技术文章
Dify 工作流相关教程与资讯
How to
【How to】营销人员如何构建可靠的AI工作流
In 2026, every marketer knows how to write a prompt. We ask ChatGPT to write copy, or we ask Claude to brainstorm campaign ideas. But as marketing teams try to scale these experiments into daily opera
Company
【Company】How Dify.AI powers the company that's powering the world
A global leader in consumer electronics, renowned for reshaping how people charge and interact with smart devices, supports over 100 million users worldwide through its extensive product lineup. To ma
How to
【How to】开始使用 Dify
Welcome to your new AI workspace! If you are looking to bring the power of AI into your daily life, your business, or your products, you are in the right place. Building with AI used to require a team
Event
【Event】准备好迎接IF Con东京2025
On October 24, 2025, LangGenius will host IF Con Tokyo 2025 , a one-day conference dedicated to turning AI ideas into real-world outcomes. LangGenius is the company behind Dify, a no/low-code platform
Company
【Company】致那些总觉得可以更好的人
Most job ads look like the same face. Passion. Mission. Change the world. Competitive pay. Flexible work. Diversity and inclusion. Then the universal line: If you love challenges, embrace change, and
How to
【How to】财务自动化实战：如何利用 Dify 工作流破解“信贷优先”管理难题
In modern enterprise management, "Credit First" is becoming a common choice for teams pursuing extreme efficiency. Distributing corporate credit cards (like Mercury Cards) to employees and allowing th
Release
【Release】扩展插件端点：为 Dify 带来无服务器灵活性
About Endpoint The Endpoint is a new, extensible type introduced in Difyâs v1.0.0 plugin system, providing a new API entry point for Dify. Plugins can define the logic of these APIs through code. Fr
Release
【Release】Dify v0.7.0: Enhancing LLM Memory with Conversation Variables and Variable Assigners
We have been focusing on enhancing LLM application memory management to meet specific scenario needs. While LLMs can store chat history in context windows, attention limitations often lead to memory g
How to
【How to】Enhancing GPT-Researcher with Parallel and Advanced Iterative Features
Hi, Iâm Evan from the Dify product team. Today, Iâll explain how GPT-Researcher works and how to use advanced iterative features to enhance your workflow. Introduction GPT-Researcher is a popular
Product
【Product】借助 InfraNodus 增强 Dify RAG：扩展 LLM 上下文
Retrieval-Augmented Generation (RAG) is a well-known way to give large language models (LLMs) extra context from your own knowledge base or documents. However, most RAG setups have a hard time graspin
Release
【Release】Dify.AI v0.3.13 发布：轻松调用 Llama2、ChatGLM 等顶级开源大语言模型
Many attentive users noticed updates to our product over the weekendâweâve integrated many new LLMs from model suppliers, a long-awaited version V0.3.13 for many friends. Previously, Dify has succ
Product
【Product】EdgeOne Pages 插件：快速部署，即时验证
We are pleased to announce that the Tencent Cloud EdgeOne Pages plugin is now available on the Dify Marketplace. This powerful deployment plugin enables users to instantly publish ZIP and HTML file as