Gists

Abstract

The Gemini API unlocks potential for diverse applications but requires consistent output formatting. This report proposes a method using question phrasing and API calls to craft a bespoke output, enabling seamless integration with user applications. Examples include data categorization and obtaining multiple response options.

Introduction

With the release of the LLM model Gemini as an API on Vertex AI and Google AI Studio, a world of possibilities has opened up. Ref The Gemini API significantly expands the potential of various scripting languages and paves the way for diverse applications. However, leveraging the Gemini API smoothly requires consistent output formatting, which can be tricky due to its dependence on the specific question asked.

Gists

Abstract

Gemini API on Vertex AI/Studio unlocks new applications with data retrieval and content generation through function calls. This report explores using the API for reverse engineering with a sample interpreter in Google Apps Script.

Introduction

The recent release of the LLM model Gemini as an API on Vertex AI and Google AI Studio unlocks a vast potential for new applications and methodologies. It significantly expands capabilities across diverse situations, paving the way for groundbreaking applications. Notably, the Gemini API allows data retrieval and content generation through function calls. In my recent report, “Guide to Function Calling with Gemini and Google Apps Script”, I explore function calls as a launchpad for various applications. This report showcases reverse engineering using the Gemini API, with a sample interpreter for creating sample values from a given regex using Google Apps Script.

Gists

Abstract

This report presents a workaround for copying a sheet, including its charts, from Google Spreadsheet “A” to Google Spreadsheet “B” using Google Apps Script.

Description

In this report, I would like to introduce a workaround for the following goal:

• Copying a sheet including charts from Google Spreadsheet “A” to Google Spreadsheet “B” using a script.

In general, when Sheets API is used, all objects of the Spreadsheet can be copied easily. However, when I tested this, I noticed the following problems:

Overview

This is a Google Apps Script library for supporting to use Google APIs with Google Apps Script.

Description

There are numerous powerful Google APIs available today. Google Apps Script streamlines interacting with these APIs through a simplified authorization process. Additionally, advanced Google services integrate seamlessly with Apps Script, making Google APIs highly advantageous for users.

However, utilizing APIs beyond advanced Google services can be challenging for some users. Developing a simpler method for using various Google APIs would significantly increase their accessibility and empower a broader range of users to create diverse applications.

Gists

Abstract

Google offers powerful APIs but using them (except advanced services) can be complex. A new, simpler method would benefit developers creating diverse applications. To address this, I built a Google Apps Script library simplifying API access.

Description

There are numerous powerful Google APIs available today. Google Apps Script streamlines interacting with these APIs through a simplified authorization process. Additionally, advanced Google services integrate seamlessly with Apps Script, making Google APIs highly advantageous for users.

• v1.2.3 (March 11, 2024)

  Modified the URL of the application installed in Microsoft Azure.

GitHub of OnedriveApp

• v2.0.5 (March 10, 2023)

  1. From this version, when the API key is used, the large file is downloaded by the API key. Because the specification for downloading the shared large file is sometimes changed. When the API key is not used, the shared large file is downloaded by the current specification (v2.0.4). If the shared large file cannot be downloaded by the change of the specification on Google’s side, please use the API key and test it again. The usage of goodls has not changed.

The detail information and how to get this are https://github.com/tanaikech/goodls.

• v2.0.4 (March 9, 2023)

  1. From January 2024, it seems that the specification of the process for downloading a large shared file on Google Drive has been changed. So I updated goodls to reflect this. The usage of goodls has not changed. In the current stage, when a large share file is downloaded, it is required to click the following button.

  <form
    id="download-form"
    action="https://drive.usercontent.google.com/download"
    method="get"
  >
    <input
      type="submit"
      id="uc-download-link"
      class="goog-inline-block jfk-button jfk-button-action"
      value="このままダウンロード"
    />
    <input type="hidden" name="id" value="fileId" />
    <input type="hidden" name="export" value="download" />
    <input type="hidden" name="authuser" value="0" />
    <input type="hidden" name="confirm" value="t" />
    <input type="hidden" name="uuid" value="uuId" />
    <input type="hidden" name="at" value="some value" />
  </form>
  

  In this version, the URL obtained by this click is created, and the created URL is used for downloading it.

Gists

Abstract

The Gemini API can now do semantic searches, going beyond content generation. This means it can understand the meaning of your search and provide better results, even if your words don’t exactly match the data. This report introduces the enhanced search capabilities of the Gemini API.

Introduction

The Gemini API expands its potential beyond content generation to encompass powerful semantic search capabilities. Searching existing data is crucial in various situations. However, before the introduction of generative AI, traditional search methods relied solely on keyword matching. Recent advancements in semantic search have introduced similarity search, allowing for a more nuanced understanding of queries. Combining this with the generative power of the Gemini API can significantly enhance the search results of existing data. This report explores the possibilities of enhanced search using the Gemini API.

CorporaApp was updated to v1.0.3.

• v1.0.3 (March 6, 2024)

  1. New method of getChunk was added. When this method is used, you can retrieve a single chunk using the resource name of chunk.

You can see the detail information here https://github.com/tanaikech/CorporaApp