♊️ GemiNews 🗞️ (dev)

Demo 1: Embeddings + Recommendation Demo 2: Bella RAGa Demo 3: NewRetriever Demo 4: Assistant function calling

🗞️March 28, 2024

🗿Semantically Similar Articles (by :title_embedding)

March 28, 2024

2024-03-28 - (from GCP latest releases)

Apigee Integrated Portal Announcement On March 28, 2024 we released an updated version of Apigee integrated portal. Fixed Bug ID Description 324872865 Fixed scrolling issue with API documentation display when navigating to the overview page. Assured Workloads Feature The following compliance programs now support the following products. See supported products for more information: Australia Regions with Assured Support: Access Transparency Canada Regions and Support: Access Transparency EU Regions and Support: Access Approval Certificate Authority Service Cloud Monitoring Cloud Run Firestore Sensitive Data Protection FedRAMP Moderate: Artifact Registry Cloud Workstations Israel Regions and Support: Dataflow Memorystore for Redis Japan Regions: Access Approval Access Transparency US Regions and Support: Access Transparency BigQuery Feature You can now query data in SAP Datasphere using a federated query. This feature is in preview. Feature Query optimization using search indexes is now applied to comparisons of string literals and indexed data, including the equal (=), IN, and LIKE operators and the STARTS_WITH function. This feature is generally available (GA). Capacity Planner Feature Preview: Capacity planner supports the following for data aggregated by organization ID: View and export the actual and forecasted usage data of the VMs and persistent disks in your organization. Generate gcloud CLI commands to create future reservation requests based on the actual or forecasted usage data of your VMs by organization. For more information, see the following pages: About Capacity Planner Export usage and forecast data in Capacity Planner Reserve capacity from actual or forecasted usage View actual and forecasted usage in Capacity Planner Chronicle SOAR Announcement Release 6.2.53 is currently in Preview. Fixed Issue when filtering Cases in Cases Page (ID #49689809) Fixed Case filter is_not not working as expected (ID #00279039) Fixed Unsupported providers causing playbooks not to run (ID #00262970) Fixed Playbook block missing when trying to add it to a case (ID #00273133) Fixed Report Scheduler not sending out reports as planned (ID #00277914) Cloud Logging Feature Pie charts are now available for visualizing data in the Log Analytics page. For more information, see Change chart type. Cloud Monitoring Feature Uptime checks now support authentication by using a service account and a generated OpenID Connect (OIDC) token, as an alternative to providing a username and password. For more information, see Create public uptime checks. Cloud Run Changed All jobs are now subject to maintenance events, not just jobs longer than one hour, which increases reliability for jobs under 1 hour. These maintenance events are transparent and don't require any changes to your container. Cloud SQL for MySQL Feature You can now simulate a planned maintenance update with near-zero downtime on your Cloud SQL Enterprise Plus primary instance without updating your database. For more information, see About maintenance on Cloud SQL instances. Cloud SQL for PostgreSQL Feature You can now simulate a planned maintenance update with near-zero downtime on your Cloud SQL Enterprise Plus primary instance without updating your database. For more information, see About maintenance on Cloud SQL instances. Config Connector Announcement Config Connector version 1.114.1 is now available. Changed SQLInstance and ComputeBackendService now have additional safeguards against populating plain-text secrets back into the object. Fixed Fixed resource deletion of AlloyDBInstance and EdgeContainerNodePool when their "parent objects" no longer exist. Changed Initial support (alpha stability) for pausing reconciliation, by setting spec.actuationMode: Paused in the ConfigConnectorContext. Changed Initial support (alpha stability) for defaulting state-into-spec to absent (the recommended setting), by setting spec.stateIntoSpec: Absent in the ConfigConnectorContext. Changed AccessContextManagerServicePerimeterResource is promoted from alpha to beta Changed Added support for ComputeNetworkFirewallPolicyAssociation (v1beta1) resource. Changed Added support for APIKeysKey (v1alpha1) resource. Changed BigQueryDataSet Added access[].iamMember field. Changed ComputeAddress Added status.observedState.address field. Changed ComputeTargetHttpsProxy Added spec.certificateManagerCertificates