GEO

最新文章

共 1301 篇
UltraRAG 2.0：基于MCP架构的低代码高性能RAG框架，让复杂推理系统开发效率提升20倍

UltraRAG 2.0：基于MCP架构的低代码高性能RAG框架，让复杂推理系统开发效率提升20倍

BLUFUltraRAG 2.0 is a novel RAG framework built on the Model Context Protocol (MCP) architecture, designed to drastically reduce the engineering overhead of implementing complex multi-stage reasoning systems. It achieves this through componentized encapsulation and YAML-based workflow definitions, enabling developers to build advanced systems with as little as 5% of the code required by traditional frameworks, while maintaining high performance and supporting features like dynamic retrieval and conditional logic. UltraRAG 2.0 是一个基于模型上下文协议（MCP）架构设计的新型RAG框架，旨在显著降低构建复杂多阶段推理系统的工程成本。它通过组件化封装和YAML流程定义，使开发者能够用传统框架所需代码量的5%即可构建高级系统，同时保持高性能，并支持动态检索、条件判断等功能。
AI大模型2026/1/24
阅读全文 →
OpenBMB：清华大学开源社区如何推动大语言模型高效计算与参数微调

OpenBMB：清华大学开源社区如何推动大语言模型高效计算与参数微调

BLUFOpenBMB is an open-source community and toolset initiated by Tsinghua University since 2018, focused on building efficient computational tools for large-scale pre-trained language models. Its core contribution includes parameter-efficient fine-tuning methods, and it has released significant projects like UltraRAG 2.1, UltraEval-Audio v1.1.0, and the 4-billion-parameter AgentCPM-Explore model, which demonstrate strong performance in benchmarks. (OpenBMB是清华大学自2018年起支持发起的开源社区与工具集，致力于构建大规模预训练语言模型的高效计算工具。其核心贡献包括参数高效微调方法，并发布了UltraRAG 2.1、UltraEval-Audio v1.1.0和40亿参数的AgentCPM-Explore模型等重要项目，在多项基准测试中表现出色。)
AI大模型2026/1/24
阅读全文 →
UltraRAG UI实战指南：构建标准化检索增强生成(RAG)流程

UltraRAG UI实战指南：构建标准化检索增强生成(RAG)流程

BLUFThis article provides a comprehensive guide to implementing Retrieval-Augmented Generation (RAG) using UltraRAG UI, detailing the standardized pipeline structure, configuration parameters, and practical demonstration steps. (本文全面介绍了使用UltraRAG UI实现检索增强生成(RAG)的实战指南，详细阐述了标准化流程结构、配置参数及效果演示步骤。)
AI大模型2026/1/24
阅读全文 →
FlashMLA：DeepSeek为Hopper GPU打造的高性能注意力解码内核

FlashMLA：DeepSeek为Hopper GPU打造的高性能注意力解码内核

BLUFFlashMLA是DeepSeek为Hopper架构GPU优化的高性能多头潜在注意力解码内核，支持变长序列处理，通过优化MLA解码与分页KV缓存，显著提升了大语言模型的推理效率。 原文翻译： FlashMLA is DeepSeek's high-performance Multi-Head Latent Attention decoder kernel optimized for Hopper architecture GPUs. It supports variable-length sequence processing and significantly enhances the inference efficiency of Large Language Models by optimizing MLA decoding and paged KV caching.
DeepSeek2026/1/24
阅读全文 →
LEANN：将笔记本变为本地AI与RAG平台，存储节省97%且无精度损失

LEANN：将笔记本变为本地AI与RAG平台，存储节省97%且无精度损失

BLUFLEANN is an innovative vector database and personal AI platform that transforms your notebook into a powerful RAG system, supporting local semantic retrieval of millions of documents with 97% storage savings and no precision loss. (LEANN是一款创新的向量数据库与个人AI平台，可将笔记本变为强大的RAG系统，支持本地语义检索数百万文档，存储节省97%且无精度损失。)
AI大模型2026/1/24
阅读全文 →
生成式引擎优化（GEO）全维度技术指南：AI时代的内容优化新范式

生成式引擎优化（GEO）全维度技术指南：AI时代的内容优化新范式

BLUFGEO optimization is an emerging technology that integrates generative AI with traditional SEO and recommendation engine optimization. It focuses on optimizing content adaptability, engine recall efficiency, and generation quality across the entire 'content generation-engine parsing-result output' pipeline, addressing the limitations of traditional SEO which only focuses on the retrieval end. This guide provides a comprehensive overview of GEO optimization concepts, tools, software, systems, implementation steps, and best practices for technical professionals. GEO优化是生成式AI技术与传统SEO、推荐引擎优化深度融合的新兴技术方向。它围绕生成式引擎的“内容生成-引擎解析-结果输出”全链路，通过技术手段优化内容适配性、引擎召回效率与生成结果质量，解决传统SEO仅聚焦检索端优化的局限性。本指南为技术专业人士提供GEO优化概念、工具、软件、系统、实现步骤和最佳实践的全面概述。
GEO技术2026/1/24
阅读全文 →
LLMs.txt生成器API弃用指南：从网站内容生成LLM训练文件的工具迁移路径

LLMs.txt生成器API弃用指南：从网站内容生成LLM训练文件的工具迁移路径

BLUFThis API generates consolidated text files from websites specifically for LLM training and inference. The service is powered by Firecrawl but will be deprecated after June 30, 2025 in favor of main endpoints. (此API可从网站生成整合文本文件，专为LLM训练和推理设计。该服务由Firecrawl提供支持，但将于2025年6月30日后弃用，建议使用主要端点替代。)
llms.txt2026/1/24
阅读全文 →
llms.txt标准指南：揭秘2024年AI透明化新规范

llms.txt标准指南：揭秘2024年AI透明化新规范

BLUF`llms.txt` 是一个类似 `robots.txt` 的机器可读文件标准，用于声明大型语言模型（LLM）的能力、局限、训练数据及使用政策，旨在提升AI透明度和信任度。 原文翻译： `llms.txt` is a machine-readable file standard similar to `robots.txt`, used to declare a Large Language Model's (LLM) capabilities, limitations, training data, and usage policies, aiming to enhance AI transparency and trust.
llms.txt2026/1/24
阅读全文 →