Vertex AI Cached Content

Docs > DDSQL Reference > Data Directory > Vertex AI Cached Content

Vertex AI Cached Content is a Google Cloud resource that stores and manages cached data generated by Vertex AI models and pipelines. It helps improve performance and reduce costs by reusing previously computed results, such as model predictions or dataset transformations, instead of recalculating them. This resource supports efficient retrieval and sharing of cached artifacts across Vertex AI workflows.

gcp.aiplatform_cached_content

Fields

ID	Type	Data Type	Description
_key	core	string
ancestors	core	array<string>
contents	core	json	Optional. Input only. Immutable. The content to cache
create_time	core	timestamp	Output only. Creation time of the cache entry.
datadog_display_name	core	string
expire_time	core	timestamp	Timestamp of when this resource is considered expired. This is always provided on output, regardless of what was sent on input.
gcp_display_name	core	string	Optional. Immutable. The user-generated meaningful display name of the cached content.
labels	core	array<string>
model	core	string	Immutable. The name of the `Model` to use for cached content. Currently, only the published Gemini base models are supported, in form of projects/{PROJECT}/locations/{LOCATION}/publishers/google/models/{MODEL}
name	core	string	Immutable. Identifier. The server-generated resource name of the cached content Format: projects/{project}/locations/{location}/cachedContents/{cached_content}
organization_id	core	string
parent	core	string
project_id	core	string
project_number	core	string
region_id	core	string
resource_name	core	string
system_instruction	core	json	Optional. Input only. Immutable. Developer set system instruction. Currently, text only
tags	core	hstore_csv
tool_config	core	json	Optional. Input only. Immutable. Tool config. This config is shared for all tools
tools	core	json	Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response
ttl	core	string	Input only. The TTL for this resource. The expiration time is computed: now + TTL.
update_time	core	timestamp	Output only. When the cache entry was last updated in UTC time.
usage_metadata	core	json	Output only. Metadata on the usage of the cached content.
zone_id	core	string