ai_search function (Beta)

BetaAug 7, 2026VerifiedAdded Sep 22, 2026

The ai_search() SQL function retrieves information from one or more AI Search indexes configured as knowledge sources. Given a natural-language query, the function generates optimized search queries, retrieves and deduplicates results across sources, reranks them by relevance, and returns the most relevant documents.

Vector search SQL Data integration

Read Databricks's release notes

https://docs.databricks.com/aws/en/release-notes/product/2026/august#ai_search-function-beta

Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.

More Databricks Data Intelligence Platform releases

Databricks Data Intelligence PlatformAug 6, 2026

JAR tasks on serverless compute are now generally available

Package Scala or Java code as a JAR and run it as a task in a Lakeflow Job on serverless compute. Your JAR must match the Scala, Java Development Kit (JDK), and Databricks Connect versions of your serverless environment version. See Create and run JARs on serverless compute .

GASource

Databricks Data Intelligence PlatformAug 5, 2026

Search and replace text across files

You can now search and replace text across files in a Databricks Git folder or Declarative Automation Bundles project from the Search pane. See Search and replace across files .

UpdateSource

Databricks Data Intelligence PlatformAug 10, 2026

Databricks Runtime 19: August 10, 2026

New features and improvements collect_union aggregate function : SQL and the Scala and Python DataFrame APIs now support collect_union , which returns the distinct union of the elements in arrays within each group.

UpdateSQLGovernanceSecuritySource

Databricks Data Intelligence PlatformAug 4, 2026

Databricks Runtime maintenance updates (08/04)

New maintenance updates are available for supported Databricks Runtime versions. These updates include bug fixes, security patches, and performance improvements. For details, see: Databricks Runtime 18 LTS Databricks Runtime 18.2 Databricks Runtime 18.1 Databricks Runtime 17.3 LTS Databricks Runtime 16.4 LTS Databricks Runtime 15.4 LTS Databricks Runtime...

UpdateSecurityPerformanceSource

Databricks Data Intelligence PlatformAug 3, 2026

Serverless compute access control is now generally available

Serverless compute access control is now generally available. Workspace admins can govern who runs serverless workloads through two built-in serverless compute objects: Default Interactive Compute (governs access to notebooks and Databricks Connect) and Default Automated Compute (governs access to jobs and Spark Declarative Pipelines on Lakeflow).

GAData integrationNotebooksSource

Databricks Data Intelligence PlatformAug 3, 2026

Organize your work with spaces

You can now use spaces to organize your work in the Databricks editor. Each space lets you focus on a specific folder or project while preserving your open tabs, so you can easily pick up where you left off. See Organize your work with spaces .

UpdateSource

Databricks Data Intelligence PlatformAug 3, 2026

Filter updates for the Databricks Excel Add-in

The Databricks Excel Add-in now supports cascading filters and case-insensitive string matching. Additionally, the LIKE , NOT LIKE , IN , NOT IN , and ILIKE filters are no longer available in the filters list. See Filter imported data .

UpdateSource

Databricks Data Intelligence PlatformAug 13, 2026

Expanded networking billing for OpenSharing SecureConnect

Databricks will be expanding networking billing for OpenSharing SecureConnect. Today, data providers are billed for data transfer (egress) when recipients access shared data through SecureConnect. Additional charge types and access scenarios, including charges billed to recipients, are planned.

PricingPricingRegionsSource

Also shipped on Aug 7, 2026

Snowflake SnowflakeAug 7, 2026

DCM Projects (General availability)

DCM Projects are now generally available and are no longer in Preview . DCM Projects enable a declarative approach to managing Snowflake objects as code. You define the desired target state of your databases, tables, tasks, and other Snowflake objects in definition files, and Snowflake determines and applies the necessary changes to reach that state.

GASQLPricingDeveloper toolsSource

Snowflake Snowflake Cortex AIAug 7, 2026

Snowflake Native Apps: Cortex Agents and MCP servers (General availability)

Cortex Agents and MCP servers in Snowflake Native Apps are now generally available. Providers can create the following objects in an app’s setup script: Apps can also use inter-app communication so that one app’s agent calls another app’s agent or MCP server.

GAAI agentsMCPSource

Google Cloud AlloyDBAug 7, 2026

AlloyDB can sync BigQuery tables in preview

BigQuery tables can be synced into AlloyDB once or on a periodic schedule, giving operational analytics low-latency transactional access to data lake data.

PreviewSQLPerformanceSource

Google Cloud AlloyDBAug 7, 2026

AlloyDB integration with BigQuery enters preview

AlloyDB can connect operational and analytical data through real-time lakehouse federation to BigQuery, periodic data synchronization and one-time table syncs, all in preview.

PreviewSQLStreamingSource

Google Cloud Gemini EnterpriseAug 7, 2026

Gemini Enterprise: Custom MCP server data stores

You can connect your custom Model Context Protocol (MCP) server with Gemini Enterprise to securely access your company's private data, custom internal tools, and MCP-compliant third-party systems. This feature is turned off by default. To enable it, an Organization Policy Administrator must remove the organization constraint.

GALLMsMCPGovernanceSource

Anthropic Claude PlatformAug 7, 2026

Claude Managed Agents sessions support hard spend budgets

A session budget caps spend at public list rates; when reached, the session pauses with the budget_reached stop reason instead of starting new model requests. Deployments can apply the same budget to every session they start.

PricingAI agentsLLMsPricingSource