> ## Documentation Index > Fetch the complete documentation index at: https://rasa.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Set Up Your Agent on GCP > Before you begin, ensure you've finished installing Rasa Pro on Google Cloud Platform: > [!NOTE] > > Before you begin, ensure you've finished installing Rasa Pro on Google Cloud Platform: > [Installation Guide](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-intro.md) ## Recommended Next Steps Now that you have successfully deployed Rasa Pro on GCP, you can proceed with getting a live Rasa agent in place that you can interact with. **Plan of Action:** * Confirm Your Agent Runs Locally * Upload Trained Model to GCP * Run Your Deployed Rasa Agent *** ## Confirm Your Agent Runs Locally If you already have a Rasa agent, make sure it trains and runs successfully on your local machine. ### Don’t Have an Agent Yet? If you already have a Rasa agent you’ve built, you can skip this section and go directly to [Upload Trained Model to GCP](https://rasa.com/docs/learn/deployment/gcp/gcp-playbook-setup-agent.md#upload-trained-model-to-gcp). If not, feel free to use one of our pre-built **Starter Packs**. These agents come ready-made for specific industries, and you can run them as-is or customize them for your own use case. Download the latest release of one of the following: * [Starter Pack - Insurance](https://github.com/rasa-customers/starterpack-insurance-en/releases) * [Starter Pack - Retail Banking](https://github.com/rasa-customers/starterpack-retail-banking-en/releases/) * [Starter Pack - Telecom](https://github.com/rasa-customers/starterpack-telco-en/releases) ### Run Your Starter Pack Locally Once you have downloaded your Starter Pack, follow the corresponding instructions linked below to train and run your Rasa agent locally: * [Instructions - Insurance](https://learning.rasa.com/rasa-starter-packs/insurance/) * [Instructions - Retail Banking](https://learning.rasa.com/rasa-starter-packs/retail-banking/) * [Instructions - Telecom](https://learning.rasa.com/rasa-starter-packs/telecom/) > [!NOTE] > > Make sure your local agent's `endpoints.yaml` matches the one in the deployed agent, so that the agent behaves identically in both environments. You can see the default values set by the deployment playbook [here](https://github.com/RasaHQ/rasa-deployment-playbooks/blob/main/gcp/rasa/assistant/values.template.yaml). > If you want to change the configuration of models for the deployed agent, change `gcp/rasa/assistant/values.yaml` and rerun your `helm upgrade` command. ## Upload Trained Model to GCP After you have successfully run your Rasa agent locally, you can now move it to the cloud to share with others. This consists of two steps: 1. Upload the Rasa Model 2. Restart Rasa Kubernetes Pod ### Upload the Rasa Model Navigate to your Rasa project directory ```bash theme={null} cd /path/to/your/rasa/project ``` Authenticate with Google Cloud ```bash theme={null} gcloud auth login ``` Upload the model to your bucket ```bash theme={null} gsutil cp models/ gs://$MODEL_BUCKET/models.tar.gz ``` Verify upload ```bash theme={null} gsutil ls gs://$MODEL_BUCKET/ ``` #### Alternatively, via Google Cloud Console UI: 1. Go to your Google Cloud Console UI 2. Make sure you have the same project selected that you used to create your deployment 3. Go to **Cloud Storage > Buckets** 4. Select the bucket that you assigned to `BUCKET_NAME_ENTROPY` during the deployment process: `gcp/setup/environment-variables.sh` * Example: `rasa-xbuc-ab-se-x2-rasa-model` * **Tip:** Do not select the bucket that ends with `-studio` 5. Click **Upload** to upload your local `models.tar.gz` into the bucket ### Restart Rasa Restart Rasa to create a new pod which will pull your new model from your bucket. Authenticate to your GCP cluster ```bash theme={null} gcloud container clusters get-credentials $NAME --region $REGION --project $PROJECT_ID ``` > [!NOTE] > > If you changed the Kubernetes deployment name from the default `rasa`, use your custom deployment name in place of `rasa` in the commands below. Restart deployments ```bash theme={null} kubectl -n $NAMESPACE rollout restart deployment rasa ``` To check if the Rasa pod is up and running yet, run the following command and see if the status of the new Rasa pod is "Running". ```bash theme={null} kubectl -n $NAMESPACE rollout status deployment/rasa # or kubectl -n $NAMESPACE get pods -w ``` **Tip:** You can view info, warning and error messages in your pod logs: View the pod's logs ```bash theme={null} kubectl -n rasa logs ``` #### Alternatively, via Google Cloud Console UI: 1. Go to your Google Cloud Console UI 2. Make sure you have the same project selected that you used to create your deployment 3. Go to **Kubernetes Engine > Workloads** 4. Click on the `rasa` workload 5. In **Deployment Details menu:** Actions > Scale > Edit Replicas > Replicas: `0` 6. Press **Scale** 7. Wait until the pod has been terminated 8. In **Deployment Details menu:** Actions > Scale > Edit Replicas > Replicas: `1` 9. Press **Scale** You have now successfully updated the model and restarted your Rasa Pro environment. Next, you’ll set up a simple front-end web page to try out your agent. ## Interact With Your Rasa Agent ### Interact With Your Rasa Agent from Your Browser Up to now, you’ve been running and interacting with your Rasa agent **locally** from your browser, connected to your **local instance** of Rasa Pro. Now, you'll update the connection so your browser interacts with your **deployed (cloud) instance** of Rasa Pro. This way, you’ll be testing your Rasa agent running in the cloud rather than on your local machine. 1. In your Starter Pack project folder, go to the `chatwidget` directory 2. Open up the `index.html` file in a text editor 3. Replace ```html theme={null}