This feature is in Private Preview. To try it, reach out to your Databricks contact.
Looking for a different RAG Studio doc? Go to the RAG documentation index
This document walks you through configuring the required infrastructure to create a RAG Studio application:
You will need these values when creating your RAG Application, so we suggest using a scratch pad, such as the one below, to write down these values as you walk through the steps below. These values will be requested from you when you initialize your application.
Select a Databricks workspace with Unity Catalog and serverless enabled in a supported region. Note the URL of the workspace to use when configuring the application e.g.,
RAG Studio creates all assets within a Unity Catalog schema.
Data Editorpermissions for your Databricks account to the catalog / schema using SQL or the Catalog Explorer
If you created a new catalog/schema, you already have the necessary permissions.
GRANT USE SCHEMA, APPLY TAG, MODIFY, READ VOLUME, REFRESH, SELECT, WRITE VOLUME, CREATE FUNCTION, CREATE MATERIALIZED VIEW, CREATE MODEL, CREATE TABLE, CREATE VOLUME ON SCHEMA my_schema TO `email@example.com`;
Create a new endpoint using the UI or Python SDK or select an existing endpoint.
This approach is a temporary workaround to enable your app’s chain, which is hosted on Model Serving to access to the vector search indexes created by RAG Studio. In the future, this will not be needed.
Create a personal access token (PAT) that has access to the Unity Catalog schema you created above.
Option 1: Create a PAT token for your user account by following these steps. .. note :: Using a PAT token is only suggested for development. Using a service principal is strongly recommended for production.
Save the PAT to a secret scope
databricks secrets create-scope <scope-name> databricks secrets put-secret <scope-name> <secret-name>
RAG Studio natively integrates with Databricks Model Serving for access to Foundational Models. This integration is used for RAG Studio’s
🤖 LLM Judge and within your
🔗 Chain and
🗃️ Data Processor.
You need access to 2 types of models:
Optionally, you can also configure:
Open Source models hosted with Databricks Foundation Model provisioned throughput.
Follow the steps for deploying a provisioned throughput model to load any supported open source model with a
External Models such as (Azure) OpenAI.
Follow the steps to configure external models in Databricks Model Serving to load any supported open source model with a