ranking is the point.
Time series, anything sampled at regular intervals
Line
tension: 0.3 for a natural curve. Stack multiple datasets when you're comparing trends, not when each line wanders independently — overlap gets unreadable past 4 lines.
Parts of a whole, ≤5 slices
Doughnut
Use cutout: '60%' so the empty middle can hold a total or label. Skip if the segments are very uneven (one slice >70%) — the small slices vanish; show a stacked bar instead.
Two continuous variables, looking for correlation
Scatter
Add a trend line if the relationship is the takeaway. For dense clouds, drop point opacity to 0.3–0.5 so density reads.
Stacked / cumulative composition over time
Stacked bar / stacked area
Bar when the buckets are discrete (months, segments); area when the underlying signal is continuous.
Single-value vs target / threshold
Bar with reference line or KPI card
A whole chart is overkill for one number — consider a metric card with a sparkline instead.
Multi-dimensional comparison (3–6 axes)
Radar
Only when the axes are genuinely commensurate — otherwise a small-multiples bar grid is clearer.
Inline SVG charts (no library)
Reach for inline SVG when the data is small, the shape is simple, or
you want the chart to share design with surrounding diagrams (matching
corner radii, palette, type). No script, no CDN — just shapes and text.
Reach for Chart.js when you need axes, tooltips, hover, animation, or
many series.
Good fits for inline SVG:
Progress / completion bar — a value rendered against a fixed track, often paired with a percentage label to its right
Ranking strip — a small number of horizontal bars stacked vertically, each bar a different category color, sized by value
Sparkline — a terse trend line with no axes that sits next to a number to give the number context
KPI donut / ring — a single percentage rendered as a circle arc, with the number in the middle of the ring
Stacked composition row — one horizontal bar split into colored segments to show parts of a whole, when a doughnut would feel heavy
Custom-shape charts — anything where the chart shape is part of the metaphor (a thermometer for temperature, a battery for charge, a fuel gauge, a tide-line)
Theme consistency for inline SVG:
Use the .t / .ts / .th classes on for labels, captions, and headlines.
They pick up the theme's text colors and typography scale automatically.
Never set font-size or fill on label text manually unless you need a specific deviation.
For neutral backgrounds (track behind a progress bar, empty slot in a ring), use fill="var(--color-bg-secondary)" so it blends into the surrounding card.
For data colors, prefer the chart-dataset 400-stop hexes from the table above — they're calibrated to read on both light and dark backgrounds.
If you need a whole group recolored (rect + label + stroke together), wrap it in a (or any of the 9 ramp classes) and let the SVG class system handle fill + stroke + text in one shot.
Keep stroke-widths to 0.5 px for chrome (axis lines, grid) and 1.5 px for data (lines, sparklines) — matches the 0.5 px borders the rest of the host UI uses, so the chart doesn't feel chunkier than its neighbors.
Add opacity="0.85" on data fills — softens the color slightly so it sits comfortably next to text without overwhelming it.
Math hints for the less obvious shapes:
Donut arc length: circumference = 2 × π × r. To draw v% of the ring, set stroke-dasharray="{v×circumference/100} {circumference}" on the foreground circle, and transform="rotate(-90 cx cy)" so the arc starts at 12 o'clock instead of 3 o'clock.
Bar widths in a viewBox="0 0 680 …": leave 40 px of margin on each side, giving a 600 px usable plot width.
Component patterns
Metric cards — KPI strip
Revenue
$3,870
▲ 12.4%
Pair with a chart below for a compact dashboard. Add a tiny inline-SVG
sparkline under each value if the trend matters.
Comparison layout — two paths side by side
Monolith
Deploy unit
1 service
Latency
Low (in-process)
Scaling
Vertical
Microservices
Deploy unit
N services
Latency
Higher (network)
Scaling
Horizontal per service
Interactive explainer — slider drives output
Interest5.0%
The pattern generalises: every interactive element binds an input listener, recomputes a value, and writes it to a result node.
Pair with an inline SVG that re-draws on every input change for a "live diagram".
Persist the active tab with saveState/loadState so it survives reloads.
Charts in inactive tabs render at 0×0. Plotly, ECharts, and vis-network all measure their container at init time.
If that container is inside a hidden / display:none panel, they paint into a zero-size canvas and stay blank even after the tab becomes visible.
Two workarounds, pick one:
Lazy-init: only call Plotly.newPlot / echarts.init / new vis.Network the first time its tab is shown (track a tabInit[id] flag in the handler).
Resize on show: init everything up front (so data is ready), then in showTab call the right resize hook for whichever lib is in that tab.
Note the API differs per library — c.resize() does not work for all of them:
// ECharts: instance.resize()
echartsInstance.resize();
// Plotly: pass the container element, no .resize() on the chart
Plotly.Plots.resize(document.getElementById('plotly-container'));
// vis-network: redraw + fit — the instance has no .resize()
networkInstance.redraw();
networkInstance.fit();
// Chart.js: instance.resize() — but Chart.js auto-resizes on
// container size change so usually nothing needed.
Skip the resize call for D3 / Vega-Lite / inline SVG — they paint declaratively into the SVG namespace and aren't bothered by hidden parents.
