Vector Search and RAG with pgvector on Lakebase

Builds a semantic retrieval layer on pgvector inside Lakebase Postgres, taught against a live "Ask the docs" app that Classroom Setup deploys. Following the lecture-demo pattern, learners decide when pgvector beats Databricks AI Search, design a document/chunk schema, choose and build HNSW and IVFFlat indexes, generate embeddings in batch with ai_query(), and write a hybrid search combining vector similarity, a metadata filter, and full-text ranking (ts_rank_cd cover-density) in one query. An optional closing section surveys Lakebase Search (Beta) and its lakebase_text (BM25) and lakebase_vector (ANN) extensions.

Skill Level

Associate

Duration

Prerequisites

The content was developed for participants with these skills/knowledge/abilities:

• Comfort with Python and SQL, plus basic embeddings/RAG concepts

• Familiarity with Postgres concepts (tables, indexes, extensions, foreign keys)

• Ability to connect to Lakebase and enable the pgvector extension

Self-Paced

Custom-fit learning paths for data, analytics, and AI roles and career paths through on-demand videos

Customer registration Partner registration

See all our registration options

Registration options

Databricks has a delivery method for wherever you are on your learning journey

Self-Paced

Custom-fit learning paths for data, analytics, and AI roles and career paths through on-demand videos

Instructor-Led

Public and private courses taught by expert instructors across half-day to two-day courses

Blended Learning

Self-paced and weekly instructor-led sessions for every style of learner to optimize course completion and knowledge retention. Go to Subscriptions Catalog tab to purchase

Purchase now

Skills@Scale

Comprehensive training offering for large scale customers that includes learning elements for every style of learning. Inquire with your account executive for details

Upcoming Public Classes

Migrating to Lakebase

Migrates an existing Postgres workload to Lakebase. Following the lecture-demo pattern, learners use a decision matrix to confirm fit, assemble a pre-migration checklist, execute a pg_dump/pg_restore migration (and its alternatives), and design a cutover strategy with validation queries that catch subtle drift.

Paid & Subscription

Lab

Associate

Production Operations: HA, Read Replicas, Instant Restore

Hardens Lakebase for production. Following the lecture-demo pattern and framed around an incident, learners configure High Availability across zones, add read replicas and route analytical traffic to them, tune the restore window, and recover from data loss with a point-in-time branch.

Paid & Subscription

Lab

Associate

AI Agents and Long-Term Memory on Lakebase

Gives AI agents durable memory on Lakebase. Following the lecture-demo pattern, learners distinguish the three memory categories, choose among framework paths, persist a LangGraph conversation with a checkpointer, resume a thread after a restart, isolate per-tier state with branches, and recall facts across threads with a semantic store.

Paid & Subscription

Lab

Associate