Databricks
Configure Databricks Model Serving to access foundation models and custom models through Braintrust.
Authentication
Choose between two authentication methods:
- Personal Access Token (PAT): Use a Databricks personal access token for authentication
- Service Principal OAuth: Use OAuth with a service principal for authentication
Configuration
Field | Description |
---|---|
API base URL URL String | Required. Your Databricks workspace URL in the format https://{workspace-name}.cloud.databricks.com . Documentation |
Authentication typepat | service_principal_oauth | Optional. Choose between personal access token or service principal OAuth. Default is pat . Documentation |
Secret String | Required if using pat auth type. Your Databricks personal access token. Documentation |
Client ID String | Required if using service_principal_oauth auth type. Client ID for service principal authentication. Documentation |
Client Secret String | Required if using service_principal_oauth auth type. Client secret for service principal authentication. Documentation |
Models
Databricks provides access to several foundation models through Model Serving.
Foundation models
- Meta Llama 3.1 70B Instruct
- Meta Llama 3.1 8B Instruct
- Mistral 7B Instruct
- Mixtral 8x7B Instruct
- MPT-7B Instruct
Custom models
Deploy your own fine-tuned models through Databricks Model Serving.
Setup requirements
- Databricks Workspace: Ensure you have access to a Databricks workspace
- Model Serving: Enable Model Serving in your workspace
- Authentication: Set up either PAT or service principal authentication
- Model Endpoints: Deploy the models you want to use as serving endpoints
Endpoint configuration
Configure the following for model endpoints in Databricks.
- Serving Endpoint Name: Use this as the model name in Braintrust
- Endpoint URL: Automatically constructed from your workspace URL
- Authentication: Uses the configured authentication method