Preface

Since I have already written several articles on the basics of AI, I figured it's about time to release an AI learning map: on one hand, it helps clear my own thoughts, allowing me to clearly know which knowledge points I have specifically learned and practiced, and serves as my own AI learning notebook; on the other hand, it also gives friends who happen to come across it a general reading order when looking at AI-related articles.

However, currently there is very little content, but there's no other way; we can only take it one step at a time.

Getting Started with AI

This section covers the basic knowledge of the AI field, mainly the parts that beginners can quickly get in touch with and start using: these articles range from the most basic local large language model UIs and introductions to commonly used API providers, to how to use Docker to deploy open-source large language model UIs (such as LobeChat) along with detailed usage tutorials, and further to common basic knowledge such as using Docker to build local large language models on your own.

This is from the perspective of my own actual learning, describing the basic tools and processes I believe are needed for getting started with AI, hoping to help beginner friends quickly accumulate practical experience.

• Starting Your AI Journey: A Detailed Introduction to Local LLM UIs and LLM API Providers
• Highly Internationally Recognized ChatGPT API Proxy Solution: Comprehensive Analysis of OpenRouter + Domestic Payment Guide Currently the most recommended way to use ChatGPT (and other mainstream model provider) APIs in China
• AI Multimodal Model Overview: From Text-to-Image/Video to chatgpt-web-midjourney-proxy Hands-on Practice
• Value Reconstruction of Personal Blogs in the AI Era (I): Becoming a Trusted Knowledge Anchor—The New Value of Personal Blogs in the AI Era
• Personal Knowledge Engineering (I): From Article Index to Knowledge Structure—A Practice of AI-Collaborative Exploration of Personal Knowledge Systems
• Personal Knowledge Engineering (II): From Cognitive Structure to Knowledge Engineering—Why Does Knowledge Need to Be Structured?
• AI Era Observation (I): Generalists, No Longer Just the Privilege of Geniuses

AI Principles

This section mainly focuses on the working mechanisms behind AI systems. Compared to the introductions in “Getting Started with AI” which lean towards tools and ecosystems, the articles here focus more on explaining the basic logic of AI when processing information, such as vector representation, RAG (Retrieval-Augmented Generation) workflows, and core concepts like embedding.

This content does not stop at the level of abstract theory, but combines actual practical cases to step-by-step dismantle the operation process of AI systems, allowing readers to understand the technical logic behind modern AI applications as a whole.

• AI Semantic Space Exploration (I): Vectors—The Universal Language in the AI World Understand vectors, and you can understand the underlying working principles of AI.
• AI Semantic Space Exploration (II): From a Word to an Article—How Semantic Vectors Are Generated Understand how text is transformed into vectors.
• AI Semantic Space Exploration (III): How Does AI Determine If Two Vectors Are Similar? Understand how similarity is compared between vectors.
• Understanding RAG from Scratch (Part 1): Principles and Complete Process Analysis
• Understanding RAG from Scratch (II): Running a Local RAG Demo on Mac mini—A Practical Guide to the Minimal Architecture
• AI and Cognition (I): Reconstruction of Creation in the AI Era—From Information Processing to Cognitive Collaboration
• AI and Cognition (II): AI Language Ability—From Appearance to Mechanism
• Value Reconstruction of Personal Blogs in the AI Era (Part 1): Becoming a Trusted Knowledge Anchor
• Value Reconstruction of Personal Blogs in the AI Era (II): From Content Recording to Digital Personality—How to Make AI Understand “Who I Am”

AI Applications

This section is mainly about some practical application cases of AI.

• Docker Series: Detailed Deployment Tutorial Based on the Open Source Large Language Model UI Framework: LobeChat Currently one of the few AI frontend solutions that supports automatic multi-device synchronization
• Unlocking the Full Potential of LobeChat: A Complete Guide from Setup to Practical Application
• Building a Private AI: A Detailed Tutorial on Building an Open-Source Large Language Model Locally Based on Ollama
• Deploying Llama 3.2 on Mac mini (M4 Pro): A Complete Guide to Efficient Running and Cross-Origin Access Optimization via Ollama
• The Most Convenient AI App Frontend: Comprehensive Introduction to Chatbox + User Guide An out-of-the-box AI App-style multi-platform frontend that can be used right after downloading and installing
• Exploration of Features and Research on Built-in Tools of the WordPress Chatbot Plugin ”AI Engine”
• Free Entry-Level Local AI Image Generation Tools on Mac (Part 1): Detailed Explanation of Diffusion Bee Settings and Practical Demonstration
• Free Entry-Level Local AI Image Generation Tools on Mac (Part 2): Draw Things Installation and Usage Tutorial
• Building a Self-Hosted Embedding Model with Ollama + Chatbox Knowledge Base in Practice A simple and convenient way to implement a personal knowledge base.
• Making Embedding an Infrastructure: Deploying Independent Embedding Services in PVE + LXC
• Building a “Lightweight Knowledge Index” for My Blog (V): Guess What You Want—The Real Introduction of Embeddings
• Building a “Lightweight Knowledge Index” for My Blog (VI): AI Summary and Editable Semantic Layer Design
• Building a “Lightweight Knowledge Index” for My Blog (VII): Right Menu—The Unified Organizational Mechanism of Semantic Space and Classification System
• From Knowledge Acquisition to Capability Invocation: How MCP Changes AI Application Architecture