Serve Markdown to AI Agents with Accept Headers
Serve Markdown to AI agents and LLMs via the Accept: text/markdown header. Browsers get HTML, agents get clean Markdown.
API Documentation
Summary
This documentation details the `toMarkdown` utility within Cloudflare Workers AI, which converts various file formats like PDF, HTML, and images into structured Markdown. This process is designed to optimize data for large language models (LLMs), retrieval-augmented generation (RAG) pipelines, and AI Agents.
Highlights
- Supports a wide range of formats including PDF, XML, Microsoft Office, CSV, Apple documents, and common image types.
- Facilitates better LLM performance by providing structured, semantic, and machine-readable input.
- Image conversion utilizes specialized Workers AI models for automated object detection and summarization.
- Provides detailed output metadata including filename, MIME type, estimated token count, and the converted content.
auto-generated
Context
Audience
Developers building AI applications
DomainArtificial Intelligence
Formattechnical documentation
Accessvia code binding or REST API
Source Overview
Cloudflare Workers AI offers a toMarkdown utility that converts files in formats such as PDF, images, HTML, XML, Office, CSV, and Apple documents into structured Markdown.
The conversion tool can be accessed via code binding or REST API, and supports features like object detection and summarization for images. Converted outputs include the document’s name, detected mimetype, token count, and Markdown-formatted content.
Topics
Related
RAG PipelinesLarge Language ModelsAI AgentsDocument ProcessingObject Detection
