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
The following guide walks you through deploying an version of the application in the development
Environment so you can chat with it through the
💬 Review UI.
The default RAG Studio template ships with a fully functioning application. You can deploy the code as-is. See Create versions of your RAG application to iterate on the app’s quality to understand how to create a new
This step will run the
🗃️ Data Processor, package the
🔗 Chain into a Unity Catalog model, and then deploy the
🔗 Chain to Model Serving.
Deploy the application to your workspace by running the following command in your console. This step will take approximately 15-30 minutes.
./rag create-rag-version -e dev
Congrats! You have deployed a fully functioning RAG application, complete with logging, the ability to collect feedback from users and LLM-Judges, and automated quality/cost/latency metric computation.
While we are only exploring this application for the purposes of getting started with RAG Studio, this application is ready to be deployed to your production environment.
In the console, you will see output similar to below. Open the URL in your web browser to open the
💬 Review UI.
...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/dev
You can now interact with the RAG application!