cached_contents

Creates, updates, deletes, gets or lists a cached_contents resource.

Overview

Name	cached_contents
Type	Resource
Id	google.aiplatform.cached_contents

Fields

The following fields are returned by SELECT queries:

get

Name	Datatype	Description
name	string	Immutable. Identifier. The server-generated resource name of the cached content Format: projects/{project}/locations/{location}/cachedContents/{cached_content}
contents	array	Optional. Input only. Immutable. The content to cache
createTime	string (google-datetime)	Output only. Creation time of the cache entry.
displayName	string	Optional. Immutable. The user-generated meaningful display name of the cached content.
encryptionSpec	object	Input only. Immutable. Customer-managed encryption key spec for a CachedContent. If set, this CachedContent and all its sub-resources will be secured by this key. (id: GoogleCloudAiplatformV1EncryptionSpec)
expireTime	string (google-datetime)	Timestamp of when this resource is considered expired. This is always provided on output, regardless of what was sent on input.
model	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}
systemInstruction	object	The structured data content of a message. A Content message contains a role field, which indicates the producer of the content, and a parts field, which contains the multi-part data of the message. (id: GoogleCloudAiplatformV1Content)
toolConfig	object	Optional. Input only. Immutable. Tool config. This config is shared for all tools (id: GoogleCloudAiplatformV1ToolConfig)
tools	array	Optional. Input only. Immutable. A list of Tools the model may use to generate the next response
ttl	string (google-duration)	Input only. The TTL for this resource. The expiration time is computed: now + TTL.
updateTime	string (google-datetime)	Output only. When the cache entry was last updated in UTC time.
usageMetadata	object	Output only. Metadata on the usage of the cached content. (id: GoogleCloudAiplatformV1CachedContentUsageMetadata)

list

Name	Datatype	Description
name	string	Immutable. Identifier. The server-generated resource name of the cached content Format: projects/{project}/locations/{location}/cachedContents/{cached_content}
contents	array	Optional. Input only. Immutable. The content to cache
createTime	string (google-datetime)	Output only. Creation time of the cache entry.
displayName	string	Optional. Immutable. The user-generated meaningful display name of the cached content.
encryptionSpec	object	Input only. Immutable. Customer-managed encryption key spec for a CachedContent. If set, this CachedContent and all its sub-resources will be secured by this key. (id: GoogleCloudAiplatformV1EncryptionSpec)
expireTime	string (google-datetime)	Timestamp of when this resource is considered expired. This is always provided on output, regardless of what was sent on input.
model	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}
systemInstruction	object	The structured data content of a message. A Content message contains a role field, which indicates the producer of the content, and a parts field, which contains the multi-part data of the message. (id: GoogleCloudAiplatformV1Content)
toolConfig	object	Optional. Input only. Immutable. Tool config. This config is shared for all tools (id: GoogleCloudAiplatformV1ToolConfig)
tools	array	Optional. Input only. Immutable. A list of Tools the model may use to generate the next response
ttl	string (google-duration)	Input only. The TTL for this resource. The expiration time is computed: now + TTL.
updateTime	string (google-datetime)	Output only. When the cache entry was last updated in UTC time.
usageMetadata	object	Output only. Metadata on the usage of the cached content. (id: GoogleCloudAiplatformV1CachedContentUsageMetadata)

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get	select	projectsId, locationsId, cachedContentsId		Gets cached content configurations
list	select	projectsId, locationsId	pageSize, pageToken	Lists cached contents in a project
create	insert	projectsId, locationsId		Creates cached content, this call will initialize the cached content in the data storage, and users need to pay for the cache data storage.
patch	update	projectsId, locationsId, cachedContentsId	updateMask	Updates cached content configurations
delete	delete	projectsId, locationsId, cachedContentsId		Deletes cached content

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
cachedContentsId	string
locationsId	string
projectsId	string
pageSize	integer (int32)
pageToken	string
updateMask	string (google-fieldmask)

SELECT examples

get

Gets cached content configurations

SELECT
name,
contents,
createTime,
displayName,
encryptionSpec,
expireTime,
model,
systemInstruction,
toolConfig,
tools,
ttl,
updateTime,
usageMetadata
FROM google.aiplatform.cached_contents
WHERE projectsId = '{{ projectsId }}' -- required
AND locationsId = '{{ locationsId }}' -- required
AND cachedContentsId = '{{ cachedContentsId }}' -- required
;

list

Lists cached contents in a project

SELECT
name,
contents,
createTime,
displayName,
encryptionSpec,
expireTime,
model,
systemInstruction,
toolConfig,
tools,
ttl,
updateTime,
usageMetadata
FROM google.aiplatform.cached_contents
WHERE projectsId = '{{ projectsId }}' -- required
AND locationsId = '{{ locationsId }}' -- required
AND pageSize = '{{ pageSize }}'
AND pageToken = '{{ pageToken }}'
;

INSERT examples

create

Creates cached content, this call will initialize the cached content in the data storage, and users need to pay for the cache data storage.