field. Changed DNSRecordSet Added spec.routingPolicy field. Changed GKEHubFeatureMembership Added spec.policycontroller field. Dataflow Feature The Dataflow right fitting feature is now supported by non-Prime batch pipelines. Dataproc Announcement New Dataproc on Compute Engine subminor image versions: 2.0.97-debian10, 2.0.97-rocky8, 2.0.97-ubuntu18 2.1.45-debian11, 2.1.45-rocky8, 2.1.45-ubuntu20, 2.1.45-ubuntu20-arm 2.2.11-debian12, 2.2.11-rocky9, 2.2.11-ubuntu22 Feature Dataproc on Compute Engine: New Hadoop Google Secret Manager Credential Provider feature introduced in latest Dataproc on Compute Engine 2.0 image versions. Google Cloud Architecture Center Feature (New guide) Model development and data labeling with Google Cloud and Labelbox: Provides guidance for building a standardized pipeline to help accelerate the development of ML models. Looker Studio Announcement Looker Studio release notes moved to Google Cloud We've changed how we deliver product release notes. Looker Studio release notes are available solely on the Google Cloud release notes platform. Release notes prior to this change are preserved in the historical release notes page in the Looker Studio Help Center. Changed Label fields available in the New Search Ads 360 connector You can now include the following New Search Ads 360 fields in your reports: Label (Keyword) Label (Ad) Learn more about the New Search Ads 360 connector. Sensitive Data Protection Feature The SWITZERLAND_SOCIAL_SECURITY_NUMBER infoType detector is available in all regions. For more information about all built-in infoTypes, see InfoType detector reference. Vertex AI Search and Conversation Feature Vertex AI Search: Autocomplete updates Autocomplete is Generally available (GA) for the US and EU multi-regions as well for the global region. Autocomplete supports access transparency. This means that, when access transparency is enabled, if Google personal access your autocomplete data, this is recorded in the Access Transparency logs. For information about autocomplete, see Configure autocomplete, and for information about Access Transparency, see Enable Access Transparency in Vertex AI Search. Feature Vertex AI Search: Structured data stores (GA) Use of data stores containing structured data is Generally available (GA). Additionally, two new field value types are allowed for structured data stores: geolocation and datetime. For information about structured data stores, see Structured data in Prepare for ingesting and Schemas: auto-dectection versus providing you own. Feature Vertex AI Search: Boost search results (Public preview) Boosting search results using custom numerical attributes and according to freshness is available in Public preview. For more information, see Boost search results. Feature Vertex AI Search: Extractive segments and relevance scores (GA) Extractive segments and relevance scores for extractive segments are GA. For more information, see Extractive segments. Feature Vertex AI Search: Document chunking and parsing improvements (Public preview) The following improvements have been introduced for document chunking and parsing: Adjacent chunks: When returning chunks in search responses, you can return chunks from immediately before and after the relevant chunk in the source document. Doing so can improve context and accuracy. Page span: Chunk metadata in search responses includes the span of pages where the chunk appeared in the source document. List chunks: List all chunks from a specific source document. Get chunks: Get a specific chunk. Get processed documents in JSON: Get a parsed document or a chunked document in JSON format. Bring your own chunks (Preview with allowlist): Upload data that you've already chunked. Contact your Google account team if you're interested in trying this feature. For more information, see Parse and chunk documents. Feature Vertex AI Search: Media recommendations analytics (GA) Analytics for media recommendations are GA. You can view analytics for your media recommendations apps in the Google Cloud console. For more information, see View analytics. Feature Vertex AI Search: Connect Google Drive to Vertex AI Search (GA) Syncing Google Drive data to Vertex AI Search is available in GA. For more information, see Sync from Google Drive. Video Stitcher API Changed Added a new tokenConfig field to the Media CDN key. Set this field to sign the URL using the Media CDN token. reCAPTCHA Enterprise Announcement reCAPTCHA Enterprise account defender for mobile applications is now generally available (GA). You can use this feature to detect and prevent account-related fraudulent activities on mobile applications.

