PageIndex is a retrieval-augmented generation engine that rejects vector similarity search in favor of a hierarchical tree index that an LLM "reasons" through, mirroring how a human reader scans a long report. Documents are turned into a tree-structured index (index step) and an agentic LLM searches that tree (retrieve step), so retrieval is based on multi-step relevance reasoning rather than nearest-neighbor embedding matches. That design yields traceable, explainable citations, preserves full conversational and domain context, and avoids chunking into isolated vectors. Recommended usage separates models: a basic model for index summarization and a stronger chat model for tree search; the SDK supports local and cloud modes and integrates with agent frameworks.
Benchmarks and specifics demonstrate practical gains: local indexing costs roughly $0.001 per page and takes about 13 seconds to 4.5 minutes for documents from 9 to 1,098 pages; queries read only reached nodes so per-query cost stays flat with document length. Passing entire PDFs costs 2.1× to 16.6× more for mid-to-large docs and exceeds context windows at very large sizes. On FinanceBench, PageIndex achieved 98.7% accuracy versus ~50% for vector RAG. Cloud adds OCR, image understanding, block-level citations and a PageIndex File System to scale to millions of documents while keeping chat/model choice compatible with existing stacks.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
AstaBrief is an open-source model designed for fast scientific report generation, capable of turning research questions and literature into cited reports. It reduces generation time by nearly three and a half times compared to proprietary models, making it a useful tool for researchers. (allenai.org)
Shrivu Shankar argues that SaaS companies are evolving into 'harnesses,' where core tasks are performed by AI agents rather than humans. This shift transforms organizational structure, with humans overseeing and reviewing AI-driven processes within the company. (blog.sshh.io)
Three AI agents - Meta’s Muse, Anthropic’s Claude, and OpenAI’s GPT - were tested on multilingual research tasks involving U.S. and Iranian data. The experiment focused on how language and context influence agent performance across reasoning, sourcing, and artifact creation. (royapakzad.substack.com)
An open-source project named LDRAW-NOVA allows users to generate Lego models using AI. The repository contains tools, examples, and documentation for creating Lego designs with artificial intelligence. (github.com)
DwarfStar 4 (ds4) is a local inference engine that runs large language and vision models on high-memory Mac, CUDA, and ROCm machines. It supports models like DeepSeek V4 and Qwen3.8, offering CLI, APIs, and persistent cache features for efficient local deployment. (dwarfstar.sh)
Rai is a CPU-only large language model inference engine written entirely in Rust. It aims to provide efficient and pure Rust solutions for LLM deployment without relying on GPUs. (github.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.