Smoke-Test a RAG Pipeline on Databricks Lakebase

Run the full RAG pipeline on a small demo corpus of 25 passages. Use it to check your Databricks setup before you build with real data.

Level
Beginner
Duration
About 20 min
Cost
Free tier
Runs on a vendor free plan.
Technologies
RAGpgvectorDatabricks LakebaseDatabricks Apps

What you will build

  • The same RAG pipeline as the SEC filings lab, on 25 invented passages
  • A Lakebase Postgres project with pgvector enabled
  • A small RAG app deployed to Databricks Apps

Prerequisites

  • A Databricks Free Edition account
  • The Databricks CLI, logged in with databricks auth login
  • Python 3.9 or newer with pip

Run it

Install once, then launch the lab. Preview the steps first with the dry run. Remove everything when you finish.

pip install 'labagent[rag]'
databricks auth login

# preview the steps without changing anything
labagent launch rag-lakebase --name demo --dry-run

# launch the lab (safe to re-run, it resumes where it stopped)
labagent launch rag-lakebase --name demo

# remove only what the lab created
labagent destroy rag-lakebase --name demo

Steps

  1. 1

    Preflight

    Check your login, the serving endpoints, and the Free Edition project limit.

  2. 2

    Create the Lakebase project

    Start the Postgres project that holds the vectors.

  3. 3

    Load the demo corpus

    Chunk the passages, embed them, and load them.

  4. 4

    Build the indexes

    Add vector, full-text and metadata indexes.

  5. 5

    Deploy the app

    Publish the Databricks App and open it.

FAQ

Why use a demo corpus?+
It is a smoke test. If this lab runs, your login, serving endpoints and project limit are set up correctly.
Is the data real?+
No. The 25 passages are invented. Use the SEC filings lab for real documents.
Does this lab cost money?+
It runs on Databricks Free Edition. Free Edition allows one Lakebase project, and apps stop after 24 hours.

Pick how you want to use this lab

Run it free

Use the commands above on your own machine and account.

Go to the commands

Get team access

Private environments for a class or team.

Send us details

Book a corporate workshop

A 30-minute call to scope training for your team.

Book a call
Team access

Run this lab for your team

Tell us the class size and the date. We reply within one business day.

We respect your privacy. No spam, ever.

Related labs

Free tierIntermediate

Build a RAG App with pgvector on Databricks Lakebase

Build a retrieval-augmented generation app over real SEC 10-K filings. It has hybrid search, company and year filters, cited answers, and a quality gate that blocks a bad deploy.

About 45 min
RAGpgvectorDatabricks LakebaseDatabricks AppsPostgreSQL
View lab
Free tierBeginner

Deploy a Text-to-SQL AI Agent on Databricks Apps

Deploy the open-source db-agent to Databricks Apps over a built-in sample dataset. The lab then asks a test question through the live app to confirm it works.

About 20 min
Text-to-SQLAI agentsDatabricks AppsUnity CatalogSQL warehouse
View lab