Quantium GenAI Hackathon

This repo contains resources for participants of the Quantium GenAI Hackathon

Summary

Peer into the future of business solutions on the cloud!

This is an opportunity to experiment with Generative AI on Google Cloud, and build new solutions to real business problems.

Below are the links to your team's project:

• AI Artisans
• AI Billionaires
• Artificial Appetite
• Automating My Job Away
• Bing Chillin
• Chat PNC
• Checkout Max Ultra Pro
• Classy Tendies
• CWC
• Data Dreamers
• eNGS
• FatGPT
• GENius and Inspiring
• Grad Engineers and Eric
• HackAIholics
• KISS AI
• LINNAEAN
• Maui
• New Chicago
• PII AI
• Q-Smart
• Rishy and the Dutty
• SASQUAD
• S.M.A.R.T
• Team Hamburger
• The Q RedWinery
• Walnuts
• wiq.SAGA
• wiq.Trends

Your Project

Each team recieves a dedicated Google Cloud project <team-name-random-suffix>, with the Project Owner permission.

By default, the following servers/APIs are enabled:

• "aiplatform.googleapis.com"
• "artifactregistry.googleapis.com"
• "bigquery.googleapis.com"
• "compute.googleapis.com"
• "cloudbuild.googleapis.com"
• "cloudfunctions.googleapis.com"
• "datacatalog.googleapis.com"
• "dataflow.googleapis.com"
• "datastudio.googleapis.com"
• "dlp.googleapis.com"
• "eventarc.googleapis.com"
• "logging.googleapis.com"
• "sourcerepo.googleapis.com"
• "run.googleapis.com"
• "pubsub.googleapis.com"
• "monitoring.googleapis.com"
• "notebooks.googleapis.com"
• "eventarcpublishing.googleapis.com"
• "storage.googleapis.com"

gcloud CLI Guide

To run the following commands in your browser, open Cloud Shell through the Google Cloud Console.

• gcloud init will initialise, authorise and configure the gcloud CLI
• gcloud auth login will authorise access to the gcloud CLI for your current account
• gcloud config set project <PROJECT_ID> will set the default project to work on

To run these commands locally, install the gcloud CLI.

Vertex AI commands

You can manage your Vertex AI Entities through the gcloud CLI. For example:

• gcloud ai operations describe 1234 --project=example --region=us-central1 will describe the operation 1234 from project example in the region us-central1
• gcloud ai models upload --container-image-uri="gcr.io/example/my-image" --display-name=my-model --project=example --region=us-central1 will upload the model my-image under project example in the region us-central1

For a full list of Vertex AI commands, see here.

Quotas

Each project has quotas to restrict your consumption of shared resources, including hardware, software and network components.

These quotas are measured per region. This means that your project could have 60 requests per minute in one region, and 60 requests per minute in another supported region.

Vertex AI Quotas

Request Quota	Value
base_model:chat-bison requests per minute	60
base_model:code-bison, which includes codechat-bison, requests per minute	15
base_model:code-gecko requests per minute	15
base_model:text-bison requests per minute	60
base_model:textembedding-gecko requests per minute	600
Resource management requests* per minute	600
Job or long-running operation requests per minute	60
Online prediction requests per minute+	30,000
Online prediction request throughput per minute	1.5 GB
Online explanation requests per minute	600
Vertex AI Vizier requests per minute	6,000
Vertex AI Feature Store online serving requests per minute	300,000
Vertex ML Metadata requests per minute	12,000

* Resource management requests include any request that is not a job, long-running operation, online prediction request, or Vertex AI Vizier request.

⁺ This quota applies for public endpoints only. Private endpoints have unlimited requests per minute.

Resources

Additional information and resources are available at the links below:

• Introduction to Vertex AI
• Vertex AI Workbench Managed Notebooks (More secure)
• Vertex AI Workbench User-Managed Notebooks (More configurable)
• Vertex AI Jupyter Notebook tutorials
• Howto for JupyterLab Notebooks
• Vertex AI Quotas and Supported Regions