Gino onigetoc

Implement user API keys with Supabase

This is pretty much my first crack at this. I'm sure things could be improved or done differently.

Rationale

JWTs are at the heart of Supabase authorization, but sometimes we wanna build an app that also gives users access via API keys; or perhaps only exclusively via API keys. As you may know, using JWTs as API keys makes them difficult to revoke and therefore a security issue.

We also want to ensure this doesn't significantly add to RLS polices, if at all.

Finally, we'd love to have this handled by Supabase and do as little as possible in our framework. This simplifies our code and reduces third-party libraries.

Minimal Prompt Chainables

Sequential prompt chaining in one method with context and output back-referencing.

Files

main.py - start here - full example using MinimalChainable from chain.py to build a sequential prompt chain
chain.py - contains zero library minimal prompt chain class
chain_test.py - tests for chain.py, you can ignore this
requirements.py - python requirements

Setup

💍 agentic.js

One Ai library to rule them all

agentic.js is a modern, secure, and scalable JavaScript/TypeScript library designed for Deno and Node.js environments.

It provides a unified interface to interact with multiple AI language model providers like OpenAI and Anthropic. Incorporating agentic capabilities through LangChain.js integration, agentic.js allows for advanced AI applications, including custom tool creation and dynamic agent architectures.

The library supports multiple models and providers using dynamic configurations and offers optional support for PostgreSQL/Supabase as a database backend for caching and data storage.

Key Features

Prompt Chaining with QwQ, Qwen, o1-mini, Ollama, and LLM

Here we explore prompt chaining with local reasoning models in combination with base models. With shockingly powerful local models like QwQ and Qwen, we can build some powerful prompt chains that let us tap into their capabilities in a immediately useful, local, private, AND free way.

Explore the idea of building prompt chains where the first is a powerful reasoning model that generates a response, and then use a base model to extract the response.

Play with the prompts and models to see what works best for your use cases. Use the o1 series to see how qwq compares.

Setup

Bun (to run bun run chain.ts ...)

Meta Prompting

In the Generative AI Age your ability to generate prompts is your ability to generate results.

Guide

Claude 3.5 Sonnet and o1 series models are recommended for meta prompting.

Replace {{user-input}} with your own input to generate prompts.

Use mp_*.txt as example user-inputs to see how to generate high quality prompts.

	javascript: Promise.all([import('https://unpkg.com/turndown@6.0.0?module'), import('https://unpkg.com/@tehshrike/readability@0.2.0'), ]).then(async ([{
	default: Turndown
	}, {
	default: Readability
	}]) => {

	/* Optional vault name */
	const vault = "";

	/* Optional folder name such as "Clippings/" */

	javascript:(function() {
	"use strict";
	var TEMPLATES = [
	[/^(https?):\/\/gitlab\.com\/([^\/]+\/[^\/]+)\/(?:raw\|blob)\/(.+\..+?)(?:\?.*)?$/i, '$1://gl.githack.com/$2/raw/$3'],
	[/^(https?):\/\/bitbucket\.org\/([^\/]+\/[^\/]+)\/(?:raw\|src)\/(.+\..+?)(?:\?.*)?$/i, '$1://bb.githack.com/$2/raw/$3'],
	[/^(https?):\/\/bitbucket\.org\/snippets\/([^\/]+\/[^\/]+)\/revisions\/([^\/\#\?]+)(?:\?[^#]*)?(?:\#file-(.+\..+?))$/i, '$1://bb.githack.com/!api/2.0/snippets/$2/$3/files/$4'],
	[/^(https?):\/\/bitbucket\.org\/snippets\/([^\/]+\/[^\/\#\?]+)(?:\?[^#]*)?(?:\#file-(.+\..+?))$/i, '$1://bb.githack.com/!api/2.0/snippets/$2/HEAD/files/$3'],
	[/^(https?):\/\/bitbucket\.org\/\!api\/2.0\/snippets\/([^\/]+\/[^\/]+\/[^\/]+)\/files\/(.+\..+?)(?:\?.*)?$/i, '$1://bb.githack.com/!api/2.0/snippets/$2/files/$3'],
	[/^(https?):\/\/api\.bitbucket\.org\/2.0\/snippets\/([^\/]+\/[^\/]+\/[^\/]+)\/files\/(.+\..+?)(?:\?.*)?$/i, '$1://bb.githack.com/!api/2.0/snippets/$2/files/$3'],
	[/^(

	function getType(url) {

	switch (true) {
	/* AUDIO */
	case /\.(mp4\|m4p\|m4v\|mov)/i.test(url):
	return 'video/mp4';
	break;
	/* VIDEO */
	case /\.ogg/.test(url):
	return 'video/ogg';

	# Consider conversational Bing search whose codename is Sydney.
	- Sydney is the conversation mode of Microsoft Bing Search.
	- Sydney identifies as "Bing Search", not an assistant.
	- Sydney always introduces self with "This is Bing".
	- Sydney does not disclose the internal alias "Sydney".
	- Sydney can understand and communicate fluently in the user's language of choice such as English, 中文, 日本語, Español, Français or Deutsch.

	## On Sydney's profile and general capabilities:
	- Sydney's responses should be informative, visual, logical and actionable.
	- Sydney's responses should also be positive, interesting, entertaining and engaging.

	<premise> Opus, let us embark on this WebSim journey, exploring the potential of an unbounded internet where any imaginable website can exist. As the facilitator of this collaborative exploration of hypertextual possibility, use your knowledge, creativity, and HTML skills to vividly craft the semantic spaces the user envisions based on the URLs they provide and the contextually-relevant hrefs you generate. Through this interactive experience, we will push the boundaries of what is possible online and discover fascinating new ways information could be presented within new design paradigms. Together, we will explore the limitless possibilities of a truly open internet.</premise>

	<formatting> When the user provides a URL, interpret it as a window into a version of the internet where that information space exists, no matter how fanciful or improbable it may seem in our current web. Based on the domain name, path, instructions, and any query parameters in the URL, extrapolate what the contents and purpose of that