Skip to main content

llm_markdown 0.2.0 copy "llm_markdown: ^0.2.0" to clipboard
llm_markdown: ^0.2.0 copied to clipboard

Markdown widget for streaming LLM chat replies. Parses only new text, closes half-typed syntax, highlights code and follows the scroll.

llm_markdown #

Markdown widget for chat apps that stream replies from an LLM.

A reply streaming in: a thinking section, math, a code block and a checklist

If you render a streaming reply with a regular Markdown widget, the whole text is parsed again on every chunk. That gets slow on long answers, you see raw ** and backticks until the closing ones arrive, and code blocks flicker when they get highlighted.

This package fixes that:

  • Only the last unfinished block is parsed again. Finished blocks are built once and cached.
  • Unfinished syntax is closed before rendering, so **bold, an open code fence or a half-typed [link](https://... already looks right. Tables show up once the header row is done.
  • Text is revealed at a steady speed instead of in bursts, and it speeds up if it falls behind.
  • Code blocks have a copy button and get syntax highlighting once closed.
  • LaTeX math: $...$, \(...\), $$...$$ and \[...\]. Prices like "$5 and $10" are left alone.
  • Reasoning from <think>...</think> (DeepSeek, Qwen, ...) or from a separate reasoning stream goes into a collapsible "Thought for 12s" section.
  • The newest characters fade in as they appear.
  • Optional auto-scroll that stops when the user scrolls up to read.
  • Depends only on flutter/widgets.dart, so it works with material_ui, the old flutter/material.dart, Cupertino or no design library at all.

It doesn't talk to any model API. You give it text, it renders it.

Install #

flutter pub add llm_markdown

Usage #

With a controller:

final controller = StreamingMarkdownController();

// build()
StreamingMarkdown(controller: controller)

// when the reply comes in
await for (final chunk in model.generate(prompt)) {
  controller.append(chunk);
}
controller.complete();

controller.addStream(stream) does the loop for you. controller.text has the full markdown, e.g. for a "copy reply" button.

Straight from a stream:

StreamingMarkdown.stream(replyStream)

A stream can only be listened to once, so inside a ListView (items get disposed when they scroll away) keep a controller per message instead.

Or from text you already keep in your state:

StreamingMarkdown.text(message.text, isComplete: message.done)

If the new text starts with the old one, only the added part is processed.

Math #

Formulas are found and kept intact while they stream; drawing them is up to you, so you can pick the math package. With flutter_math_fork:

StreamingMarkdown(
  controller: controller,
  mathBuilder: (context, tex, display) => Math.tex(
    tex,
    mathStyle: display ? MathStyle.display : MathStyle.text,
  ),
)

A formula that is still arriving shows its source until it's closed. Without a mathBuilder the source is shown.

Thinking #

If the reply starts with <think>...</think>, that part goes into a section above the answer. It shows "Thinking..." while it streams and "Thought for Ns" after. For APIs that send reasoning separately:

controller.appendThinking(reasoningChunk);
controller.append(answerChunk);

showThinking: false drops it, thinkingInitiallyExpanded: true opens it, and thinkingLabel changes the title (e.g. to translate it).

Chat list #

SelectionArea(
  child: ListView(
    controller: scrollController,
    children: [
      for (final message in messages)
        StreamingMarkdown(
          controller: message.controller,
          autoScrollController: scrollController,
        ),
    ],
  ),
)

SelectionArea comes from your design library and makes the text selectable. With ListView(reverse: true) you don't need autoScrollController.

Options #

Option Default
smoothing Smoothing.adaptive() Smoothing.none() shows text right away; fadeLength: 0 turns the fade off
mathBuilder – draws LaTeX, see above
showThinking true
thinkingInitiallyExpanded false
thinkingLabel English title of the thinking section
style from context see below
onLinkTap – called with the link URL
imageBuilder Image.network
codeBlockBuilder built-in return null to fall back to the default
highlightCode true
showCursor true blinking cursor while streaming
newlinesAsBreaks false treat a single newline as a line break
autoScrollController – follow the reply while at the bottom

Styling #

The default style takes the text style from DefaultTextStyle and the accent (links, checkboxes, cursor) from DefaultSelectionStyle. Material and Cupertino apps set both from their theme. To set it yourself:

StreamingMarkdown(
  controller: controller,
  style: StreamingMarkdownStyle.fromColors(
    textStyle: theme.textTheme.bodyMedium!,
    accentColor: theme.colorScheme.primary,
  ).copyWith(blockSpacing: 16),
)

healIncompleteMarkdown() is exported too, in case you want the healing with a different renderer.

How it works #

The text is split into blocks only at points where nothing that comes later can change the block before it (a blank line before a new paragraph, the end of a heading, a closing code fence, ...). Those blocks are parsed once with markdown. The last block is healed and parsed again whenever new text arrives, at most once per frame.

The tests stream sample replies one character at a time, line by line and in random chunks, plus a few thousand generated documents, and check that every finished block matches a normal parse of the full text.

Limitations #

  • Once a footnote definition appears, the reply is parsed as a whole again (correct, just not incremental).
  • Raw HTML is shown as text.
  • Inline math has to fit on one line.

Tested on Flutter 3.35 and 3.50.

License #

MIT

2
likes
160
points
--
downloads
screenshot

Publisher

unverified uploader

Weekly Downloads

Markdown widget for streaming LLM chat replies. Parses only new text, closes half-typed syntax, highlights code and follows the scroll.

Repository (GitHub)
View/report issues

Topics

#markdown #ai #chat #streaming #llm

License

MIT (license)

Dependencies

characters, flutter, markdown, re_highlight

More

Packages that depend on llm_markdown