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.
Gemini 1.5 API, released recently, significantly expands these capabilities. It can generate content by up to 1 million tokens, a substantial increase compared to previous versions. Additionally, Gemini 1.5 can now process up to 3,000 image files, vastly exceeding the 16-image limit of Gemini 1.0. Ref
While Gemini cannot directly work with Google Drive formats like Docs, Sheets, Slides, or PDFs yet, there are workarounds. In a previous report, I demonstrated a method for converting PDF data into images that Gemini can then process for tasks like invoice parsing. Ref
This report introduces a new Google Apps Script library called “GeminiWithFiles” that simplifies this process. GeminiWithFiles allows users to easily upload files and generate content using Gemini’s powerful capabilities. It also enables efficient description creation from multiple images with a single API call, significantly reducing the workload compared to processing each image individually as demonstrated in my prior report. Ref
By streamlining the process and expanding capabilities, GeminiWithFiles holds promise for various use cases across different domains. This report serves as an extended approach to the previous one, aiming to further reduce process costs and improve efficiency when working with Gemini and unstructured data.
Library’s project key
1dolXnIeXKz-BH1BlwRDaKhzC2smJcGyVxMxGYhaY2kqiLa857odLXrIC
You can see the detail information here https://github.com/tanaikech/GeminiWithFiles