Releasesby Glyphai_prep_search supports plain text and markdown input (Beta)
The ai_prep_search() SQL function now accepts plain text and markdown STRING content in addition to the structured VARIANT output of ai_parse_document . You can now chunk and prepare text that you already have as a string for AI Search indexing and retrieval-augmented generation (RAG) pipelines, without first running it through document parsing.
Also shipped Aug 25, 2026Databricks in August 2026 →
BigQuery data governance tags are supported in Terraform
BigQuery data governance tags are supported in Terraform. This feature is in Preview .
Multi-value tags (General availability)
With this release, multi-value tags are generally available. You can assign more than one string value to the same tag.
Remote app operations for Snowflake Native Apps (Preview)
Remote app operations are now available in public preview for Snowflake Native Apps. Providers can perform on-demand operations on consumer apps, including running SQL statements ( run_sql ), retrying a failed upgrade ( retry_upgrade ), and disabling/enabling the app ( disable / enable ), all through a new system function SYSTEM$REMOTE_APP_OPERATION .
Remote Development with the Snowflake Extension for Visual Studio Code (Preview)
Remote Development with the Snowflake Extension for Visual Studio Code is now available in public preview.
Stable egress IP addresses on Azure (Preview)
Stable egress IP addresses are now available in preview on Azure. You can generate Snowflake egress IP address ranges (as CIDR addresses) and add them to an external server's allowlist so that Snowflake can make requests to that server.
General availability: Bring Your Own Cloud (BYOC)
BYOC is now generally available and recommended for production usage on the Enterprise plan, across AWS, GCP, and Azure. BYOC runs the Pinecone data plane inside your own cloud account, so your vectors, metadata, and queries stay in your environment.
More from Databricks Data Intelligence PlatformEvery Databricks Data Intelligence Platform release →
Query text is now masked by default in system tables and APIs
Because SQL statements can contain sensitive information, Databricks now masks query text in the following places: statement_text in system.query.history returns . query_text in the Query History API and the List Queries API returns . Keys in request_params in system.access.audit that contain SQL definitions are omitted.
Private network gateway is in Private Preview
Private network gateway is in Private Preview . A private network gateway connects Databricks serverless compute to resources in your VPC, on-premises systems, and the internet through a single managed gateway, reusing your existing network connectivity configuration (NCC).
Databricks Runtime 19: August 24, 2026
Library and environment updates Updated Java from Zulu21.50+19-CA to Zulu21.52+15-CA . Updated Java libraries: com.fasterxml.jackson.core.jackson-annotations from 2.21 to 2.22 com.fasterxml.jackson.core.jackson-core from 2.21.2 to 2.22.1 com.fasterxml.jackson.core.jackson-databind from 2.21.2 to 2.22.1 com.fasterxml.jackson.datatype.jackson-datatype-joda...
Zhipu AI GLM 5.3 now available as a Databricks-hosted model
Model Serving now supports GLM 5.3 as a Databricks-hosted model in supported US and Americas regions. This text-only mixture of experts (MoE) model supports a context window of up to 1,048,576 tokens, up to 65,536 output tokens, function calling, structured output, coding, agentic tool use, and always-on reasoning.
Restrict service principal OAuth secrets to specific API scopes
You can now restrict a service principal's OAuth secret to specific API scopes, such as sql or jobs , instead of all APIs. A token minted from a scoped secret can't exceed those scopes, which limits the impact of a leaked secret. See Authorize service principal access to Databricks with OAuth .
ai_transcribe function (Beta)
The ai_transcribe() SQL function transcribes an audio file into text. It returns the transcript as time-stamped segments, and labels each segment with a speaker when speaker diarization is enabled for your workspace. The output is a VARIANT value, so you can chain it into other AI Functions. This feature is in Beta . See ai_transcribe function .
Upcoming end of life for the Supervisor API
The Supervisor API (Beta) reaches end of life on September 30, 2026. After that date, the API is no longer available. Databricks recommends migrating to custom agents on Databricks Apps . See Supervisor API (Beta) (deprecated) .
Write data back to Databricks from Google Sheets
The Databricks Connector for Google Sheets now lets you write data from Google Sheets back to a Unity Catalog table. You can create a new table or overwrite an existing table without leaving Google Sheets. See Write data back to Databricks from Google Sheets .