[Technology] 🌎 https://cloud.google.com/release-notes#March_28_2024 [🧠] [v2] article_embedding_description: {:llm_project_id=>"Unavailable", :llm_dimensions=>nil, :article_size=>15699, :llm_embeddings_model_name=>"textembedding-gecko"}
[🧠] [v1/3] title_embedding_description: {:ricc_notes=>"[embed-v3] Fixed on 9oct24. Only seems incompatible at first glance with embed v1.", :llm_project_id=>"unavailable possibly not using Vertex", :llm_dimensions=>nil, :article_size=>15699, :poly_field=>"title", :llm_embeddings_model_name=>"textembedding-gecko"}
[🧠] [v1/3] summary_embedding_description:
[🧠] As per bug https://github.com/palladius/gemini-news-crawler/issues/4 we can state this article belongs to titile/summary version: v3 (very few articles updated on 9oct24)

🗿article.to_s 

------------------------------
Title: March 28, 2024
[content]
Apigee Integrated Portal
Announcement
On March 28, 2024 we released an updated version of Apigee integrated portal.
Fixed



Bug ID
Description





324872865
Fixed scrolling issue with API documentation display when navigating to the overview page.



Assured Workloads
Feature
The following compliance programs now support the following products. See
supported products for more information:


Australia Regions with Assured Support:

Access Transparency

Canada Regions and Support:

Access Transparency

EU Regions and Support:

Access Approval
Certificate Authority Service
Cloud Monitoring
Cloud Run
Firestore
Sensitive Data Protection

FedRAMP Moderate:

Artifact Registry
Cloud Workstations

Israel Regions and Support:

Dataflow
Memorystore for Redis

Japan Regions:

Access Approval
Access Transparency

US Regions and Support:

Access Transparency


BigQuery
Feature
You can now query data in SAP Datasphere using a federated query. This feature is in preview.
Feature
Query optimization using search indexes is now applied to comparisons of string literals and indexed data, including the equal (=), IN, and LIKE operators and the STARTS_WITH function. This feature is generally available (GA).
Capacity Planner
Feature
Preview: Capacity planner supports the following for data aggregated by organization ID:


View and export the actual and forecasted usage data of the VMs and persistent disks in your organization.
Generate gcloud CLI commands to create future reservation requests based on the actual or forecasted usage data of your VMs by organization.


For more information, see the following pages:


About Capacity Planner
Export usage and forecast data in Capacity Planner
Reserve capacity from actual or forecasted usage
View actual and forecasted usage in Capacity Planner

Chronicle SOAR
Announcement
Release 6.2.53 is currently in Preview.
Fixed
Issue when filtering Cases in Cases Page (ID #49689809)
Fixed
Case filter is_not not working as expected (ID #00279039)
Fixed
Unsupported providers causing playbooks not to run (ID #00262970)
Fixed
Playbook block missing when trying  to add it to a case (ID #00273133)
Fixed
Report Scheduler not sending out reports as planned (ID #00277914)
Cloud Logging
Feature
Pie charts are now available for visualizing data in the Log Analytics page. For more information, see Change chart type.
Cloud Monitoring
Feature
Uptime checks now support authentication by using a service account and a generated OpenID Connect (OIDC) token, as an alternative to providing a username and password. For more information, see Create public uptime checks.
Cloud Run
Changed
All jobs are now subject to maintenance events, not just jobs longer than one hour, which increases reliability for jobs under 1 hour. These maintenance events are transparent and don't require any changes to your container.
Cloud SQL for MySQL
Feature
You can now simulate a planned maintenance update with near-zero downtime on your Cloud SQL Enterprise Plus primary instance without updating your database. For more information, see About maintenance on Cloud SQL instances.
Cloud SQL for PostgreSQL
Feature
You can now simulate a planned maintenance update with near-zero downtime on your Cloud SQL Enterprise Plus primary instance without updating your database. For more information, see About maintenance on Cloud SQL instances.
Config Connector
Announcement
Config Connector version 1.114.1 is now available.
Changed
SQLInstance and ComputeBackendService now have additional safeguards against populating plain-text secrets back into the object.
Fixed
Fixed resource deletion of AlloyDBInstance and EdgeContainerNodePool when their "parent objects" no longer exist.
Changed
Initial support (alpha stability) for pausing reconciliation, by setting spec.actuationMode: Paused in the ConfigConnectorContext.
Changed
Initial support (alpha stability) for defaulting state-into-spec to absent (the recommended setting),
  by setting spec.stateIntoSpec: Absent in the ConfigConnectorContext.
Changed
AccessContextManagerServicePerimeterResource is promoted from alpha to beta
Changed
Added support for ComputeNetworkFirewallPolicyAssociation (v1beta1) resource.
Changed
Added support for APIKeysKey (v1alpha1) resource.
Changed
BigQueryDataSet


