Metadata and attribute filtering for AI search
Starting with 17.4, the AI assistant can now constrain content search by document attributes — for example content type, language, or folder path — in addition to keywords. Editors can ask natural-language questions such as “find news articles under products” and get results filtered and constrained by those attributes.
How it works
-
Metadata generation. Metadata are generated upon the ingestion of a content item into the RAG. See below for the default attributes that get stored in the RAG, see also here on how to alter what goes in your RAG.
-
Filterable attributes catalog. The platform informs the AI which metadata attributes are available for using in searches.
-
Attribute-aware search. The assistant uses those attributes to narrow results, alone or together with keyword search, when the user requests it.
Attribute filtering is under active development. Exact-value filters work, for example, you can ask the assistant to find docs with locale 'en'. Friendly names such as "English docs" are not mapped to locale codes yet. Date ranges can't be used as filters in 17.4. More metadata will become filterable in future releases
Default metadata attributes
These attributes are indexed by default and can be used when filtering search results:
| Field | Meaning | How to use in assistant |
|---|---|---|
id | Document identifier (uuid) | Literally, "find document with id [uuid]" |
nodeName | Repository node name | Literally, "find document with name [name]" |
contentCategory | Content category | "find Documents [Pages, Resource bundles"] |
displayName | Display name shown in the CMS | "find document named [any term in the display name] |
createdAt | Creation time | Not supported for filtering in 17.4 |
lastModifiedAt | Last modification time | Not supported for filtering in 17.4 |
publishedAt | Publication time | Not supported for filtering in 17.4 |
translationId | Translation group identifier (uuid) | Reserved: will be used with translation support |
locale | Language / locale | Currently use literally, "find docs with locale 'de'" |
contentType | Document type (namespace-qualified name) | Use content type friendly name, e.g "find Banners" |
path | Folder path in the repository | Full or partial path match, e.g. "find News under 'archive' |
Optional attributes with no value are left out of the index rather than stored as empty strings, in an effort to treat “missing” values in a consistent way across all supported vector stores.
Note that a re-indexing of the RAG is needed if you are on pre 17.4 version. See here for more information.