Tutorials - LanceDB

Every tutorial is one page in the sidebar, grouped by what it builds. The documentation explains how a feature works; these show it doing something. Examples marked as notebooks live in the vectordb-recipes repository and are runnable in Colab; the rest are written up here.

Where to start

Search

Vector, multi-vector, hybrid and full-text retrieval.

RAG

Retrieval-augmented generation and agent applications.

Feature engineering

Deriving columns and materialized views.

Training

Curating data and training models directly on a table.

The features these use

Feature	What it covers
Vector search	Similarity search, distance metrics, and tuning it.
Full-text search	Keyword search over text columns.
Hybrid search	Keyword and vector search combined.
Multi-vector search	Several embeddings per document.
Reranking	Reordering results to improve the top-k.
Feature engineering	Deriving columns and tables from data already stored.
Materialized views	A table defined by a query, brought up to date by each refresh.
Training	Reading a table into a data loader.