Added access[].iamMember field.

Changed
ComputeAddress


Added status.observedState.address field.

Changed
ComputeTargetHttpsProxy


Added spec.certificateManagerCertificates field.

Changed
DNSRecordSet


Added spec.routingPolicy field.

Changed
GKEHubFeatureMembership


Added spec.policycontroller field.

Dataflow
Feature
The Dataflow right fitting feature is now supported by non-Prime batch pipelines.
Dataproc
Announcement

New Dataproc on Compute Engine subminor image versions:


2.0.97-debian10, 2.0.97-rocky8, 2.0.97-ubuntu18
2.1.45-debian11, 2.1.45-rocky8, 2.1.45-ubuntu20, 2.1.45-ubuntu20-arm
2.2.11-debian12, 2.2.11-rocky9, 2.2.11-ubuntu22


Feature
Dataproc on Compute Engine: New Hadoop Google Secret Manager Credential Provider feature introduced in latest Dataproc on Compute Engine 2.0 image versions.
Google Cloud Architecture Center
Feature
(New guide) Model development and data labeling with Google Cloud and Labelbox: Provides guidance for building a standardized pipeline to help accelerate the development of ML models.
Looker Studio
Announcement
Looker Studio release notes moved to Google Cloud

We've changed how we deliver product release notes. Looker Studio release notes are available solely on the Google Cloud release notes platform. 

Release notes prior to this change are preserved in the  historical release notes  page in the Looker Studio Help Center.
Changed
Label fields available in the New Search Ads 360 connector

You can now include the following New Search Ads 360 fields in your reports:


Label (Keyword)
Label (Ad)


Learn more about the New Search Ads 360 connector.
Sensitive Data Protection
Feature
The SWITZERLAND_SOCIAL_SECURITY_NUMBER infoType detector is available in all regions. For more information about all built-in infoTypes, see InfoType detector reference.
Vertex AI Search and Conversation
Feature
Vertex AI Search: Autocomplete updates

Autocomplete is Generally available (GA) for the US and EU multi-regions as well for the global region.

Autocomplete supports access transparency. This means that, when access transparency is enabled, if Google personal access your autocomplete data, this is recorded in the Access Transparency logs. 

For information about autocomplete, see Configure autocomplete, and for information about Access Transparency, see Enable Access Transparency in Vertex AI Search.
Feature
Vertex AI Search: Structured data stores (GA)

Use of data stores containing structured data is Generally available (GA). Additionally, two new field value types are allowed for structured data stores: geolocation and datetime.

For information about structured data stores, see Structured data in Prepare for ingesting and Schemas: auto-dectection versus providing you own.
Feature
Vertex AI Search: Boost search results (Public preview)

Boosting search results using custom numerical attributes and according to freshness is available in Public preview.

For more information, see Boost search results.
Feature
Vertex AI Search: Extractive segments and relevance scores (GA)

Extractive segments and relevance scores for extractive segments are GA.

