EdgeDocAPI

Developer Guides & Use Cases

Zero-retention edge APIs for converting URLs/HTML to clean Markdown, splitting documents into deterministic RAG chunks, and extracting structured OpenGraph & JSON-LD metadata.

Markdown Conversion

HTML to Markdown API

Convert messy HTML pages into clean, token-efficient Markdown in milliseconds on Cloudflare Edge. Strips scripts, navbars, and ads with zero data retention.

POST /v1/url-to-markdown
AI Agents

URL to Markdown for LLMs

Fetch any public HTTPS webpage and turn it into clean Markdown with estimated token counts for GPT, Claude, and Gemini prompts.

POST /v1/url-to-markdown
RAG Pipelines

RAG Chunker for LangChain

Replace brittle regex splitters with a deterministic edge RAG chunking API. Preserves Markdown headings, token budgets, overlap, and source metadata.

POST /v1/rag-chunk
Metadata Extraction

OpenGraph & JSON-LD Extractor API

Extract OpenGraph tags, Twitter Cards, Schema.org JSON-LD objects, canonical URLs, headings, and outbound links from any URL or HTML payload.

POST /v1/extract-metadata
Edge Infrastructure

Edge Web-to-Markdown without Browser Bloat

Fast, lightweight HTML-to-Markdown extraction running natively on Cloudflare Workers without expensive Puppeteer/Playwright clusters.

POST /v1/url-to-markdown
Vector Databases

Deterministic RAG Chunking for Pinecone

Prepare clean, metadata-enriched chunks with exact token budgets and overlap ready for Pinecone upsert pipelines.

POST /v1/rag-chunk
Vector Databases

Semantic Chunking for Qdrant & pgvector

Streamline document ingestion into Qdrant, Weaviate, or pgvector using deterministic heading-aware chunking with overlap.

POST /v1/rag-chunk
RAG Frameworks

HTML to Markdown for LlamaIndex

Feed clean Markdown into LlamaIndex MarkdownNodeParser instead of noisy HTML tags, scripts, and navigation menus.

POST /v1/url-to-markdown
Privacy & Security

Zero-Retention Document API

Stateless, ephemeral-memory HTML-to-Markdown, RAG chunking, and metadata extraction API. Zero payload logging, SHA-256 API keys.

POST /v1/url-to-markdown
Cost Optimization

Webpage Token Counter API

Convert any public HTTPS URL or HTML page to clean Markdown and get an instant calibrated token count before calling expensive LLM APIs.

POST /v1/url-to-markdown
AI Agents

Clean Article Extractor for GPT

Extract main article text as clean Markdown from news, blogs, and documentation URLs for OpenAI Assistants and function calling.

POST /v1/url-to-markdown
Claude & MCP

Markdown Preprocessing for Claude

Convert web pages and HTML into clean Markdown chunks optimized for Claude prompts and Model Context Protocol (MCP) tools.

POST /v1/url-to-markdown
Technical SEO

Structured Metadata API for SEO

Audit OpenGraph tags, Twitter Cards, canonical URLs, JSON-LD structured data, headings, and outbound links via a single fast edge API.

POST /v1/extract-metadata
Content Intelligence

Canonical & Headings Extractor API

Extract clean document heading outlines (H1-H6), canonical URLs, and resolved links from any public webpage or HTML snippet.

POST /v1/extract-metadata
MCP Ecosystem

MCP Server for Cursor, Claude & Windsurf

Install docopsapi-mcp to give Cursor, Claude Desktop, and Windsurf instant url_to_markdown, rag_chunk, and extract_metadata tools.

POST /v1/url-to-markdown