Kanon 2 Enricher – the first hierarchical graphitization model
Hey HN, This is Kanon 2 Enricher, the first hierarchical graphitization model. It represents an entirely new class of AI models designed to transform document corpora into rich, highly structured knowledge graphs. In brief, our model is capable of: - Entity extraction, classification, and linking: identifying key entities like individuals, companies, governments, locations, dates, documents, and more, and classifying and linking them together. - Hierarchical segmentation: breaking a document up into its full hierarchy, including divisions, sections, subsections, paragraphs, and so on. - Text…
Kanon 2 Enricher – the first hierarchical graphitization model launched on March 3, 2026 with 10 votes, #1,177 of 23,380 launches that month and more than 90% of that year's launches.
In plain words
Kanon 2 Enricher is an AI model that converts document collections into structured knowledge graphs. It extracts and links entities such as people, companies, and locations; segments documents hierarchically from divisions down to paragraphs; and identifies textual elements like headings and tables of contents. The tool outputs data in the Isaacus Legal Graph Schema format and is designed for organizations needing to organize and structure large document corpora into interconnected, queryable information.
written from the facts on this page · September 2026
From the sources
We’re publicly releasing Kanon 2 Enricher , the world’s first hierarchical graphitization model , capable of transforming unstructured documents of any length into rich, highly structured knowledge graphs with sub-second latency. We’re also releasing the Isaacus Legal Document Graph Schema (ILDGS) , a first-of-a-kind knowledge graph schema for representing the structure and entities referenced within legal documents, which Kanon 2 Enricher natively outputs to. In the interests of supporting open legal AI and data research, we’ve made ILDGS freely available under the CC BY 4.0 license. Kanon 2 Enricher is available for use today via the Isaacus API . We thank Harvey, KPMG Law, Alvarez &…from isaacus.com
In the maker’s words, at launch
Hey HN, This is Kanon 2 Enricher, the first hierarchical graphitization model. It represents an entirely new class of AI models designed to transform document corpora into rich, highly structured knowledge graphs. In brief, our model is capable of: - Entity extraction, classification, and linking: identifying key…
Does a similar job
all alternatives →
FastGraphRAG – Better RAG using good old PageRank2024 · github.com · ▲457Hey there HN! We’re Antonio, Luca, and Yuhang, and we’re excited to introduce Fast GraphRAG, an open-source RAG approach that leverages knowledge graphs and the 25 years old PageRank for better information retrieval and reasoning. Building a good RAG pipeline these days takes a lot of manual optimizations. Most engineers intuitively start from naive RAG: throw everything in a vector database and hope that semantic search is powerful enough. This can work for use cases where accuracy isn’t too important and hallucinations are tolerable, but it doesn’t work for more difficult queries that…
Graphiti – LLM-Powered Temporal Knowledge Graphs2024 · github.com · ▲142Hey HN! We're Paul, Preston, and Daniel from Zep. We've just open-sourced Graphiti, a Python library for building temporal Knowledge Graphs using LLMs. Graphiti helps you create and query graphs that evolve over time. Knowledge Graphs have been explored extensively for information retrieval. What makes Graphiti unique is its ability to build a knowledge graph while handling changing relationships and maintaining historical context. At Zep, we build a memory layer for LLM applications. Developers use Zep to recall relevant user information from past conversations without including the entire…
Chonky – a neural approach for text semantic chunking2025 · github.com · ▲169TLDR: I’ve made a transformer model and a wrapper library that segments text into meaningful semantic chunks. The current text splitting approaches rely on heuristics (although one can use neural embedder to group semantically related sentences). I propose a fully neural approach to semantic chunking. I took the base distilbert model and trained it on a bookcorpus to split concatenated text paragraphs into original paragraphs. Basically it’s a token classification task. Model fine-tuning took day and a half on a 2x1080ti. The library could be used as a text splitter module in a RAG system or…
- OSOpen-Source DocumentAI with Ollama2025 · rlama.dev · ▲295
Complete AI Platform: RAG Systems & Intelligent Agents for Local AI
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