For more information, see Extractive segments.
Feature
Vertex AI Search: Document chunking and parsing improvements (Public preview)

The following improvements have been introduced for document chunking and parsing:


Adjacent chunks: When returning chunks in search responses, you can return chunks from immediately before and after the relevant chunk in the source document. Doing so can improve context and accuracy.
Page span: Chunk metadata in search responses includes the span of pages where the chunk appeared in the source document.
List chunks: List all chunks from a specific source document.
Get chunks: Get a specific chunk.
Get processed documents in JSON: Get a parsed document or a chunked document in JSON format.
Bring your own chunks (Preview with allowlist): Upload data that you've already chunked. Contact your Google account team if you're interested in trying this feature.


For more information, see Parse and chunk documents. 
Feature
Vertex AI Search: Media recommendations analytics (GA)

Analytics for media recommendations are GA. You can view analytics for your media recommendations apps in the Google Cloud console.

For more information, see View analytics.
Feature
Vertex AI Search: Connect Google Drive to Vertex AI Search (GA)

Syncing Google Drive data to Vertex AI Search is available in GA.

For more information, see Sync from Google Drive. 
Video Stitcher API
Changed
Added a new tokenConfig field to the Media CDN key. Set this field to sign the URL using the Media CDN token.
reCAPTCHA Enterprise
Announcement
reCAPTCHA Enterprise account defender for mobile applications is now generally available (GA).

You can use this feature to detect and prevent account-related fraudulent activities on mobile applications.
[/content]

PublishedDate: 2024-03-28
Category: Technology
NewsPaper: GCP latest releases
{"id"=>1342,
"title"=>"March 28, 2024",
"summary"=>nil,
"content"=>"Apigee Integrated Portal\n

Announcement

\n

On March 28, 2024 we released an updated version of Apigee integrated portal.

\n

Fixed

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Bug IDDescription
324872865Fixed scrolling issue with API documentation display when navigating to the overview page.
\nAssured Workloads\n

Feature

\n

The following compliance programs now support the following products. See\nsupported products for more information:

\n\n
    \n
  • Australia Regions with Assured Support:\n
      \n
    • Access Transparency
      • \n
    • \n
  • Canada Regions and Support:\n
      \n
    • Access Transparency
      • \n
    • \n
  • EU Regions and Support:\n
      \n
    • Access Approval
      • \n
    • Certificate Authority Service
      • \n
    • Cloud Monitoring
      • \n
    • Cloud Run
      • \n
    • Firestore
      • \n
    • Sensitive Data Protection
      • \n
    • \n
  • FedRAMP Moderate:\n
      \n
    • Artifact Registry
      • \n
    • Cloud Workstations
      • \n
    • \n
  • Israel Regions and Support:\n
      \n
    • Dataflow
      • \n
    • Memorystore for Redis
      • \n
    • \n
  • Japan Regions:\n
      \n
    • Access Approval
      • \n
    • Access Transparency
      • \n
    • \n
  • US Regions and Support:\n
      \n
    • Access Transparency
      • \n
    • \n
\nBigQuery\n

Feature

\n

You can now query data in SAP Datasphere using a federated query. This feature is in preview.

\n

Feature

\n

Query optimization using search indexes is now applied to comparisons of string literals and indexed data, including the equal (=), IN, and LIKE operators and the STARTS_WITH function. This feature is generally available (GA).

\nCapacity Planner\n

Feature

\n

Preview: Capacity planner supports the following for data aggregated by organization ID:

\n\n
    \n

  • View and export the actual and forecasted usage data of the VMs and persistent disks in your organization.

    • \n

  • Generate gcloud CLI commands to create future reservation requests based on the actual or forecasted usage data of your VMs by organization.

    • \n
\n\n

For more information, see the following pages:

\n\n\nChronicle SOAR\n

Announcement

\n

Release 6.2.53 is currently in Preview.

