This article is a recap of an Anthropic session at Google Cloud Next '26, covering topics such as Anthropic's 54% coding market share in 2025, the evolution from chat to code to cowork, the definition of AI agents, the Solutions Machine concept, the Great Inversion of value, and three compounding opportunities. The session emphasizes that enterprise software will change more in the next two years than in the past twenty, with AI agents shifting from top-down planning to bottom-up execution.
原文翻译:
本文是Google Cloud Next '26上Anthropic session的回顾,涵盖了Anthropic在2025年占据54%编码市场份额、从聊天到编码再到协作的进化、AI代理的定义、解决方案机器概念、价值的大反转以及三个复合机遇。session强调企业软件在未来两年的变化将超过过去二十年,AI代理从自上而下的规划转向自下而上的执行。
This document compiles the most helpful resources for understanding AI engineering, covering ML theory, foundation models, evaluation, prompt engineering, RAG, finetuning, dataset engineering, inference optimization, and architecture. It includes papers, case studies, blog posts, and tools referenced in the book 'AI Engineering'.
原文翻译:本文档汇集了理解AI工程最有用的资源,涵盖ML理论、基础模型、评估、提示工程、RAG、微调、数据集工程、推理优化和架构。包括《AI工程》一书中引用的论文、案例研究、博客文章和工具。
This article presents a local hybrid RAG pattern combining lexical retrieval, ONNX-based semantic embeddings, and Foundry Local chat model for offline AI assistants. It covers architecture, implementation, and best practices for graceful degradation when semantic path fails.
原文翻译:本文介绍了一种本地混合RAG模式,结合词法检索、基于ONNX的语义嵌入和Foundry Local聊天模型,用于离线AI助手。涵盖架构、实现和最佳实践,确保语义路径不可用时优雅降级。
RAG-Anything is a lightweight RAG system based on LightRAG, designed for multimodal document processing (PDF, images, tables, formulas, etc.). It provides end-to-end parsing, multimodal understanding, knowledge graph indexing, and modal-aware retrieval. This article covers installation, configuration, and usage examples with SiliconFlow platform.
原文翻译:
RAG-Anything 是基于 LightRAG 的轻量级 RAG 系统,专为多模态文档(PDF、图片、表格、公式等)处理而设计。它提供端到端解析、多模态理解、知识图谱索引和模态感知检索。本文涵盖安装、配置以及使用硅基流动平台的示例。