New Research: Supply Chain Attack on Axios Pulls Malicious Dependency from npm.Details →
Socket
Book a DemoSign in
Socket

@itaylor/markdowner

Package Overview
Dependencies
Maintainers
1
Versions
2
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

@itaylor/markdowner

Convert various file formats to markdown using AI and specialized converters

latest
Source
npmnpm
Version
0.0.2
Version published
Maintainers
1
Created
Source

Markdowner

Convert various file formats to markdown using AI and specialized converters.

Supported Formats

  • PDF (.pdf) - AI-powered conversion with image analysis
  • Images (.png, .jpg, .jpeg) - AI vision model describes content
  • Word (.docx) - Direct conversion
  • PowerPoint (.pptx) - Extract slides and content
  • Excel (.xlsx) - Convert to markdown tables
  • Text (.txt, .md) - Pass-through

Requirements

For AI features (choose one):

Option 1: OpenAI (or compatible services):

# Get API key from OpenAI, or use any OpenAI-compatible service
export OPENAI_API_KEY="your-api-key-here"

Option 2: Ollama (local):

# Install Ollama
curl -fsSL https://ollama.com/install.sh | sh

# Pull model and start server
ollama pull gemma3:27b
ollama serve

CLI Usage

# Convert file to markdown (uses local Ollama by default)
markdowner document.pdf

# Save to file
markdowner document.pdf -o output.md

# Use OpenAI
markdowner document.pdf \
  --openai-base-url https://api.openai.com/v1 \
  --openai-api-key $OPENAI_API_KEY \
  --openai-model gpt-4-vision-preview

# Use Ollama on remote server
markdowner document.pdf \
  --openai-base-url http://remote:11434/v1 \
  --openai-api-key ollama \
  --openai-model gemma3:27b

# Legacy Ollama syntax (still supported)
markdowner file.pdf --ollama-url http://localhost:11434

# Disable AI (faster, basic extraction for pdfs, images will throw)
markdowner document.pdf --no-ai

Library Usage

import { markdowner } from 'markdowner';

// With OpenAI
const markdown = await markdowner('./document.pdf', {
  openai: {
    baseURL: 'https://api.openai.com/v1',
    apiKey: process.env.OPENAI_API_KEY,
    model: 'gpt-4-vision-preview',
  },
});

// With Ollama using OpenAI-compatible API
const markdown = await markdowner('./document.pdf', {
  openai: {
    baseURL: 'http://localhost:11434/v1',
    apiKey: 'ollama', // required but unused
    model: 'gemma3:27b',
  },
});

// Legacy Ollama syntax (still supported)
const markdown = await markdowner('./document.pdf', {
  ollamaUrl: 'http://localhost:11434',
});

// Without AI (faster, basic extraction only)
const markdown = await markdowner('./document.pdf', {});

FAQs

Package last updated on 01 Nov 2025

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts