Wei Zhang razhangwei

pydantic
langgrah

Instructions for Aider and other LLM tools: Keep it simple!

Embrace Simplicity Over Cleverness

Write code that's immediately understandable to others
If a solution feels complex, it probably needs simplification
Optimize for readability first, performance second unless proven otherwise
Avoid premature optimization

Caddy Configuration Cheat Sheet

Basic Site Configuration

# Simple static site
example.com {
    root * /var/www/html
    file_server
}

the external hardware needs to be EXT4.
relative path: usually the same as the shared forder so that it's identifiable.
extra options:
- --update
- --exclude dir1 --exclude dir2
View Logs: Check Diagnostics -> System Logs -> Logs -> Rsync - Jobs to see backup details.
Manual Backup: Select a job in the grid panel and click "Run" to start a backup manually.
Email Notifications: Configure email settings to receive backup status updates.
Mounting After Backup: To check files after backup, manually mount the drive without triggering another backup.

Here's a concise cheatsheet for Mustache templating:

Basic Syntax

Variables: {{variable}}
Escaped HTML: {{variable}} (default)
Unescaped HTML: {{{variable}}} or {{& variable}}
Comments: {{! comment }}

Sections

Typical good structure:

Title
- Overview.
Table of Contents
Roadmap
Setup
Configuration
Data Loading
Evaluation Function

Here's a concise cheatsheet for JSON Schema:

Basic Structure

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "$id": "https://example.com/schema.json",
  "title": "Schema Title",
  "description": "Schema description",

Basic Structure

Hydra uses YAML-like syntax for configuration files, typically with a .yaml extension.

key: value
nested:
  key: value
list:
  - item1

	from typing import List, Dict, Tuple
	import torch
	import torch.nn as nn
	import torch.nn.functional as F

	class RQVAE:
	def __init__(self,
	input_dim: int, # Shape: scalar (e.g., 768 for BERT embeddings)
	hidden_dims: List[int], # Shape: [dim1, dim2, ..., latent_dim]
	num_codebooks: int, # Shape: scalar (e.g., 3 for 3-level quantization)

	<artifacts_info>
	The assistant can create and reference artifacts during conversations. Artifacts are for substantial, self-contained content that users might modify or reuse, displayed in a separate UI window for clarity.

	# Good artifacts are...
	- Substantial content (>15 lines)
	- Content that the user is likely to modify, iterate on, or take ownership of
	- Self-contained, complex content that can be understood on its own, without context from the conversation
	- Content intended for eventual use outside the conversation (e.g., reports, emails, presentations)
	- Content likely to be referenced or reused multiple times