Intents : Explain with zep how to make a big model understand customer intents.
在自然语言处理(NLP)中,意图指用户表达某种目的,想做或想要的事情。通过分析用户发出的信息,识别其背后的意图,从而回复相关的内容。例如，“订餐”、“查看天气”、“我想去巴黎”等都是有效的意图。 为了...
Sorting
Vector Database Depth Comparison: Weaviate, Milvus & Qdrant
In the field of artificial intelligence and machine learning, especially when building applications such as RAG (Retrieval Augmented Generation) systems and semantic search, efficiently processing and retrieving massive unstructured data becomes crucial. Vector databases have emerged as a core technology to address this challenge. They are not only for storing high-dimensional ...
Unlocking the Little Red Book Marketing Code: A Guide to Growing Overseas User Operations (with PDF download)
Xiaohongshu, a hot social e-commerce platform in China and even in Asia, has long gone beyond a simple shopping app to become a weathervane for young people's lifestyles and a new position for brand marketing. For overseas brands and individuals wishing to enter the Chinese market or reach young consumers, mastering Xiaohongshu...
Learn how AI Coding works, starting with Cline!
没想到，AI 在编程领域掀起了半变天。从 v0 、bolt.new 再到各类结合 Agant 的编程工具 Cursor、Windsurf，AI Coding 已经具备 idea MVP 的巨大潜力。从...
Workflow (Workflow): an article to read the operating principles of workflow
开始之前，先了解几个“关键词”： 工作流 (Workflow)： 简单说，就是 “完成一件事的完整步骤”。 它像一份“说明书”，告诉你为了达成目标，需要做什么、按什么顺序做、谁来做。 输入 (Inpu...
Turn Cursor into Devin in an hour and learn the difference!
本文是“理解和部署智能体 AI”系列的一部分： 智能体 AI 系列 1：Devin 和 Agent Cursor 之间的比较 智能体 AI 系列 2：从思考者到执行者 —— 智能体 AI 的范式革命和...
Five ways to realize the LLM memory system
When building large language modeling (LLM) applications, memory systems are one of the key technologies to enhance conversation context management, long-term information storage, and semantic understanding. An efficient memory system can help the model maintain consistency over long conversations, extract key information, and even have the ability to retrieve historical conversations...
An article to take you to understand RAG (Retrieval Augmented Generation), the concept of theoretical introduction + code practice
一、LLMs 已经具备了较强能力了，为什么还需要 RAG(检索增强生成)? 尽管 LLM 已展现出显著的能力，但以下几个挑战依然值得关注： 幻觉问题：LLM 采用基于统计的概率方法逐词生成文本，这一机...
Simple, effective RAG retrieval strategy: sparse + dense hybrid search and rearrangement, and use "cue caching" to generate overall document-relevant context for text chunks.
为了让 AI 模型在特定场景中发挥作用，它通常需要访问背景知识。例如，客户支持聊天机器人需要了解其服务的具体业务，而法律分析机器人需要掌握大量的过往案例。 开发者通常使用检索增强生成（Retrieva...
Visual RAG for PDF with Vespa - a Python demo application
Introduction Thomas joined Vespa in April 2024 as a Senior Software Engineer. In one of his last previous assignments as an AI consultant, he actually built a RAG application based on Vespa's massive PDF collection...
Requirements Development Paradigm Change in Software Engineering Brought about by AI-Assisted Programming (Baoyu)
今年 AI 领域最大的突破之一应该是在编程领域，像 Cursor、v0 dev 这样的 AI 编程工具，不仅大幅降低了普通人编程的门槛，也让专业程序员的开发效率大幅提升。 但是我们听到的新闻都是不...
AI College of Engineering: 1. Tip Engineering
🚀 提示工程 提示工程（Prompt Engineering）是生成式 AI 时代的一项关键技能，这是一门设计有效指令来引导语言模型生成期望输出的艺术与科学。据 DataCamp 报道，这一新兴学科涉...
Retrieval: What is Retrieval? Explain the common "retrieval" techniques used in RAG.
基本概念 在信息技术领域，检索 (Retrieval) 指的是从一个大型数据集（通常是文档、网页、图像、音频、视频或其他形式的信息）中，根据用户的查询或需求，高效地定位和提取相关信息的过程。 其核心目...
![Agent AI: 探索多模态交互的前沿世界[李飞飞-经典必读]](https://oss.sharenet.ai/wp-content/uploads/2025/01/6dbf9ac2da09ee1.png)
Agent AI: Exploring the Frontier World of Multimodal Interaction [Fei-Fei Li - Classic Must Reads]
《Agent AI: Surveying the Horizons of Multimodal Interaction》 原文：https://ar5iv.labs.arxiv.org/html/24...
GraphReader: Graph-based Intelligents to Enhance Long Text Processing for Large Language Models
GraphReader:基于图的智能体，增强大型语言模型的长文本处理能力 图解专家：像个善于制作思维导图的导师，将冗长的文本转化为清晰的知识网络，让AI能够像沿着地图探索一样，轻松找到答案需要的各个关...
CAG: A cache-enhanced generation method that is 40 times faster than RAG
比RAG(检索增强生成)快40倍的CAG(缓存增强生成)。CAG彻底改变了知识获取方式：不再是实时检索外部数据，而是预先将所有知识加载到模型上下文中。这就像是把一个巨大的图书馆浓缩成了一本随身携带的工...
Google Agents and Basic Applications White Paper (Chinese version)
作者：Julia Wiesinger，Patrick Marlow和 Vladimir Vuskovic 原文：https://www.kaggle.com/whitepaper-agents 目...
2023 Old article review: a guide to the RAG system build process and evaluation
检索增强生成（Retrieval Augmented Generation，RAG）正在成为大语言模型（LLM）和向量数据库最受欢迎的应用之一。RAG 是通过从向量数据库（例如 Weaviate）检索...
OpenAI-o3 and Monte-Carlo Ideas
o3 来了，分享一些个人的浅见。关于 Test-time Scaling Law 的进展，比我们想象中的要快得多。但我想说的是，这条路其实有些曲折——它是 OpenAI 在追求 AGI 的道路上，采取...
English 
简体中文 
日本語 
한국어 
Español 
Deutsch 
Français 
Português do Brasil