Web Content Extraction
Extract the main content and metadata from a public HTTPS webpage as Markdown, text, or JSON.
ONGSOOLABS FEATURES
Explore the content processing capabilities OngsooLabs provides today and how to use them.
AVAILABLE NOW
Read, organize, and summarize web content, then turn it into formats AI can use.
Extract the main content and metadata from a public HTTPS webpage as Markdown, text, or JSON.
Read a text-layer PDF from a public HTTPS URL and return it as Markdown.
File uploads, DOCX, OCR, and encrypted PDFs are not currently supported.
Get a summary and related keywords in one request, so you can understand the key points of a public webpage.
Split supplied text or extracted content into chunks that preserve order and context for embeddings and search.
WAYS TO USE
Integrate with the API, try the capabilities in Playground, or connect Reader MCP to an AI tool.
Add web content extraction, PDF reading, webpage summaries, and Chunking to your product or workflow.
View DocsSign in to try web content extraction, webpage summaries, and public PDF reading in your browser.
Try PlaygroundConnect Reader MCP to read public web content from supported AI tools and use it in your workflow.
View MCP GuideEXPLORING
We are exploring ways to understand more kinds of content and turn it into formats AI can use.
Explore ways to read and understand more kinds of content beyond webpages and PDFs.
Explore ways to extract the information you need in more consistent formats and make it easier for AI to reuse.
These directions are being explored. Their availability and release timelines have not been decided.
START HERE
View Reader results in Playground, then explore the Docs when you are ready to integrate.