duanyrf

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

duanyrf

Create React and Typescript project with Vite

pnpm create vite;

Choose react + Typescript + SWC template project.

Install and configure tailwindcss

1. install dependencies with pnpm add -D tailwindcss postcss autoprefixer;

2. Generate both tailwind.config.cjs and postcss.config.cjs with pnpm exec tailwindcss init -p;

3. Configure your template paths in tailwind.config.cjs file:

duanyrf

services:
  db:
    image: postgres
    ports:
      - 5432:5432
    environment:
      POSTGRES_USER: postgres
      POSTGRES_PASSWORD: 123456
      POSTGRES_DB: ovisionweb
    volumes:

duanyrf

version: "3.9"

services:
  db:
    image: mysql:latest
    environment:
      MYSQL_DATABASE: database-name
      MYSQL_ROOT_PASSWORD: your_root_password
      MYSQL_USER: a_common_user
      MYSQL_PASSWORD: password_for_user