AI enabled Search. What do we mean by that?
Search engines that deal with embeddings, rerankers, LLMs, web scrapers, classifiers over multilingual and multimodal data.
Jina.AI is a player in this arena with many models; e.g: Reader-LM-v2 to convert Raw HTML to markdown. It is a 1.5B parameter language model that converts raw HTML into markdown or JSON, handling up to 512K tokens combined input/output length with support for 29 languages. Unlike its predecessor that treated HTML-to-markdown as a 'selective-copy' task, v2 approaches it as a translation process, enabling superior handling of complex elements like code fences, nested lists, tables, and LaTeX equations.