INSERT INTO google.aiplatform.cached_contents (
data__tools,
data__systemInstruction,
data__encryptionSpec,
data__name,
data__expireTime,
data__ttl,
data__displayName,
data__toolConfig,
data__model,
data__contents,
projectsId,
locationsId
)
SELECT 
'{{ tools }}',
'{{ systemInstruction }}',
'{{ encryptionSpec }}',
'{{ name }}',
'{{ expireTime }}',
'{{ ttl }}',
'{{ displayName }}',
'{{ toolConfig }}',
'{{ model }}',
'{{ contents }}',
'{{ projectsId }}',
'{{ locationsId }}'
RETURNING
name,
contents,
createTime,
displayName,
encryptionSpec,
expireTime,
model,
systemInstruction,
toolConfig,
tools,
ttl,
updateTime,
usageMetadata
;

Manifest

# Description fields are for documentation purposes
- name: cached_contents
props:
  - name: projectsId
    value: "{{ projectsId }}"
    description: Required parameter for the cached_contents resource.
  - name: locationsId
    value: "{{ locationsId }}"
    description: Required parameter for the cached_contents resource.
  - name: tools
    description: |
      Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response
    value:
      - exaAiSearch:
          apiKey: "{{ apiKey }}"
          customConfigs: "{{ customConfigs }}"
        computerUse:
          excludedPredefinedFunctions:
            - "{{ excludedPredefinedFunctions }}"
          environment: "{{ environment }}"
          enablePromptInjectionDetection: {{ enablePromptInjectionDetection }}
        googleSearchRetrieval:
          dynamicRetrievalConfig:
            mode: "{{ mode }}"
            dynamicThreshold: {{ dynamicThreshold }}
        googleSearch:
          excludeDomains:
            - "{{ excludeDomains }}"
          searchTypes:
            imageSearch: "{{ imageSearch }}"
            webSearch: "{{ webSearch }}"
          blockingConfidence: "{{ blockingConfidence }}"
        parallelAiSearch:
          enableDataRetention: {{ enableDataRetention }}
          enableZeroDataRetention: {{ enableZeroDataRetention }}
          apiKey: "{{ apiKey }}"
          customConfigs: "{{ customConfigs }}"
        googleMaps:
          enableWidget: {{ enableWidget }}
          groundingTypes:
            places: "{{ places }}"
            routing: "{{ routing }}"
        retrieval:
          vertexAiSearch:
            filter: "{{ filter }}"
            dataStoreSpecs:
              - dataStore: "{{ dataStore }}"
                filter: "{{ filter }}"
            datastore: "{{ datastore }}"
            engine: "{{ engine }}"
            maxResults: {{ maxResults }}
          vertexRagStore:
            ragRetrievalConfig:
              topK: {{ topK }}
              ranking:
                llmRanker: "{{ llmRanker }}"
                rankService: "{{ rankService }}"
              filter:
                vectorDistanceThreshold: {{ vectorDistanceThreshold }}
                metadataFilter: "{{ metadataFilter }}"
                vectorSimilarityThreshold: {{ vectorSimilarityThreshold }}
            ragResources:
              - ragCorpus: "{{ ragCorpus }}"
                ragFileIds: "{{ ragFileIds }}"
            similarityTopK: {{ similarityTopK }}
            vectorDistanceThreshold: {{ vectorDistanceThreshold }}
          externalApi:
            apiSpec: "{{ apiSpec }}"
            elasticSearchParams:
              searchTemplate: "{{ searchTemplate }}"
              numHits: {{ numHits }}
              index: "{{ index }}"
            authConfig:
              googleServiceAccountConfig:
                serviceAccount: "{{ serviceAccount }}"
              apiKeyConfig:
                name: "{{ name }}"
                apiKeySecret: "{{ apiKeySecret }}"
                apiKeyString: "{{ apiKeyString }}"
                httpElementLocation: "{{ httpElementLocation }}"
              oidcConfig:
                idToken: "{{ idToken }}"
                serviceAccount: "{{ serviceAccount }}"
              oauthConfig:
                accessToken: "{{ accessToken }}"
                serviceAccount: "{{ serviceAccount }}"
              authType: "{{ authType }}"
              httpBasicAuthConfig:
                credentialSecret: "{{ credentialSecret }}"
            endpoint: "{{ endpoint }}"
            apiAuth:
              apiKeyConfig:
                apiKeySecretVersion: "{{ apiKeySecretVersion }}"
                apiKeyString: "{{ apiKeyString }}"
            simpleSearchParams: "{{ simpleSearchParams }}"
          disableAttribution: {{ disableAttribution }}
        functionDeclarations: "{{ functionDeclarations }}"
        urlContext: "{{ urlContext }}"
        enterpriseWebSearch:
          blockingConfidence: "{{ blockingConfidence }}"
          excludeDomains:
            - "{{ excludeDomains }}"
        codeExecution: "{{ codeExecution }}"
  - name: systemInstruction
    description: |
      The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
    value:
      role: "{{ role }}"
      parts:
        - videoMetadata:
            startOffset: "{{ startOffset }}"
            endOffset: "{{ endOffset }}"
            fps: {{ fps }}
          thought: {{ thought }}
          fileData:
            fileUri: "{{ fileUri }}"
            mimeType: "{{ mimeType }}"
            displayName: "{{ displayName }}"
          text: "{{ text }}"
          executableCode:
            language: "{{ language }}"
            code: "{{ code }}"
            id: "{{ id }}"
          functionResponse:
            name: "{{ name }}"
            response: "{{ response }}"
            parts:
              - inlineData:
                  mimeType: "{{ mimeType }}"
                  displayName: "{{ displayName }}"
                  data: "{{ data }}"
                fileData:
                  fileUri: "{{ fileUri }}"
                  mimeType: "{{ mimeType }}"
                  displayName: "{{ displayName }}"
            id: "{{ id }}"
            scheduling: "{{ scheduling }}"
          codeExecutionResult:
            id: "{{ id }}"
            outcome: "{{ outcome }}"
            output: "{{ output }}"
          audioTranscription:
            text: "{{ text }}"
            speakerLabel: "{{ speakerLabel }}"
            words:
              - word: "{{ word }}"
                startOffset: "{{ startOffset }}"
                endOffset: "{{ endOffset }}"
          inlineData:
            mimeType: "{{ mimeType }}"
            displayName: "{{ displayName }}"
            data: "{{ data }}"
          functionCall:
            willContinue: {{ willContinue }}
            args: "{{ args }}"
            id: "{{ id }}"
            partialArgs:
              - jsonPath: "{{ jsonPath }}"
                numberValue: {{ numberValue }}
                boolValue: {{ boolValue }}
                nullValue: "{{ nullValue }}"
                stringValue: "{{ stringValue }}"
                willContinue: {{ willContinue }}
            name: "{{ name }}"
          mediaResolution:
            level: "{{ level }}"
          thoughtSignature: "{{ thoughtSignature }}"
  - name: encryptionSpec
    description: |
      Input only. Immutable. Customer-managed encryption key spec for a `CachedContent`. If set, this `CachedContent` and all its sub-resources will be secured by this key.
    value:
      kmsKeyName: "{{ kmsKeyName }}"
  - name: name
    value: "{{ name }}"
    description: |
      Immutable. Identifier. The server-generated resource name of the cached content Format: projects/{project}/locations/{location}/cachedContents/{cached_content}
  - name: expireTime
    value: "{{ expireTime }}"
    description: |
      Timestamp of when this resource is considered expired. This is *always* provided on output, regardless of what was sent on input.
  - name: ttl
    value: "{{ ttl }}"
    description: |
      Input only. The TTL for this resource. The expiration time is computed: now + TTL.
  - name: displayName
    value: "{{ displayName }}"
    description: |
      Optional. Immutable. The user-generated meaningful display name of the cached content.
  - name: toolConfig
    description: |
      Optional. Input only. Immutable. Tool config. This config is shared for all tools
    value:
      functionCallingConfig:
        allowedFunctionNames:
          - "{{ allowedFunctionNames }}"
        mode: "{{ mode }}"
        streamFunctionCallArguments: {{ streamFunctionCallArguments }}
      retrievalConfig:
        latLng:
          longitude: {{ longitude }}
          latitude: {{ latitude }}
        languageCode: "{{ languageCode }}"
  - name: model
    value: "{{ model }}"
    description: |
      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: contents
    description: |
      Optional. Input only. Immutable. The content to cache
    value:
      - role: "{{ role }}"
        parts: "{{ parts }}"

UPDATE examples

patch

Updates cached content configurations

UPDATE google.aiplatform.cached_contents
SET 
data__tools = '{{ tools }}',
data__systemInstruction = '{{ systemInstruction }}',
data__encryptionSpec = '{{ encryptionSpec }}',
data__name = '{{ name }}',
data__expireTime = '{{ expireTime }}',
data__ttl = '{{ ttl }}',
data__displayName = '{{ displayName }}',
data__toolConfig = '{{ toolConfig }}',
data__model = '{{ model }}',
data__contents = '{{ contents }}'
WHERE 
projectsId = '{{ projectsId }}' --required
AND locationsId = '{{ locationsId }}' --required
AND cachedContentsId = '{{ cachedContentsId }}' --required
AND updateMask = '{{ updateMask}}'
RETURNING
name,
contents,
createTime,
displayName,
encryptionSpec,
expireTime,
model,
systemInstruction,
toolConfig,
tools,
ttl,
updateTime,
usageMetadata;

DELETE examples

delete

Deletes cached content

DELETE FROM google.aiplatform.cached_contents
WHERE projectsId = '{{ projectsId }}' --required
AND locationsId = '{{ locationsId }}' --required
AND cachedContentsId = '{{ cachedContentsId }}' --required
;