Use generative AI

Deploy an AI application that harnesses the power of LLMs

Deploy generative applications using Vertex AI and Google Cloud

New customers get $300 in free credits to fully explore and conduct an assessment of Google Cloud.
Who this is for
Developers, Data Scientists, Data Engineers, Business Analysts
What you'll deploy
An application that uses Google Cloud's generative AI products
How you'll deploy
Once you’ve signed up for Google Cloud, you can deploy through the console.

What is generative AI?

Generative AI is a type of artificial intelligence that can create new content, such as text, images, audio, and 3D models. It does this by learning patterns from existing data and then using that knowledge to generate new and unique outputs. Generative AI is capable of producing highly realistic and complex content that mimics human creativity, making it a valuable tool for many industries, such as gaming, entertainment, and product design.

What is a large language model?

A large language model (LLM) is a type of artificial intelligence (AI) model that has been trained on a massive dataset. LLMs are able to understand and generate human-like text, and they can be used for a variety of tasks, such as: document summarization, translating language, and creating new content.

What are good use cases for generative AI?

Enterprise generative AI use cases include using foundation models to power understanding complex data, powering assistants, customer service interactions and content generation.

Solution Details

Document Summarizer with Vertex PaLM

This workflow uses Vertex's PaLM API to create automated document summaries.

  1. A Jupyter Notebook, to upload the document data for processing
  2. The uploaded PDF file is sent to a function running on Cloud Functions. This function handles PDF file processing.
  3. The Cloud Functions function uses Cloud Vision to extract all text from the PDF file.
  4. The Cloud Functions function stores the extracted text inside a Cloud Storage bucket.
  5. The Cloud Functions function uses Vertex AI LLM API to summarize the extracted text.
  6. The Cloud Functions function stores the text summaries of  PDFs in BigQuery tables.
  7. As an alternative to uploading PDF files through Jupyter Notebook, the developer can upload a PDF file directly to a Cloud Storage bucket — for instance, through the Console UI or gcloud. This upload triggers Eventarc to begin the Document Processing phase.
  8. As a result of the upload to Cloud Storage, Eventarc triggers the Document Processing phase, handled by Cloud Functions.

Document Summarization with Generative AI

Google Cloud experience level


Estimated deployment time

11 min

1 min to configure, 10 min to deploy

New customers get $300 in free credits to fully explore and conduct an assessment of Google Cloud.
  • Active Google Cloud account
  • Administrator rights to your project
Google Cloud
  • ‪English‬
  • ‪Deutsch‬
  • ‪Español‬
  • ‪Español (Latinoamérica)‬
  • ‪Français‬
  • ‪Italiano‬
  • ‪Português (Brasil)‬
  • ‪简体中文‬
  • ‪繁體中文‬
  • ‪日本語‬
  • ‪한국어‬