You need to enable the Vertex AI API and set up the Google Application Default Credentials.

​
Chat model

We recommend configuring Claude 3.5 Sonnet as your chat model.
config.yaml
models:
  - name: Claude 3.5 Sonnet
    provider: vertexai
    model: claude-3-5-sonnet-20240620
    env:
      projectId: <PROJECT_ID>
      region: us-east5

​
Autocomplete model

We recommend configuring Codestral or code-gecko as your autocomplete model.
config.yaml
models:
  - name: Codestral (Vertex AI)
    provider: vertexai
    model: codestral
    roles:
      - autocomplete
    env:
      projectId: <PROJECT_ID>
      region: us-central1

​
Embeddings model

We recommend configuring text-embedding-004 as your embeddings model.
config.yaml
models:
  - name: Text Embedding-004
    provider: vertexai
    model: text-embedding-004
    env:
      projectId: <PROJECT_ID>
      region: us-central1
    roles:
      - embed

​
Reranking model

Vertex AI currently does not offer any reranking models. Click here to see a list of reranking model providers.

​
Express mode

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