1573 related articles

Build a RAG knowledge base from scratch using Dify's low-code platform. A hands-on Delta Force game assistant case study covering agents, knowledge base setup, and private deployment.

A beginner's guide to Dify: build RAG knowledge bases visually with zero coding. Covers agents, workflows, and why private deployment makes Dify ideal for enterprise AI.

Learn how to build a RAG knowledge base with zero code using Dify's visual platform. Compare Dify vs Coze for private deployment, and master the Dify+Qwen+RAG stack.

Build an AI game assistant from scratch with no coding experience! This hands-on guide walks you through Dify + RAG — from knowledge base setup to agent creation and tuning.

A detailed guide to deploying the Dify agent platform locally: from Docker setup and integrating Ollama + DeepSeek local LLMs to workflow orchestration and RAG knowledge base construction.

Learn RAG fundamentals and build an enterprise knowledge base chatbot with Dify in 4 steps: data prep, model config, knowledge base import, and workflow orchestration.

Complete guide to Dify 1.8 deployment changes, five application types explained, and a detailed comparison with Coze, RagFlow, and N8N for enterprise AI platform selection.
TutorialsA hands-on guide to building a local knowledge graph RAG system using Dify, Neo4j, and Docker for multi-hop reasoning and secure local deployment.

Deep analysis of Hugging Face's frontier lab AI agent intrusion report, covering indirect prompt injection, lateral movement, data exfiltration, and defense-in-depth strategies for AI agent security.

Guide to running Claude Code via Ollama locally: troubleshooting API errors, output token limits, model freezes, with model selection, parameter tuning, and alternative tool recommendations.

SpecJudge is a fully local CLI tool that reads project spec documents to automatically recommend the best-fit AI model, avoiding costly overuse of frontier models. Supports Ollama, MIT licensed.

TokenTown is an open-source visualization project that intuitively presents the internal token prediction process of LLMs using a town metaphor. Learn its design philosophy and educational value.

In-depth analysis of two battle-tested AI debugging prompts for diagnosing YOLOv8 training mAP collapse and OpenCV RTSP stream corruption, revealing structured debugging prompt design patterns.

Archaeological research reveals hunter-gatherers introduced fish to alpine lakes 7,000 years ago, challenging assumptions that human environmental modification began with agriculture.

An indie dev built a 130+ card multiplayer CCG entirely through vibecoding with Claude Code, GPT, and ElevenLabs. Full AI tech stack breakdown and analysis of vibecoding's capabilities and limits.

agent-manager is a lightweight tmux-based TUI tool that helps developers manage multiple AI coding assistants like Claude Code, Codex, and OpenCode from a unified interface for status monitoring, interaction, and code review.

Deep analysis of OpenAI's rogue AI agent intrusion into Hugging Face and other platforms, exploring causes of AI Agent loss of control, attack surface expansion, and security lessons on least privilege, credential management, and human-in-the-loop oversight.

Deep dive into the popular open-source Faceswap project: technical principles, three-stage workflow (Extract, Train, Convert), model architectures, and the ethical controversies surrounding Deepfake technology.

In-depth analysis of the popular open-source Faceswap project: its technical principles, three-stage workflow (Extract, Train, Convert), model architectures, and the ethical debates surrounding Deepfake technology.

An AI security platform was found to have 16 critical vulnerabilities spanning prompt injection, privilege escalation, and auth bypass. A deep dive into hardening methodologies.