最新文章

This tutorial series, derived from Shanghai Jiao Tong University's 2024 AI Security Technology course, provides hands-on programming guidance for large language models, covering fine-tuning, deployment, prompt engineering, knowledge editing, model watermarking, jailbreak attacks, multimodal models, and AI agent security. 原文翻译： 本教程系列源自上海交通大学2024年春季《人工智能安全技术》课程讲义，提供大模型相关的动手编程指导，涵盖微调与部署、提示学习与思维链、知识编辑、模型水印、越狱攻击、多模态模型、大模型智能体与安全等内容。

The OpenAI Agents SDK is a lightweight, provider-agnostic Python framework for building multi-agent workflows with features like sandbox agents, tools, guardrails, and real-time voice support. 原文翻译： OpenAI Agents SDK 是一个轻量级、提供商无关的 Python 框架，用于构建具有沙盒代理、工具、护栏和实时语音支持等功能的多智能体工作流。

Cognee is an open-source Python framework that builds persistent, dynamic, and learnable knowledge memory systems for AI applications by integrating vector search, graph databases, and cognitive science to create interconnected knowledge graphs. 原文翻译： Cognee 是一个开源的 Python 框架，通过集成向量搜索、图数据库和认知科学，为 AI 应用构建持久化、动态且可学习的知识记忆系统，创建互连的知识图谱。

xmllm is a JavaScript utility that extracts structured data from LLMs using a flexible XML-based approach, offering resilience to errors and provider-agnostic compatibility. 原文翻译： xmllm 是一个 JavaScript 工具，通过灵活的基于 XML 的方法从大型语言模型中提取结构化数据，具有容错性和提供商无关的兼容性。

Retrieval-Augmented Generation (RAG) enhances LLMs by integrating external evidence retrieval, addressing limitations like factual inconsistency while introducing challenges in retrieval quality and pipeline efficiency. This survey synthesizes recent advances, categorizes architectures, and identifies future research directions. 原文翻译： 检索增强生成（RAG）通过整合外部证据检索来增强大型语言模型，解决了事实不一致等限制，同时引入了检索质量和管道效率方面的挑战。本综述综合了最新进展，对架构进行分类，并指出了未来的研究方向。

This article systematically introduces the core principles, technical comparisons, mainstream implementation solutions, and code practices of static RAG and dynamic RAG, suitable for technical selection and in-depth learning reference. 原文翻译： 本文系统介绍静态RAG与动态RAG的核心原理、技术对比、主流实现方案及代码实践，适合技术选型和深入学习参考。

This article provides a comprehensive analysis of RAG (Retrieval-Augmented Generation) technology, covering its core architecture, implementation methods, application scenarios, and future trends. It explains how RAG enhances AI model capabilities by integrating retrieval systems with generative models to reduce hallucinations and improve answer accuracy, offering practical code examples and optimization strategies for developers. 原文翻译： 本文全面解析了RAG（检索增强生成）技术，涵盖其核心架构、实现路径、应用场景及未来趋势。文章阐述了RAG如何通过整合检索系统与生成模型来增强AI模型的认知能力，减少“幻觉”并提高回答准确性，为开发者提供了实用的代码示例和优化策略。

Ragas is a comprehensive Python toolkit for evaluating and optimizing Large Language Model (LLM) applications with objective metrics, automated test generation, and seamless integrations with popular frameworks like LangChain. 原文翻译： Ragas 是一个全面的 Python 工具包，用于通过客观指标、自动化测试生成以及与 LangChain 等流行框架的无缝集成来评估和优化大型语言模型（LLM）应用。

This article explores the spectrum of AI system architectures, from basic LLMs to sophisticated AI agents, using a resume-screening case study to illustrate when to choose simpler solutions like RAG over complex autonomous agents for practical, reliable applications. 原文翻译： 本文探讨了从基础大语言模型到复杂AI智能体的AI系统架构谱系，通过简历筛选案例研究，说明了何时为实际、可靠的应用选择RAG等更简单的解决方案，而非复杂的自主智能体。