\n

Fixed

\n

Issue when filtering Cases in Cases Page (ID #49689809)

\n

Fixed

\n

Case filter is_not not working as expected (ID #00279039)

\n

Fixed

\n

Unsupported providers causing playbooks not to run (ID #00262970)

\n

Fixed

\n

Playbook block missing when trying to add it to a case (ID #00273133)

\n

Fixed

\n

Report Scheduler not sending out reports as planned (ID #00277914)

\nCloud Logging\n

Feature

\n

Pie charts are now available for visualizing data in the Log Analytics page. For more information, see Change chart type.

\nCloud Monitoring\n

Feature

\n

Uptime checks now support authentication by using a service account and a generated OpenID Connect (OIDC) token, as an alternative to providing a username and password. For more information, see Create public uptime checks.

\nCloud Run\n

Changed

\n

All jobs are now subject to maintenance events, not just jobs longer than one hour, which increases reliability for jobs under 1 hour. These maintenance events are transparent and don't require any changes to your container.

\nCloud SQL for MySQL\n

Feature

\n

You can now simulate a planned maintenance update with near-zero downtime on your Cloud SQL Enterprise Plus primary instance without updating your database. For more information, see About maintenance on Cloud SQL instances.

\nCloud SQL for PostgreSQL\n

Feature

\n

You can now simulate a planned maintenance update with near-zero downtime on your Cloud SQL Enterprise Plus primary instance without updating your database. For more information, see About maintenance on Cloud SQL instances.

\nConfig Connector\n

Announcement

\n

Config Connector version 1.114.1 is now available.

\n

Changed

\n

SQLInstance and ComputeBackendService now have additional safeguards against populating plain-text secrets back into the object.

\n

Fixed

\n

Fixed resource deletion of AlloyDBInstance and EdgeContainerNodePool when their "parent objects" no longer exist.

\n

Changed

\n

Initial support (alpha stability) for pausing reconciliation, by setting spec.actuationMode: Paused in the ConfigConnectorContext.

\n

Changed

\n

Initial support (alpha stability) for defaulting state-into-spec to absent (the recommended setting),\n by setting spec.stateIntoSpec: Absent in the ConfigConnectorContext.

\n

Changed

\n

AccessContextManagerServicePerimeterResource is promoted from alpha to beta

\n

Changed

\n

Added support for ComputeNetworkFirewallPolicyAssociation (v1beta1) resource.

\n

Changed

\n

Added support for APIKeysKey (v1alpha1) resource.

\n

Changed

\n

BigQueryDataSet

\n\n
    \n
  • Added access[].iamMember field.
    • \n
\n

Changed

\n

ComputeAddress

\n\n
    \n
  • Added status.observedState.address field.
    • \n
\n

Changed

\n

ComputeTargetHttpsProxy

\n\n
    \n
  • Added spec.certificateManagerCertificates field.
    • \n
\n

Changed

\n

DNSRecordSet

\n\n
    \n
  • Added spec.routingPolicy field.
    • \n
\n

Changed

\n

GKEHubFeatureMembership

\n\n
    \n
  • Added spec.policycontroller field.
    • \n
\nDataflow\n

Feature

\n

The Dataflow right fitting feature is now supported by non-Prime batch pipelines.

\nDataproc\n

Announcement

\n\n

Feature

\n

Dataproc on Compute Engine: New Hadoop Google Secret Manager Credential Provider feature introduced in latest Dataproc on Compute Engine 2.0 image versions.

\nGoogle Cloud Architecture Center\n

Feature

\n

(New guide) Model development and data labeling with Google Cloud and Labelbox: Provides guidance for building a standardized pipeline to help accelerate the development of ML models.

\nLooker Studio\n

Announcement

\n

Looker Studio release notes moved to Google Cloud

\n\n

We've changed how we deliver product release notes. Looker Studio release notes are available solely on the Google Cloud release notes platform.

\n\n

Release notes prior to this change are preserved in the historical release notes page in the Looker Studio Help Center.

\n

Changed

\n

Label fields available in the New Search Ads 360 connector

\n\n

You can now include the following New Search Ads 360 fields in your reports:

\n\n
    \n
  • Label (Keyword)
    • \n
  • Label (Ad)
    • \n
\n\n

Learn more about the New Search Ads 360 connector.

