Author(s) | Lavi Nigam, Holt Skinner |
This application demonstrates a Cloud Run application that uses the Streamlit framework.
Sample screenshots and video demos of the application are shown below:
NOTE: Before you move forward, ensure that you have followed the instructions in SETUP.md. Additionally, ensure that you have cloned this repository and you are currently in the
gemini-streamlit-cloudrun
folder. This should be your active working directory for the rest of the commands.
To run the Streamlit Application locally (on Cloud Shell), we need to perform the following steps:
-
Setup the Python virtual environment and install the dependencies:
In Cloud Shell, execute the following commands:
python3 -m venv gemini-streamlit source gemini-streamlit/bin/activate pip install -r requirements.txt
-
Your application requires the following environment variables:
- If you are using standard Vertex AI:
export GOOGLE_CLOUD_PROJECT='<Your Google Cloud Project ID>' # Change this export GOOGLE_CLOUD_REGION='us-central1' # If you change this, make sure the region is supported.
- If you are using Vertex AI in express mode:
export GOOGLE_API_KEY='<Your Vertex AI API Key>' # Change this
-
To run the application locally, execute the following command:
In Cloud Shell, execute the following command:
streamlit run app.py \ --browser.serverAddress=localhost \ --server.enableCORS=false \ --server.enableXsrfProtection=false \ --server.port 8080
The application will startup and you will be provided a URL to the application. Use Cloud Shell's web preview function to launch the preview page. You may also visit that in the browser to view the application. Choose the functionality that you would like to check out and the application will prompt the Gemini API in Vertex AI and display the responses.
NOTE: Before you move forward, ensure that you have followed the instructions in SETUP.md. Additionally, ensure that you have cloned this repository and you are currently in the
gemini-streamlit-cloudrun
folder. This should be your active working directory for the rest of the commands.
To deploy the Streamlit Application in Cloud Run, we need to perform the following steps:
-
Your Cloud Run app requires access to two environment variables:
GOOGLE_CLOUD_PROJECT
: This the Google Cloud project ID.GOOGLE_CLOUD_REGION
: This is the region in which you are deploying your Cloud Run app. For e.g. us-central1.
These variables are needed since Vertex AI needs the Google Cloud Project ID and the region.
In Cloud Shell, execute the following commands:
export GOOGLE_CLOUD_PROJECT='<Your Google Cloud Project ID>' # Change this export GOOGLE_CLOUD_REGION='us-central1' # If you change this, make sure the region is supported.
-
Build and deploy the service to Cloud Run:
In Cloud Shell, execute the following command to name the Cloud Run service:
export SERVICE_NAME='gemini-streamlit-app' # This is the name of our Application and Cloud Run service. Change it if you'd like.
In Cloud Shell, execute the following command:
gcloud run deploy "$SERVICE_NAME" \ --port=8080 \ --source=. \ --allow-unauthenticated \ --region=$GOOGLE_CLOUD_REGION \ --project=$GOOGLE_CLOUD_PROJECT \ --set-env-vars=GOOGLE_CLOUD_PROJECT=$GOOGLE_CLOUD_PROJECT,GOOGLE_CLOUD_REGION=$GOOGLE_CLOUD_REGION
On successful deployment, you will be provided a URL to the Cloud Run service. You can visit that in the browser to view the Cloud Run application that you just deployed. Choose the functionality that you would like to check out and the application will prompt the Gemini API in Vertex AI and display the responses.
Congratulations!