RAG Studio
Preview
This feature is in Private Preview. To try it, reach out to your Databricks contact.
Important
To navigate RAG Studio documentation, return to this index page. Private preview documentation doesn’t include navigation links in the side panel.
Overview
RAG Studio provides tools and an opinionated workflow for developing, evaluating, and iterating on Retrieval-Augmented Generation (RAG) applications in order to build apps that deliver consistent, accurate answers. RAG Studio is built on top of MLflow and is tightly integrated with Databricks tools and infrastructure.
Read more about RAG Studio’s product philosophy about developing RAG Applications.
Development workflow
The RAG Studio approach to improving quality is to make it easy for developers to quickly:
Adjust various knobs throughout the RAG application’s
📥 Data Ingestor
,🗃️ Data Processor
,🔍 Retriever
, and🔗 Chain
to create a newVersion
Test the
Version
offline with a📖 Evaluation Set
and🤖 LLM Judge
sDeploy the
Version
in the💬 Review UI
to collect feedback from🧠 Expert Users
Review
📈 Evaluation Results
to determine if the changes had a positive impact of quality, cost, and/or latencyInvestigate the details in the
🗂️ Request Log
and👍 Assessment & Evaluation Results Log
to identify hypotheses for how to improve quality, cost, and/or latencyIf needed, collect additional feedback on specific
🗂️ Request Log
s from🧠 Expert Users
using the💬 Review UI
Repeat until you reach your quality/cost/latency targets!
Deploy the application to production
Note
Importantly, the same development workflow above applies to production traffic! The RAG Studio data model for logs, assessments, and metrics is fully unified between development and production.
Tutorials
Tutorials demonstrate how to do the key developer workflows mentioned above, based on the fully featured sample RAG Application included with RAG Studio - a Documentation Q&A bot on the Databricks documentation.
Important
Databricks suggests getting started by going through these tutorials. Following tutorials #1 and #2 will deploy a fully functioning chat UI for the sample application. While you can do these tutorials in any order, they are designed to be done sequentially.
Additional reference
These documents provide additional reference material that is linked from the above guides.