Skip to content

Latest commit

 

History

History
 
 

chat-flask-cloudrun

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 

Cloud Run application with Web UI that demonstrates working with Vertex AI API

Author(s) Romin Irani

This application demonstrates a Cloud Run application that has a simple Form-based UI that represents a Chat widget. You can put in your query and it will invoke the PaLM Chat Bison model in the background and get back the response. It is a simple example but something that you can look to embed into your larger web application.

Flask Chat App Screen

Build and Deploy the application to Cloud Run

NOTE: Before you move forward, ensure that you have followed the instructions in SETUP.md. Additionally, ensure that you have cloned this repository and are currently in the chat-flask-cloudrun folder. This should be your active working directory for the rest of the commands.

To deploy the Flask Application in Cloud Run, we need to perform the following steps:

  1. Your Cloud Function requires access to two environment variables:

    • GCP_PROJECT : This the Google Cloud Project Id.
    • GCP_REGION : This is the region in which you are deploying your Cloud Function. For e.g. us-central1.

    These variables are needed since the Vertex AI initialization needs the Google Cloud Project Id and the region. The specific code line from the main.py function is shown here: vertexai.init(project=PROJECT_ID, location=LOCATION)

    In Cloud Shell, execute the following commands:

    export GCP_PROJECT='<Your GCP Project Id>'  # Change this
    export GCP_REGION='us-central1'             # If you change this, make sure region is supported by Model Garden. When in doubt, keep this.
  2. We are now going to build the Docker image for the application and push it to Artifact Registry. To do this, we will need one environment variable set that will point to the Artifact Registry name. We have a command that will create this repository for you.

    In Cloud Shell, execute the following commands:

    export AR_REPO='<REPLACE_WITH_YOUR_AR_REPO_NAME>'  # Change this
    export SERVICE_NAME='chat-flask-app' # This is the name of our Application and Cloud Run service. Change it if you'd like.
    gcloud artifacts repositories create "$AR_REPO" --location="$GCP_REGION" --repository-format=Docker
    gcloud auth configure-docker "$GCP_REGION-docker.pkg.dev"
    gcloud builds submit --tag "$GCP_REGION-docker.pkg.dev/$GCP_PROJECT/$AR_REPO/$SERVICE_NAME"
  3. The final step is to deploy the service in Cloud Run with the image that we built and pushed to the Artifact Registry in the previous step:

    In Cloud Shell, execute the following command:

    gcloud run deploy "$SERVICE_NAME" \
      --port=8080 \
      --image="$GCP_REGION-docker.pkg.dev/$GCP_PROJECT/$AR_REPO/$SERVICE_NAME" \
      --allow-unauthenticated \
      --region=$GCP_REGION \
      --platform=managed  \
      --project=$GCP_PROJECT \
      --set-env-vars=GCP_PROJECT=$GCP_PROJECT,GCP_REGION=$GCP_REGION

On successfully deployment, you will be provided a URL to the Cloud Run service. You can visit that in the browser to view the application that you just deployed. Give it a few queries of your choice and the application will query the Vertex AI Chat Model and provide you with the response.