Custom metadata

You can attach custom metadata to web pages using HTML <meta> tags. AI Search extracts metadata from the <head> section of each crawled page.

Before custom metadata can be extracted, you must define a schema in your AI Search configuration.

Add metadata to web pages

Add <meta> tags using either the name or property attribute:

<!DOCTYPE html>
<html>
	<head>
		<meta name="title" content="Getting Started Guide" />
		<meta name="description" content="Learn how to set up the application" />
		<meta property="og:title" content="Getting Started Guide" />
		<meta property="og:image" content="https://example.com/og-image.png" />
		<meta name="category" content="documentation" />
		<meta name="version" content="2.5" />
		<meta name="is_public" content="true" />
	</head>
	<body>
		<!-- Page content -->
	</body>
</html>

Recognized fields

For the following fields, AI Search knows which meta tags to extract from. You must still define these in your schema to enable extraction.

Field	Source
`title`	`<meta name="title">` or `<meta property="og:title">`
`description`	`<meta name="description">` or `<meta property="og:description">`
`image`	`<meta property="og:image">`

When both a standard meta tag and an Open Graph tag are present, the standard meta tag takes precedence.

How metadata extraction works

When the crawler fetches a page:

All <meta> tags with name or property attributes are parsed from the <head> section.
Tag names are matched against your schema (case-insensitive).
The content attribute value is cast to the configured data type.
Extracted metadata is stored alongside the cached HTML.
On subsequent processing, metadata flows into the vector index.

Boolean value parsing

For boolean fields, the following values are accepted (case-insensitive):

True values	False values
`true`, `1`, `yes`	`false`, `0`, `no`

Any other value is treated as invalid and the field is omitted.