Extracting structured information effectively and accurately from long unstructured text with LangExtract and LLMs. This article explores Google’s LangExtract framework and its open-source LLM, Gemma 3, demonstrating how to parse an insurance policy to surface details like exclusions.
This article details a step-by-step guide on building a knowledge graph from plain text using an LLM-powered pipeline. It covers concepts like Subject-Predicate-Object triples, text chunking, and LLM prompting to extract structured information.
A popular and actively maintained open-source web crawling library for LLMs and data extraction, offering advanced features like structured data extraction, browser control, and markdown generation.
ReaderLM-v2 is a 1.5B parameter language model developed by Jina AI, designed for converting raw HTML into clean markdown and JSON with high accuracy and improved handling of longer contexts. It supports multilingual text in 29 languages and offers advanced features such as direct HTML-to-JSON extraction. The model improves upon its predecessor by addressing issues like repetition in long sequences and enhancing markdown syntax generation.
Parsera is a simple and fast Python library for scraping websites using Large Language Models (LLMs). It's designed to be lightweight and minimize token usage for speed and cost efficiency.
Triplex is an open-source model that efficiently converts unstructured data into structured knowledge graphs at a fraction of the cost of existing methods. It outperforms GPT-4o in both cost and performance, making knowledge graph construction more accessible.
