Step 1: Set up your project and source repository

In this step, you set up your Google Cloud project and Python environment in Cloud Shell, enable the required APIs, and assign the Identity and Access Management (IAM) roles that you need to complete the tutorial. You also set up a GitHub repository containing the app source files by forking and cloning the GoogleCloudPlatform/generative-ai repository. After completing these steps, you verify the setup by running and testing the app locally in Cloud Shell.

Before you begin

1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

2. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

3. Make sure that billing is enabled for your Google Cloud project.

4. Enable the Vertex AI, Compute Engine, Artifact Registry, Identity-Aware Proxy (IAP), Cloud Run Admin, Cloud Build, Identity and Access Management (IAM) API, and Gemini for Google Cloud APIs.

   Enable the APIs

5. Make sure that you have the following role or roles on the project: Vertex AI User, Cloud Build Editor, Cloud Run Admin, Artifact Registry Admin, Compute Load Balancer Admin, Service Account User, IAP Policy Admin, OAuth Config Editor, and Service Usage Admin.

   Check for the roles

   1. In the Google Cloud console, go to the IAM page.

      Go to IAM
   2. Select the project.

   3. In the Principal column, find all rows that identify you or a group that you're included in. To learn which groups you're included in, contact your administrator.

   4. For all rows that specify or include you, check the Role colunn to see whether the list of roles includes the required roles.

   Grant the roles

   1. In the Google Cloud console, go to the IAM page.

      Go to IAM
   2. Select the project.
   3. Click Grant access.

   4. In the New principals field, enter your user identifier. This is typically the email address for a Google Account.

   5. In the Select a role list, select a role.
   6. To grant additional roles, click Add another role and add each additional role.
   7. Click Save.

6. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   Go to project selector

7. Make sure that billing is enabled for your Google Cloud project.

8. Enable the Vertex AI, Compute Engine, Artifact Registry, Identity-Aware Proxy (IAP), Cloud Run Admin, Cloud Build, Identity and Access Management (IAM) API, and Gemini for Google Cloud APIs.

   Enable the APIs

9. Make sure that you have the following role or roles on the project: Vertex AI User, Cloud Build Editor, Cloud Run Admin, Artifact Registry Admin, Compute Load Balancer Admin, Service Account User, IAP Policy Admin, OAuth Config Editor, and Service Usage Admin.

   Check for the roles

   1. In the Google Cloud console, go to the IAM page.

      Go to IAM
   2. Select the project.

   3. In the Principal column, find all rows that identify you or a group that you're included in. To learn which groups you're included in, contact your administrator.

   4. For all rows that specify or include you, check the Role colunn to see whether the list of roles includes the required roles.

   Grant the roles

   1. In the Google Cloud console, go to the IAM page.

      Go to IAM
   2. Select the project.
   3. Click Grant access.

   4. In the New principals field, enter your user identifier. This is typically the email address for a Google Account.

   5. In the Select a role list, select a role.
   6. To grant additional roles, click Add another role and add each additional role.
   7. Click Save.

Set up the source repository

1. In GitHub, fork the GoogleCloudPlatform/generative-ai repository. Learn more about forking repositories in GitHub.

   Fork the repository in GitHub

2. In the Google Cloud console, activate Cloud Shell.

   Activate Cloud Shell

   At the bottom of the Google Cloud console, a Cloud Shell session starts and displays a command-line prompt. Cloud Shell is a shell environment with the Google Cloud CLI already installed and with values already set for your current project. It can take a few seconds for the session to initialize.

3. In the Cloud Shell terminal, run the following commands to clone the forked repository and set the gemini-streamlit-cloudrun directory as the active directory:
   

   cd
   git clone https://github.com/GIT_USER_NAME/FORK_NAME/
   cd FORK_NAME/gemini/sample-apps/gemini-streamlit-cloudrun

   Replace the following:

   • GIT_USER_NAME: Your GitHub username.
   • FORK_NAME: The name of the fork repository that you just created in GitHub.

Set up the environment and dependencies

1. In the Cloud Shell terminal, run the following commands to set up a virtual environment:

   python3 -m venv gemini-streamlit
   source gemini-streamlit/bin/activate
   pip install -r requirements.txt
   

2. Run the following commands to set the environment variables needed for Vertex AI initialization:

   export GCP_PROJECT=$GOOGLE_CLOUD_PROJECT
   export GCP_REGION='us-central1' 
   

Test the app locally

1. From the Cloud Shell terminal, run the app by running the following command:

   streamlit run app.py \
     --browser.serverAddress=localhost \
     --server.enableCORS=false \
     --server.enableXsrfProtection=false \
     --server.port 8080
   

2. To preview the app, in the Cloud Shell taskbar, click , and then click Preview on port 8080.

   For more information about using the Web Preview feature, see Preview web apps.