Building a custom Gemini AI using Vertex AI for an organization

Gemini API
,
1

Hi all,
I’m building a custom generative AI application using Vertex AI’s Gemini API for my organization. The goal is to generate text content based on information extracted from .docx files.
I’m currently exploring different approaches and would appreciate any insights from the community. Here’s my initial breakdown of the steps:

  1. Text Extraction: Using Python libraries like python-docx to programmatically extract text content from .docx files.
  2. Vertex AI and Gemini API Interaction: Sending the extracted text as a prompt to the chosen Gemini model. Processing the generated content returned by the model (text format).

I’m particularly interested in learning about:

  1. Alternative approaches: Open to suggestions on alternative methods for achieving text generation from documents using Vertex AI or other tools.
    2.Possibilities: suggestion on Working in Vertex AI to build a custom Gemini AI for an organization.

Has anyone worked on similar projects or can recommend resources for building custom generative AI solutions with Vertex AI? Any advice or insights would be greatly appreciated!