AI features

Shipped today (AskAi UI, llms.txt) and on the roadmap (client-side RAG, semantic search).

Publier treats AI as first-class infrastructure. A UI shell and machine-readable content files ship today. Client-side AI is on the roadmap.

Available now

AskAi component

A floating chat panel that toggles with Cmd/Ctrl + /. Drop it on any page:

import { AskAi } from '@publier/shell/qwik';

<AskAi client:load />

The panel is a UI shell — wire it to your AI backend by listening for the submit event and rendering the response. See the AskAi component reference for keyboard shortcuts and integration recipes.

llms.txt

Enable llms.enabled: true in publier.config.yaml to generate machine-readable content files at build time:

llms:
  enabled: true
  full: true               # also emit /llms-full.txt with full Markdown bodies
  collections: [docs]      # which collections to include

AI coding tools (Cursor, Copilot, Claude) consume these for documentation-aware suggestions. Follows the llms.txt convention:

• /llms.txt — page titles and URLs.
• /llms-full.txt — full page Markdown bodies for deep context (opt in via llms.full: true).

OpenInAI

A per-page dropdown that lets readers open the current doc in ChatGPT, Claude, Perplexity, or Google AI Studio. See OpenInAI.

On the roadmap

• Semantic search — sentence-embedding model in the browser for hybrid keyword + meaning queries.
• AI doc assistant — quantized LLM running in-browser via WebGPU, RAG-grounded on your content.
• Smart features — related docs via embedding similarity, “did you mean?” on failed queries, auto-generated summaries.