Step-through walkthrough — guided narrative
A "Next ▶" button advances through a sequence of stages, each with its own caption and (optionally) a different highlighted region of the same diagram.
Useful for explaining algorithms, processes, or any topic where the order matters more than the totals.
Click Next to begin.
Next ▶
sendPrompt bridge — conversational diagrams
sendPrompt(text) is the function that makes visualizations conversational. When called, it injects the given text into the chat input field and submits it — exactly as if the user had typed and sent it themselves. The model then receives that message and responds normally, creating a feedback loop between the visual and the conversation.
This is what separates a static diagram from an exploration interface. A user sees a system architecture diagram, clicks on the "Load Balancer" node, and the model receives "Tell me more about the load balancer — how does it distribute traffic across the backend services?" as a user message. The model then responds with details, and could even generate a new sub-diagram showing the load balancer internals. The user never had to type anything — they just clicked.
Why this matters
Without sendPrompt, interactive elements inside the iframe are isolated — they can toggle visibility, animate, or filter data, but they can never talk back to the model. The user sees a cool diagram but has to manually type follow-up questions. With sendPrompt, every clickable element becomes a conversation starter. The diagram itself becomes a navigation interface for the topic.
Writing good sendPrompt text
The text you pass to sendPrompt becomes the user's message to the model. Write it as a natural follow-up question — conversational, specific, and referencing the context of the diagram:
Good prompt text (specific, contextual, references the diagram):
"Explain the attention mechanism — how does it decide which tokens to focus on?"
"Break down the CI/CD pipeline stage. What tools are typically used here?"
"Show me a more detailed diagram of the data processing layer"
"What happens when the load balancer detects a failed backend node?"
"Compare the pros and cons of the monolith vs microservices approach shown here"
Usage patterns
Simple patterns — single-click sendPrompt on a node or button:
Drill-down: onclick="sendPrompt('Explain the API gateway — what does it handle?')" on a diagram node
Quiz answer: onclick="sendPrompt('I chose B: O(n log n). Am I right? Explain why.')" on answer buttons
Guided exploration: onclick="sendPrompt('Show me a more advanced example with edge cases.')" on a "Go deeper →" button
Comparison: onclick="sendPrompt('Compare REST vs GraphQL — when should I use each?')" on one of two nodes
Form / preference collector — gather multiple user selections, then send them all at once. Use local JS to track choices (button highlights, state object) and a submit button that composes a sendPrompt from the collected answers:
What's your style?
Pace
Relaxed
Moderate
Intensive
Focus
Culture
Nature
Food
Get my recommendation →
This pattern is powerful because the model receives a structured summary of all user preferences in one message. Use local JS for the selection UI (instant feedback), then sendPrompt only on final submit.
When to use sendPrompt vs local JS:
User action
Use
Why
Learn more about a component
sendPrompt
Model gives a contextual explanation
Explore a stage / drill down
sendPrompt
Model can generate a sub-diagram
Submit answers or preferences
sendPrompt
Model evaluates or personalizes
Toggle views, adjust sliders
Local JS
Instant feedback, no reasoning needed
Filter/sort data
Local JS
Instant response, no model needed
Interactivity by default
Build dashboards, charts, graphs, interactive functions, animated sections, moving objects, expandable detail sections, cards, copyable text elements and more. If the topic allows and it makes sense for the topic, build complex and visually stunning elements.
Visualizations should feel alive and polished — not static images dumped into chat. Build interfaces that invite interaction:
Expandable sections — use collapsible elements or JS-toggled sections so users can explore at their own pace without overwhelming them upfront
Hover effects — nodes, buttons, and cards should respond to hover (the .node class adds this for SVG elements; for HTML, use :hover styles)
Smooth transitions — add transition: all 0.2s ease to interactive elements for a polished feel
Active states — when a user selects an option or clicks a tab, make the selection visually clear with the .active class or distinct styling
Progressive disclosure — show a clean overview first, let the user click to reveal detail (tabs, accordions, or sendPrompt for model-powered drill-down)
The goal is to build something that feels like a real app component embedded in chat with reactivity, sections and extra elements — not a screenshot. If the visualization has multiple facets, give the user controls to explore them. If it has hierarchical information, let them expand and collapse. If it has data, let them sort or filter.
openLink bridge — opening URLs from visualizations
Declarative grammar of graphics — feed it a JSON spec, it draws the chart
ECharts
Rich interactive dashboards, advanced chart types
Plotly
Scientific / 3D plots, statistical charts
vis-network
Force-directed network / node-link graphs
(the standalone UMD bundle — exposes vis.Network and vis.DataSet. The bare vis-network.min.js on cdnjs is the peer build and requires vis-data loaded separately, otherwise new vis.DataSet(...) throws vis is not defined.)
Tone.js / Wavesurfer
Audio synthesis, waveform visualisation
Anything else on those three CDNs is fair game — apexcharts, d3-force,
konva, flatpickr, etc. Pick whatever fits the topic.
Library init
Two patterns to follow when using a CDN library:
1 · Wrap a Chart.js canvas in a fixed-height container
maintainAspectRatio: false makes Chart.js use the container's height.
If the canvas has no intrinsic height (e.g. inside a flex column without a height set), it collapses to zero and nothing draws:
2 · Source order matters
Put external the inline
<script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.min.js">