\nSensitive Data Protection\n

Feature

\n

The SWITZERLAND_SOCIAL_SECURITY_NUMBER infoType detector is available in all regions. For more information about all built-in infoTypes, see InfoType detector reference.

\nVertex AI Search and Conversation\n

Feature

\n

Vertex AI Search: Autocomplete updates

\n\n

Autocomplete is Generally available (GA) for the US and EU multi-regions as well for the global region.

\n\n

Autocomplete supports access transparency. This means that, when access transparency is enabled, if Google personal access your autocomplete data, this is recorded in the Access Transparency logs.

\n\n

For information about autocomplete, see Configure autocomplete, and for information about Access Transparency, see Enable Access Transparency in Vertex AI Search.

\n

Feature

\n

Vertex AI Search: Structured data stores (GA)

\n\n

Use of data stores containing structured data is Generally available (GA). Additionally, two new field value types are allowed for structured data stores: geolocation and datetime.

\n\n

For information about structured data stores, see Structured data in Prepare for ingesting and Schemas: auto-dectection versus providing you own.

\n

Feature

\n

Vertex AI Search: Boost search results (Public preview)

\n\n

Boosting search results using custom numerical attributes and according to freshness is available in Public preview.

\n\n

For more information, see Boost search results.

\n

Feature

\n

Vertex AI Search: Extractive segments and relevance scores (GA)

\n\n

Extractive segments and relevance scores for extractive segments are GA.

\n\n

For more information, see Extractive segments.

\n

Feature

\n

Vertex AI Search: Document chunking and parsing improvements (Public preview)

\n\n

The following improvements have been introduced for document chunking and parsing:

\n\n
    \n
  • Adjacent chunks: When returning chunks in search responses, you can return chunks from immediately before and after the relevant chunk in the source document. Doing so can improve context and accuracy.
    • \n
  • Page span: Chunk metadata in search responses includes the span of pages where the chunk appeared in the source document.
    • \n
  • List chunks: List all chunks from a specific source document.
    • \n
  • Get chunks: Get a specific chunk.
    • \n
  • Get processed documents in JSON: Get a parsed document or a chunked document in JSON format.
    • \n
  • Bring your own chunks (Preview with allowlist): Upload data that you've already chunked. Contact your Google account team if you're interested in trying this feature.
    • \n
\n\n

For more information, see Parse and chunk documents.

\n

Feature

\n

Vertex AI Search: Media recommendations analytics (GA)

\n\n

Analytics for media recommendations are GA. You can view analytics for your media recommendations apps in the Google Cloud console.

\n\n

For more information, see View analytics.

\n

Feature

\n

Vertex AI Search: Connect Google Drive to Vertex AI Search (GA)

\n\n

Syncing Google Drive data to Vertex AI Search is available in GA.

\n\n

For more information, see Sync from Google Drive.

\nVideo Stitcher API\n

Changed

\n

Added a new tokenConfig field to the Media CDN key. Set this field to sign the URL using the Media CDN token.

\nreCAPTCHA Enterprise\n

Announcement

\n

reCAPTCHA Enterprise account defender for mobile applications is now generally available (GA).

\n\n

You can use this feature to detect and prevent account-related fraudulent activities on mobile applications.

\n\n ",
"author"=>nil,
"link"=>"https://cloud.google.com/release-notes#March_28_2024",
"published_date"=>Thu, 28 Mar 2024 07:00:00.000000000 UTC +00:00,
"image_url"=>nil,
"feed_url"=>"https://cloud.google.com/release-notes#March_28_2024",
"language"=>nil,
"active"=>true,
"ricc_source"=>"feedjira::v1",
"created_at"=>Sun, 31 Mar 2024 21:23:51.899076000 UTC +00:00,
"updated_at"=>Mon, 21 Oct 2024 16:58:38.783720000 UTC +00:00,
"newspaper"=>"GCP latest releases",
"macro_region"=>"Technology"}
Edit this article
Back to articles