mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-13 23:32:27 +00:00
Brendan Clement
305dffe27b
The earlier change dropped every statement that a materialized view's
source needs stable row ids, because main no longer requires them. That
holds for the local SDK only. Sophon main creates a view through SQL by
default with the creation checks of its pinned lancedb (00f5dd6f), which
predates #4373 and still rejects a source without stable row ids.
The refresh and management pages now say a local view needs no special
source and a deployment may still require stable row ids, and the
architecture, limits, table and database pages note that requirement.
The summaries say a refresh brings a view up to date instead of saying
it recomputes it, since a deployment may reconcile changes rather than
rebuild.
43 lines
2.0 KiB
Plaintext
43 lines
2.0 KiB
Plaintext
---
|
|
title: "Tutorials"
|
|
sidebarTitle: "Overview"
|
|
description: "Worked examples of building with LanceDB, grouped by what they build."
|
|
---
|
|
|
|
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](https://github.com/lancedb/vectordb-recipes) repository and
|
|
are runnable in Colab; the rest are written up here.
|
|
|
|
## Where to start {#start}
|
|
|
|
<CardGroup cols={2}>
|
|
<Card title="Search" icon="magnifying-glass" href="/tutorials/search/hybrid-search-beir">
|
|
Vector, multi-vector, hybrid and full-text retrieval.
|
|
</Card>
|
|
<Card title="RAG" icon="robot" href="/tutorials/agents/contextual-rag">
|
|
Retrieval-augmented generation and agent applications.
|
|
</Card>
|
|
<Card title="Feature engineering" icon="wand-magic-sparkles" href="/tutorials/feature-engineering/feature-engineering-101">
|
|
Deriving columns, materialized views, experimenting on branches.
|
|
</Card>
|
|
<Card title="Training" icon="graduation-cap" href="/training/object-detection">
|
|
Curating data and training models directly on a table.
|
|
</Card>
|
|
</CardGroup>
|
|
|
|
## The features these use {#read-the-docs}
|
|
|
|
| Feature | What it covers |
|
|
|:--------|:------------|
|
|
| [Vector search](/search/vector-search) | Similarity search, distance metrics, and tuning it. |
|
|
| [Full-text search](/search/full-text-search) | Keyword search over text columns. |
|
|
| [Hybrid search](/search/hybrid-search) | Keyword and vector search combined. |
|
|
| [Multi-vector search](/search/vector-search) | Several embeddings per document. |
|
|
| [Reranking](/reranking) | Reordering results to improve the top-k. |
|
|
| [Feature engineering](/feature-engineering) | Deriving columns and tables from data already stored. |
|
|
| [Materialized views](/management/materialized-view) | A table defined by a query, brought up to date by each refresh. |
|
|
| [Training](/training/data-loading) | Reading a table into a data loader. |
|