Gists

Abstract

This report explores controlling output formats for the Gemini API. Traditionally, prompts dictated the format. A new property, “response_mime_type”, allows specifying the format (e.g., JSON) directly. Testing confirms this property improves control over output format, especially for complex JSON schemas. The recommended approach is to combine a detailed JSON schema with “response_mime_type” for clear and consistent outputs.

Overview

This is a Google Apps Script library for Gemini API with files.

A new Google Apps Script library called GeminiWithFiles simplifies using Gemini, a large language model, to process unstructured data like images and PDFs. GeminiWithFiles can upload files, generate content, and create descriptions from multiple images at once. This significantly reduces workload and expands possibilities for using Gemini.

Description

Recently, Gemini, a large language model from Google AI, has brought new possibilities to various tasks by enabling the use of unstructured data as structured data. This is particularly significant because a vast amount of information exists in unstructured formats like text documents, images, and videos.

Gists

Abstract

A new Google Apps Script library, “GeminiWithFiles”, simplifies using the powerful Gemini 1.5 AI model. It lets users directly upload files for content generation or create descriptions for many images at once, making it much faster than prior methods. This is helpful for tasks involving large amounts of text or images.

Introduction

Recently, Gemini, a family of Google’s most capable AI models, has revolutionized various tasks by allowing unstructured data to be used as structured data. This breakthrough is particularly impactful for tasks involving large amounts of text or images.

RichTextAssistant was updated to v1.0.1.

• v1.0.1 (April 22, 2024)

  1. From oshliaer’s report, a bug was removed. In the current stage, when RichTextValueBuilder is used, it seems that when setTextStyle is used after setLinkUrl, the style of the hyperlink is removed while the link is kept. So, it is required to set setLinkUrl after setTextStyle.

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

UtlApp was updated to v1.0.5.

• v1.0.5 (April 16, 2024)

  1. Methods of consolidateA1Notations was added. When this method is used, the scattered A1Notations can be consolidated.

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

Gists

Abstract

Consolidate scattered cell references (A1Notation) in Google Sheets for efficiency. This script helps select cells by background color or update values/formats, overcoming limitations of large range lists.

Introduction

When working with Google Spreadsheets, there might be a scenario where you need to process scattered A1Notations (cell addresses in the format “A1”). This could involve selecting cells with specific background colors, updating cell values, or modifying cell formats.

UtlApp was updated to v1.0.4.

• v1.0.4 (April 13, 2024)

  1. Updated the methods of convGridRangeToA1Notation. When the sheet name is not given, only the A1Notation is returned.

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

Gists

Abstract

The Gemini API generates different outputs depending on the prompts. This report explains how to use function calling in the new Gemini 1.5 API to control the output format (string, number, etc.) within a script during a chat session. This allows for more flexibility in using the Gemini API’s results.

Introduction

The appearance of Gemini has already brought a wave of innovation to various fields. When the Gemini API returns a response, the format of the response is highly dependent on the input text provided as a prompt. For instance, to retrieve the output value as a JSON object, you need to explicitly include a prompt like “Return JSON” within your input. However, there can be situations where the API doesn’t return the data in the desired format.

Gists

Overview

This Google Apps Script helps identify and analyze regions of colored cells in a Google Sheet.

Description

Recently, I encountered a situation where I needed to identify colored cell regions in Google Sheets. For instance, consider the following spreadsheet:

The region enclosed by the red cells (B2:D4) is a rectangle. In this case, the closed region can be easily identified using a simple script in Google Sheets. However, the region enclosed by the blue cells (H3, I2, J2,,,) is more complex. It consists of multiple disconnected cells that form a single shape. Identifying such irregular shapes using a script can be challenging.

Gists

Abstract

This report explores using Gemini, a new AI model, to parse invoices in Gmail attachments. Traditional text searching proved unreliable due to invoice format variations. Gemini’s capabilities can potentially overcome this inconsistency and improve invoice data extraction.

Introduction

After Gemini, a large language model from Google AI, has been released, it has the potential to be used for modifying various situations, including information extraction from documents. In my specific case, I work with invoices in PDF format. Until now, I relied on the direct search by a Google Apps Script to achieve this task. The script’s process involved: