Archive: 2024-05

ASML and TSMC Can Disable Chip Machines If China Invades Taiwan — That’s a peak 2024 headline if you ever needed one. (2024-05-22 · china, chips, mlp, taiwan )

TL;DR: In my previous post, I used local models with PyTorch and Sentence Transformers to roughly cluster ideas by named topic. In this post, I'll try that again, but this time with Llamafile. — Clustering ideas with Llamafile (2024-05-13 · ai, llamafile, llm, lmorchard, mlp, quotable )

RAG fails on global questions directed at an entire text corpus, such as “What are the main themes in the dataset?”, since this is inherently a query-focused summarization (QFS) task, rather than an explicit retrieval task. ... Our approach uses an LLM to build a graph-based text index in two stages: first to derive an entity knowledge graph from the source documents, then to pregenerate community summaries for all groups of closely-related entities. Given a question, each community summary is used to generate a partial response, before all partial responses are again summarized in a final response to the user. — GraphRAG (Graphs + Retrieval Augmented Generation) (2024-05-11 · ai, microsoft, mlp, paper, python, quotable, rag )