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

​

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

1. Databricks Workspace: Ensure you have access to a Databricks workspace
2. Model Serving: Enable Model Serving in your workspace
3. Authentication: Set up either PAT or service principal authentication
4. Model Endpoints: Deploy the models you want to use as serving endpoints

​

Endpoint configuration

Configure the following for model endpoints in Databricks.

1. Serving Endpoint Name: Use this as the model name in Braintrust
2. Endpoint URL: Automatically constructed from your workspace URL
3. Authentication: Uses the configured authentication method

​

Additional resources

• Databricks Model Serving Documentation
• Foundation Model APIs
• Authentication Guide
• Model Serving Pricing