AI & LLMs

Docs for LLM

You can make your docs site more AI-friendly with dedicated docs content for large language models.

To begin, make a getLLMText function that converts pages into static MDX content. This is an example for Fumadocs MDX:

import { source } from '@/lib/source';
import type { InferPageType } from 'fumadocs-core/source';

export async function getLLMText(page: InferPageType<typeof source>) {
  const processed = await page.data.getText('processed');

  return `# ${page.data.title}
URL: ${page.url}

${processed}`;
}

It requires includeProcessedMarkdown to be enabled:

import { defineDocs } from 'fumadocs-mdx/config';

export const docs = defineDocs({
  docs: {
    postprocess: {
      includeProcessedMarkdown: true,
    },
  },
});

llms-full.txt

A version of docs for AIs to read.

import { source } from '@/lib/source';
import { getLLMText } from '@/lib/get-llm-text';

// cached forever
export const revalidate = false;

export async function GET() {
  const scan = source.getPages().map(getLLMText);
  const scanned = await Promise.all(scan);

  return new Response(scanned.join('\n\n'));
}

*.mdx

Allow people to append .mdx to a page to get its Markdown/MDX content.

On Next.js, you can make a route handler to return page content, and redirect users to that route.

import { type NextRequest, NextResponse } from 'next/server';
import { getLLMText } from '@/lib/get-llm-text';
import { source } from '@/lib/source';
import { notFound } from 'next/navigation';

export const revalidate = false;

export async function GET(
  _req: NextRequest,
  { params }: { params: Promise<{ slug?: string[] }> },
) {
  const { slug } = await params;
  const page = source.getPage(slug);
  if (!page) notFound();

  return new NextResponse(await getLLMText(page));
}

export function generateStaticParams() {
  return source.generateParams();
}

Page Actions

Common page actions for AI, require *.mdx to be implemented first.

npx @fumadocs/cli add ai/page-actions

Use it in your docs page like:

<div className="flex flex-row gap-2 items-center border-b pt-2 pb-6">
  <LLMCopyButton markdownUrl={`${page.url}.mdx`} />
  <ViewOptions
    markdownUrl={`${page.url}.mdx`}
    githubUrl={`https://github.com/${owner}/${repo}/blob/dev/apps/docs/content/docs/${page.path}`}
  />
</div>

Ask AI

You can install the AI search dialog using Fumadocs CLI:

npx @fumadocs/cli add ai/search

You can add the trigger component to your root layout.

AI Model

By default, it's configured for Inkeep AI using Vercel AI SDK. Update the configurations in useChat and /api/chat route to connect to your own AI model instead.

Note that Fumadocs doesn't provide the AI model, it's up to you. Your AI model can use the llms-full.txt file generated above, or more diversified sources of information when combined with 3rd party solutions.