AI hands-on tutorials

An open source AI development agent called Refact is garnering attention in the current software development space. More than just a code-completion tool, it aims to cover the entire software engineering lifecycle from requirements understanding to final deployment. Notably, Refact is the first SWE-bench tested...

In Large Language Model (LLM) application development, it is a central challenge to enable models to securely and efficiently interact with external tools and data sources. Model Context Protocol (MCP) is being created for this purpose, which aims to establish a standard set of communication between LLM and the external world...

Foreword: Why do I need to manually create a Dify workspace? Typically, Dify workspaces (or "tenants") are created through its graphical interface. However, in certain scenarios, such as automating deployments, creating tenants in bulk, migrating data, or in server environments without a front-end interface...

This article will detail how to deploy, update, and migrate the open source LLM application development platform Dify (v0.6.14) using Docker and Docker Compose. It covers advanced operations from rapid deployment to data backup to building images from source, aiming to provide developers and operations staff with a clear...

Extending AI's capabilities: a complete guide to Dify's customization tools from creation to deployment Large language models are powerful in their own right, but their power is really unleashed when they're connected to real-world data and services. Whether it's checking the latest logistics information, accessing a company's internal knowledge base, or invoking a special...

AI Agents are moving from the cloud to the developer's local endpoint. Compared to graphical user interface (GUI)-based intelligences, command line (CLI) intelligences can be more deeply integrated into development workflows, automate complex tasks through scripting, and directly manipulate local files and code libraries...

Recently, following the attention generated by tools such as Claude Code, Google has launched its free counterpart, Gemini CLI, a tool designed to integrate powerful generative AI capabilities directly into the command line terminal, opening up new possibilities for automated task processing and local file management. Command Line AI.....

For many content creators, turning a raw, boring RSS news feed into a clearly structured, insightful, and consistently styled op-ed is a time-consuming and labor-intensive endeavor. The flood of information arrives daily, but actually polishing it into engaging content often requires a combination of "mechanical transportation" and "creation"...

In the current wave of AI, AI programming has become one of the most crowded tracks. From Cursor, Windsurf to v0 by Vercel, many programming agents have sprung up. Behind their rise are Anthropic Claude, OpenAI GP...

About FLUX.1 Kontext Dev FLUX.1 Kontext is a breakthrough multimodal image editing model from Black Forest Labs that supports simultaneous text and image input, and intelligently understands the context of an image and makes precise edits. Its development version is a ...

When uploading important materials (such as plain image files or scanned PDF documents) to the knowledge base of Dify, the LLM application development platform, many users often encounter a tricky problem: Dify is unable to read and parse the content in non-text format directly. This is mainly because Dify's knowledge base natively ...

As the application of artificial intelligence in the programming field becomes more and more in-depth, many developers, after experiencing the convenience of AI-assisted programming, expect to have an "exclusive AI engineer" that understands their needs better. The core of this demand lies in the ability of AI to accurately follow the developer's personalized instructions and specific project...

Background: n8n Challenges Integrating with the RAG Knowledge Base n8n is gaining traction as a powerful open source automated workflow tool. It was founded in 2019 by Jan Oberhauser, former visual designer of Pirates of the Caribbean, and aims to provide more flexibility than tools such as Zapier, into...

Vibe Coding: code disappears, a new wave of intuition-driven software development? The exponential growth of generative artificial intelligence is reshaping industries, and software development is no exception. Around the beginning of 2025, a new wave of thinking began to gain traction in Silicon Valley: it seemed that developers could leverage AI...

Background: why public access is needed n8n n8n is a powerful open source workflow automation tool that allows users to connect different applications and services to create automated processes. However, during use, many of n8n's App nodes (especially those involving third-party service licenses) need to be paired...

serverless-qrcode-hub is an open source tool designed to solve the problem of frequent failure of QR codes in WeChat group chats. It is based on Cloudflare Workers and D1 database , without the need for traditional servers to run . Users can generate permanently valid WeChat group QR code , convenient group chat management ...

Recently, MCP (Model Calling Protocol) has become a high-frequency term in the technical circle. Simply put, MCP aims to simplify the process of using external tools or services for large language models (LLMs), significantly lowering the threshold for developers and users to build complex AI applications. With the related...

Traditional web crawler frameworks are versatile, but often require additional cleansing and formatting when processing data, which makes their integration with Large Language Models (LLMs) relatively complex. The output of many tools (e.g., raw HTML or unstructured JSON) contains a lot of noise and is not suitable for direct use in retrieving enhanced...

With the popularity of Large Language Models (LLMs) and various AI services, it is becoming increasingly common for developers to integrate these capabilities in their applications. However, directly invoking API endpoints from service providers such as OpenAI, Hugging Face, and others often presents a number of management and O&M challenges: opaque costs...