Databricks
Connect to models hosted on Databricks Model Serving.
Configuration
| Field | Required | Example |
|---|---|---|
| Application Name | Yes | my-databricks-app |
| Base URL | Yes | https://adb-<workspace-id>.<region>.azuredatabricks.net/serving-endpoints |
| Model Name | Yes | databricks-meta-llama-3-1-405b-instruct |
| API Key | Yes | Your Databricks token |
Getting Your Credentials
- Log in to your Databricks workspace
- Click your username → User Settings
- Go to Developer → Access tokens
- Generate a new token
Base URL Format
https://adb-<workspace-id>.<region>.azuredatabricks.net/serving-endpoints
Replace:
<workspace-id>: Your Databricks workspace ID<region>: Your region (e.g.,westus,eastus2)
Popular Models
Models depend on your Databricks workspace configuration. Common options include:
| Model | Description |
|---|---|
databricks-meta-llama-3-1-405b-instruct | Llama 3.1 405B |
databricks-meta-llama-3-1-70b-instruct | Llama 3.1 70B |
databricks-dbrx-instruct | Databricks DBRX |
For more information, visit the Databricks Model Serving Documentation and Foundation Models Overview.
Advanced Parameters
| Parameter | Type | Description |
|---|---|---|
max_tokens | integer | Maximum tokens |
temperature | float | Randomness |
top_p | float | Nucleus sampling |
top_k | integer | Top-k sampling |
Setup Steps
- Navigate to AI Applications → New Application
- Select Model Providers tab
- Click Databricks
- Enter your Application Name
- Enter your Base URL (Databricks serving endpoint)
- Enter your Model Name
- Enter your API Key (Databricks access token)
- Configure Advanced Settings (optional)
- Click Test Response to verify (optional)
- Review and submit