# VertexAI

## Integrate VertexAI

The following applies to the managed integration setup. For LLM integration of Google VertexAI, [follow here](https://docs.nlx.ai/platform/nlx-platform-guide/integrations/types/llm-services/google-vertex-ai) instead.

1. [Enable Vertex AI APIs in your Google Cloud project](https://cloud.google.com/vertex-ai/docs/start/cloud-environment)
2. Create a [service account](https://cloud.google.com/iam/docs/service-account-overview) in the Google Cloud project
3. [Create a custom service account for Vertex A](https://cloud.google.com/vertex-ai/docs/general/custom-service-account)
4. Assign the Vertex AI Service Agent role to the service account from step 2
5. [Create a service account key](https://cloud.google.com/iam/docs/keys-create-delete#console) in JSON format for NLX and download it
6. Copy/paste the entire JSON text into the NLX field

{% hint style="info" %}
At any time, you may edit or delete your Google integration by expanding the integration name and selecting the edit or delete links. 
{% endhint %}

***

## Using VertexAI managed integation

To successfully use your Google integration with conversations created in your workspace, be sure to complete the following:

* [ ] create a [flow](https://docs.nlx.ai/platform/nlx-platform-guide/flows-and-building-blocks/overview)
* [ ] add a [*Generative Journey* node in *Agentic* mode](https://docs.nlx.ai/platform/nlx-platform-guide/flows-and-building-blocks/overview/nodes#generative-journey) and attach your Google integration as a Tool, or use a [*Data request* node in *Built-in* mode](https://docs.nlx.ai/platform/nlx-platform-guide/flows-and-building-blocks/overview/nodes#data-request) with your integration assigned and payload fields completed
* [ ] create a [build & deploy](https://docs.nlx.ai/platform/nlx-platform-guide/ai-applications/types/core#deployment)