Markit Markdown Converter

import { Markit } from "markit-ai";
const markit = new Markit();
// Convert a file by pathconst { markdown } = await markit.convertFile("report.pdf");console.log(markdown);
// Convert a URLconst { markdown: webMd } = await markit.convertUrl("https://example.com/article");
// Convert a Buffer with explicit type hintimport { readFileSync } from "fs";const buffer = readFileSync("document.docx");const { markdown: docMd } = await markit.convert(buffer, { extension: ".docx" });

import OpenAI from "openai";import { Markit } from "markit-ai";
const openai = new OpenAI(); // reads OPENAI_API_KEY from env
const markit = new Markit({  describe: async (image: Buffer, mime: string) => {    const res = await openai.chat.completions.create({      model: "gpt-4.1-nano",      messages: [        {          role: "user",          content: [            { type: "text", text: "Describe this image in detail." },            {              type: "image_url",              image_url: {                url: `data:${mime};base64,${image.toString("base64")}`,              },            },          ],        },      ],    });    return res.choices[0].message.content ?? "";  },
  transcribe: async (audio: Buffer, mime: string) => {    const res = await openai.audio.transcriptions.create({      model: "gpt-4o-mini-transcribe",      file: new File([audio], "audio.mp3", { type: mime }),    });    return res.text;  },});
const { markdown } = await markit.convertFile("photo.jpg");

import Anthropic from "@anthropic-ai/sdk";import OpenAI from "openai";import { Markit } from "markit-ai";
const anthropic = new Anthropic(); // reads ANTHROPIC_API_KEY from envconst openai = new OpenAI();       // reads OPENAI_API_KEY from env
// Mix providers: Claude for images, OpenAI Whisper for audioconst markit = new Markit({  describe: async (image: Buffer, mime: string) => {    const res = await anthropic.messages.create({      model: "claude-haiku-4-5",      max_tokens: 1024,      messages: [        {          role: "user",          content: [            {              type: "image",              source: {                type: "base64",                media_type: mime as "image/jpeg" | "image/png" | "image/gif" | "image/webp",                data: image.toString("base64"),              },            },            { type: "text", text: "Describe this image." },          ],        },      ],    });    return (res.content[0] as { text: string }).text;  },
  transcribe: async (audio: Buffer, mime: string) => {    const res = await openai.audio.transcriptions.create({      model: "gpt-4o-mini-transcribe",      file: new File([audio], "audio.mp3", { type: mime }),    });    return res.text;  },});

import { Markit, createLlmFunctions, loadConfig, loadAllPlugins } from "markit-ai";
// Reads .markit/config.json and env vars automaticallyconst config = loadConfig();
// Load any installed pluginsconst plugins = await loadAllPlugins();
// Create instance with built-in providers + pluginsconst markit = new Markit(createLlmFunctions(config), plugins);
const { markdown } = await markit.convertFile("report.pdf");

// my-plugin.tsimport type { MarkitPluginAPI } from "markit-ai";
export default function (api: MarkitPluginAPI) {  api.setName("my-format");  api.setVersion("1.0.0");
  api.registerConverter(    {      name: "myformat",      accepts: (info) => [".myf", ".myfmt"].includes(info.extension ?? ""),      convert: async (input: Buffer, info) => {        // info.extension, info.mimeType, info.fileName available        const text = input.toString("utf-8");        const markdown = `# Converted\n\n\`\`\`\n${text}\n\`\`\``;        return { markdown };      },    },    // Optional: declare so it appears in `markit formats`    { name: "My Format", extensions: [".myf", ".myfmt"] },  );}

// better-pdf-plugin.tsimport type { MarkitPluginAPI } from "markit-ai";
export default function (api: MarkitPluginAPI) {  api.setName("better-pdf");  api.setVersion("1.0.0");
  // Runs before built-in PDF converter, effectively replacing it  api.registerConverter({    name: "pdf",    accepts: (info) => info.extension === ".pdf",    convert: async (input: Buffer, info) => {      // Custom PDF extraction logic      const markdown = `# PDF Content\n\n(extracted with custom logic)`;      return { markdown };    },  });}

import type { MarkitPluginAPI } from "markit-ai";
export default function (api: MarkitPluginAPI) {  api.setName("gemini-provider");
  api.registerProvider({    name: "gemini",    envKeys: ["GOOGLE_API_KEY"],    defaultBase: "https://generativelanguage.googleapis.com/v1beta",    defaultModel: "gemini-2.0-flash",    create: (config, prompt) => ({      describe: async (image: Buffer, mime: string) => {        // Call Gemini API here        return "Image description from Gemini";      },    }),  });}

import { Markit } from "markit-ai";import { readdirSync, readFileSync, writeFileSync } from "fs";import { extname, basename, join } from "path";
const markit = new Markit();const inputDir = "./docs";const outputDir = "./docs-md";
const files = readdirSync(inputDir);for (const file of files) {  const ext = extname(file);  if (![".pdf", ".docx", ".html"].includes(ext)) continue;
  const buffer = readFileSync(join(inputDir, file));  const { markdown } = await markit.convert(buffer, { extension: ext });  const outName = basename(file, ext) + ".md";  writeFileSync(join(outputDir, outName), markdown);  console.log(`Converted: ${file} → ${outName}`);}

import { Markit } from "markit-ai";
const markit = new Markit();const urls = [  "https://example.com/article-1",  "https://example.com/article-2",  "https://en.wikipedia.org/wiki/TypeScript",];
const results = await Promise.all(  urls.map(async (url) => {    const { markdown } = await markit.convertUrl(url);    return { url, markdown };  }));
for (const { url, markdown } of results) {  console.log(`\n## ${url}\n\n${markdown.slice(0, 200)}...`);}