Vibe Coding Discoverreader
View on GitHubConvert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
Open-source engine behind r.jina.ai and s.jina.ai: prepend a URL to get LLM-ready markdown from web pages, PDFs, Office files and images, or a search query to get the top results already fetched. Runs stateless or with S3/MinIO caching.
Use Cases
Convert any URL to LLM-friendly markdown for promptsFeed web pages into RAG ingestion pipelinesGive agents live web search results as markdownParse PDFs at a URL into markdownConvert Word/Excel/PowerPoint files to markdownCaption page images with a VLM for text-only LLMsSemantic markdown chunking for embeddingsTrim output to a token budget for fixed context windowsScreenshot or full-page shot of a rendered pageIn-site search scoped to specific domainsStrip links/images for cheaper embedding pipelines
Built With
- Language
- TypeScript
- Frameworks
- Node.js · TypeScript · Koa · Puppeteer · PDF.js · Docker · LibreOffice · MinIO/S3 · Docker Compose
Tags
url-to-markdown · web-scraping · llm-context · web-search · pdf-parsing · headless-chrome · readability · content-extraction · rag-ingestion · token-budget · markdown-chunking · screenshots · reader-api · jina-ai · curl-impersonate · office-docs