Back to Continue

How to Configure Vertex AI with Continue

docs/customize/model-providers/top-level/vertexai.mdx

1.5.451.7 KB
Original Source
<Info> Enable the [Vertex AI API](https://console.cloud.google.com/marketplace/product/google/aiplatform.googleapis.com) and set up [Google Application Default Credentials](https://cloud.google.com/docs/authentication/provide-credentials-adc) </Info>

Configuration

<Tabs> <Tab title="YAML"> ```yaml title="config.yaml" name: My Config version: 0.0.1 schema: v1
models:
  - name: <MODEL_NAME>
    provider: vertexai
    model: <MODEL_ID>
    env:
      projectId: <PROJECT_ID>
      region: us-east5
```
</Tab>
<Tab title="JSON (Deprecated)">
```json title="config.json"
{
  "models": [
    {
      "title": "<MODEL_NAME>",
      "provider": "vertexai",
      "model": "<MODEL_ID>",
      "projectId": "[PROJECT_ID]",
      "region": "us-east5"
    }
  ]
}
```
</Tab>
</Tabs>

How to Enable Vertex AI Express Mode

You can use Vertex AI in express mode by only providing an API Key. Only some Gemini models are supported in express mode for now.

<Tabs> <Tab title="YAML"> ```yaml title="config.yaml" name: My Config version: 0.0.1 schema: v1
models:
  - name: <MODEL_NAME>
    provider: vertexai
    model: <MODEL_ID>
    apiKey: <YOUR_GOOGLE_CLOUD_API_KEY>
```
</Tab>
<Tab title="JSON (Deprecated)">
```json title="config.json"
{
  "models": [
    {
      "title": "<MODEL_NAME>",
      "provider": "vertexai",
      "model": "<MODEL_ID>",
      "apiKey": "<YOUR_GOOGLE_CLOUD_API_KEY>",
    }
  ]
}
```
</Tab>
</Tabs>