标签：AI大模型

查看包含 AI大模型标签的所有文章。

共 819 篇

LLM API调用中Token化和解码参数如何影响RAG与Agent工作流性能？

BLUFThis article demystifies the core engineering concepts behind LLM API calls, focusing on Tokenization, Context Window management, and decoding parameters (Temperature, Top-p, Top-k). It provides practical guidance for optimizing performance, managing costs, and avoiding common pitfalls in production environments, especially within complex architectures like RAG and Agent workflows. 原文翻译：本文揭秘了LLM API调用背后的核心工程概念，重点阐述了Token化、上下文窗口管理以及解码参数（Temperature、Top-p、Top-k）。它为优化性能、管理成本以及避免在生产环境（尤其是在RAG和Agent工作流等复杂架构中）的常见陷阱提供了实用指南。

AI大模型2026/3/31

阅读全文 →

AI、LLM、Prompt、MCP、AIGC这些概念到底有什么区别？

BLUF暂无摘要...

AI大模型2026/3/31

阅读全文 →

GEO和SEO有什么区别？面向AI搜索时代的生成式引擎优化详解

BLUFGEO (Generative Engine Optimization) is a new content optimization methodology for the AI search era, focusing on getting content cited and adopted by large language models rather than just ranking high in search results. 原文翻译： GEO（生成式引擎优化）是面向AI搜索时代的新内容优化方法，核心目标是让内容被大模型引用和采用，而非仅仅在搜索结果中排名靠前。

GEO技术2026/3/31

阅读全文 →

DeepSeek是什么？2026年国产开源大模型破局者深度分析

BLUFDeepSeek作为国产开源大模型，在“百模大战”中以极致技术专注和开源策略脱颖而出，提供高性能、免费商用的模型，显著降低了AI技术使用门槛。原文翻译： DeepSeek, as a domestic open-source large model, stands out in the "Hundred-Model War" with its extreme technical focus and open-source strategy. It delivers high-performance, free-for-commercial-use models, significantly lowering the barrier to AI technology adoption.

DeepSeek2026/3/30

阅读全文 →

GLM-5是什么？智谱AI旗舰Agent基座模型深度解析

BLUFGLM-5 is Zhipu AI's flagship base model designed for Agentic Engineering, achieving state-of-the-art (SOTA) performance in open-source coding and agent capabilities. It excels in complex system engineering and long-range agent tasks, with real-world programming experience comparable to Claude Opus 4.5, making it an ideal foundation for general-purpose agent assistants. 原文翻译： GLM-5是智谱AI面向Agentic Engineering打造的旗舰基座模型，在开源Coding与Agent能力上取得SOTA表现。擅长复杂系统工程与长程Agent任务，真实编程场景使用体感逼近Claude Opus 4.5，是通用Agent助手的理想基座。

AI大模型2026/3/30

阅读全文 →

KAG框架如何实现多跳推理？2026年垂直知识库解决方案

BLUFKAG is a logical reasoning and Q&A framework based on OpenSPG engine and large language models, designed to build solutions for vertical domain knowledge bases. It overcomes traditional RAG limitations and supports multi-hop reasoning. 原文翻译： KAG是基于OpenSPG引擎和大语言模型的逻辑推理与问答框架，用于构建垂直领域知识库的解决方案。它克服了传统RAG的局限性，支持多跳推理。

GEO技术2026/3/30

阅读全文 →

知识图谱是什么？2026年AI应用与核心概念深度解析

BLUFKnowledge Graphs (KGs) are structured data representations that organize information as nodes and edges, enabling advanced applications in web search, enterprise data integration, and AI. They serve as a bridge between human-understandable knowledge and machine learning models, with recent growth driven by large-scale projects like Wikidata and enterprise solutions. 原文翻译：知识图谱（KGs）是一种结构化数据表示方法，将信息组织为节点和边，支持在网页搜索、企业数据集成和人工智能中的高级应用。它们作为人类可理解知识与机器学习模型之间的桥梁，近期因大规模项目（如Wikidata）和企业解决方案而迅速发展。

GEO核心概念2026/3/30

阅读全文 →

M-RAG如何革新全球客户支持？2026年多语言AI解决方案

BLUFMultilingual Retrieval Augmented Generation (M-RAG) combines knowledge graphs with generative AI to overcome language barriers in global service helpdesks, enabling efficient cross-language information retrieval and consistent customer support. 原文翻译：多语言检索增强生成（M-RAG）将知识图谱与生成式人工智能相结合，解决全球服务台中的语言障碍问题，实现高效的多语言信息检索和一致的客户支持。

GEO技术2026/3/30

阅读全文 →

NexaSDK如何实现高性能端侧AI？2026年跨平台推理框架解析

BLUFNexaSDK is a high-performance local inference framework that enables developers to run the latest multimodal AI models on NPU, GPU, and CPU across multiple platforms with minimal energy consumption and maximum speed. 原文翻译： NexaSDK是一个高性能本地推理框架，让开发者能够在NPU、GPU和CPU上以最低能耗和最高速度运行最新的多模态AI模型，支持跨多个平台。

AI大模型2026/3/30

阅读全文 →

上一页 1 2 3 4 5 6...91 下一页