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 tutorial walks you through deploying your RAG Application to the Reviewers
Environment in order to allow
🧠 Expert Users to test the application and provide feedback.
If you did not already run this command in Initialize a RAG Application, run the following command to initialize these
Environments. This command takes about 10 minutes to run.
See Infrastructure and Unity Catalog assets created by RAG Studio for details of what is created in your Workspace and Unity Catalog schema.
Run the following command to deploy the version to the Reviewers
Environment. This command takes about 10 minutes to run.
./rag deploy-chain -v 1 -e reviewers
In the console, you will see output similar to below. Open the URL in your web browser to open the
💬 Review UI. You can share this URL with your
🧠 Expert Users.
...truncated for clarity of docs... ======= Task deploy_chain_task: Your Review UI is now available. Open the Review UI here: https://<workspace-url>/ml/review/model/catalog.schema.rag_studio_databricks-docs-bot/version/1/environment/reviewers
Add permissions to the deployed version so your
🧠 Expert Userscan access the above URL.
Give the Databricks user you wish to grant access
the MLflow Experiment
the Model Serving endpoint
the Unity Catalog Model
🚧 Roadmap 🚧 Support for adding any corporate SSO to access the
💬 Review UIe.g., no requirements for a Databricks account.
Now, every time a
🧠 Expert Userschats with your RAG Application, the
🗂️ Request Logand
👍 Assessment & Evaluation Results Logwill be populated.