Anne Thorpe missAnneThorpe

Find the formula for the version you want to install:
- Visit https://github.com/Homebrew/homebrew-core/tree/master/Formula
- Click the file with your formula (e.g. “composer.rb”)
- Click “History” (top right)
- Click the commit hash for the version you want to download
- Click the three dots (top right of diff) and choose “view file”
- Click “Raw” and copy the raw URL from the browser address bar.
For example, composer 1.10.15 lives here: https://github.com/Homebrew/homebrew-core/blob/9e6e6a1ca8551901bff69d329c7fbb9007064134/Formula/composer.rb

Improving Gemini's Text Generation Accuracy with Corpus Managed by Google Spreadsheet as RAG

Abstract

Gemini excels at text generation with RAG for large datasets, but smaller ones benefit from prompting or data upload. This report explores using Gemini 1.5 Flash/Pro with RAG on medium-sized, Google Spreadsheet-stored datasets for improved accuracy and effectiveness.

Introduction

Pseudo Function Calling for Gemini API Through Prompt Engineering

Abstract

This research explores "pseudo function calling" in Gemini API using prompt engineering with JSON schema, bypassing model dependency limitations.

Introduction

Large Language Models (LLMs) like Gemini and ChatGPT offer powerful functionalities, but their capabilities can be further extended through function calling. This feature allows the LLM to execute pre-defined functions with arguments generated based on the user's prompt. This unlocks a wide range of applications, as demonstrated in these resources (see References).

Harnessing Gemini's Power: A Guide to Generating Content from Structured Data

Abstract

This report presents a method to train AI to effectively generate content from smaller, structured datasets using Python. Gemini's token processing capabilities are leveraged to effectively utilize limited data, while techniques for interpreting CSV and JSON formats are explored.

Introduction

In the era of rapidly advancing artificial intelligence (AI), the ability to analyze and leverage large datasets is paramount. While RAG (Retrieval Augmented Generation) environments are often ideal for such tasks, there are scenarios where content generation needs to be achieved with smaller datasets.

	/**
	* @OnlyCurrentDoc
	* @see https://www.googleapis.com/auth/spreadsheets
	* @see https://www.googleapis.com/auth/webmasters
	* @see https://www.googleapis.com/auth/script.external_request
	* @see https://www.googleapis.com/auth/drive
	* @see https://www.googleapis.com/auth/drive.file
	* @see https://www.googleapis.com/auth/script.container.ui
	* @see https://www.googleapis.com/auth/script.scriptapp
	*/

	// ==UserScript==
	// @name Twitch Sidebar Thumbnails
	// @author d
	// @version 1.0.0
	// @description Hover over channel in the sidebar to see a thumbnail preview of the stream.
	// @icon https://static.twitchcdn.net/assets/favicon-32-e29e246c157142c94346.png
	// @namespace https://gist.github.com/danydodson/756046e2edd9385457fe423c6bd45c18
	// @license MIT
	// @match https://www.twitch.tv/*
	// ==/UserScript==

	<rss version="2.0" xmlns:itunes="https://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:media="https://search.yahoo.com/mrss/">
	<channel>
	<title>PolyCast and ModCast</title>
	<itunes:subtitle>A Civilization Podcast Focused on Game Strategy</itunes:subtitle>
	<description>PolyCast and ModCast up to but not including Civ 7</description>
	<itunes:keywords>Sid Meier, Sid Meier's Civilization, Civilization VII, Civilization VI: Leader Pass, Civilization VI: New Frontiers Pass, Civilization VI: Gathering Storm, Civilization VI: Rise and Fall, Civilization VI, Civilization: Beyond Earth - Rising Tide, Civilization: Beyond Earth, Civilization V: Brave New World, Civilization V: Gods and Kings, Civilization VI, Civilization, Civ, Civ4, Civ5, Civ6, Civ7, CivRev, Warlords, Beyond the Sword, Sid Meier, GalCiv, Turn-Based Strategy, PolyCast, ModCast, RevCast, SCivCast, TurnCast, Firaxis, 2K</itunes:keywords>
	<itunes:author>The PolyCast.Net</itunes:author>
	<itunes:owner>
	<itunes:name>CanusAlbinus</itunes:name>

	function extractAll() {
	// 情報を書き出すスプレッドシートのファイル名を設定
	const FILENAME = "プライベートテスト2"

	// jsonファイルをGoogleドライブにアップロードしてテスト
	const jsonFile = DriveApp.getFileById('1CfwuzEQTKZA6616ZbfGcxxfkTKumQn3m');

	// スプレッドシートを新規作成
	const ss = SpreadsheetApp.create(FILENAME);

	{"messages": [{"role": "system", "content": "You are a Q&A AI assistant."}, {"role": "user", "content": "Who helps Mia find her way through the enchanted forests in 'The Starry Night Adventures'?"}, {"role": "assistant", "content": "Mia is helped by her two companions, Oliver the talking owl and Cometina, a playful comet, as she navigates the enchanted forests in 'The Starry Night Adventures.'"}]}
	{"messages": [{"role": "system", "content": "You are a Q&A AI assistant."}, {"role": "user", "content": "What is the name of the boy who discovers the hidden village in 'The Forest of Whispers'?"}, {"role": "assistant", "content": "The boy's name is Finn, and he discovers the hidden village of magical creatures while chasing his kite in 'The Forest of Whispers.'"}]}
	{"messages": [{"role": "system", "content": "You are a Q&A AI assistant."}, {"role": "user", "content": "How does the story of 'The Lost Treasure of the Dragon's Cave' emphasize the importance of friendship?"}, {"role": "assistant", "content": "In 'The L