Releasesby GlyphYou can now use the AlloyDB Columnar Engine as a read-optimized, in-memory cache for HNSW vector indexes
You can now use the AlloyDB Columnar Engine as a read-optimized, in-memory cache for HNSW vector indexes. This feature is generally available ( GA ). It accelerates vector search performance and increases queries per second (QPS) for vector workloads. For more information, see Accelerate queries with the Columnar Engine .
Also shipped Sep 21, 2026Google Cloud in September 2026 →
The query history system table is now generally available
The system.query.history system table is now generally available. Use it to access account-wide records for queries run on SQL warehouses or serverless compute, including execution status, duration metrics, and query source. See Query history system table reference .
Cortex AI Function Evaluation for measuring quality (Public Preview)
Snowflake Cortex AI Function Evaluation is now available in public preview, enabling customers to measure the output quality, cost, and token usage of custom AI Functions and Cortex AI calls against labeled datasets.
Cortex AI Function Optimization for more efficient AI implementations (Public Preview)
Snowflake Cortex AI Function Optimization is now available in public preview, enabling customers to automatically search across prompts and models for improved implementations of custom AI Functions.
Cortex Agents Compact API (Preview)
The Cortex Agents Compact API is now available in preview. Use the agent:compact endpoint to summarize a conversation and pass the compact representation to subsequent agent:run requests. Compacting conversation history reduces token consumption and helps conversations stay within the model context window.
SWE-2 Research Preview in the Agent Selector
SWE-2, Cognition's next-generation software engineering model, is rolling out as a research preview in the agent selector under the "Research preview" section. Choose SWE-2 and a reasoning effort (Medium, High, or Max) when starting a session, or switch to it mid-session with the agent toggle next to the message input; in Slack, use !swe2 .
npx devin-review CLI Retired
The standalone npx devin-review command-line tool and its unauthenticated review page have been removed. Use Devin Review on the PR tab or in the Devin Review home instead; existing installed copies of the CLI will no longer work.
More from AlloyDBEvery AlloyDB release →
AlloyDB audit log pipeline status available in Cloud Monitoring
AlloyDB for PostgreSQL instances and nodes now expose the status, throughput and backlog of the audit logging pipeline in Cloud Monitoring.
AlloyDB real-time BigQuery access adds limit pushdown and runtime projects
The preview feature pushes some LIMIT and OFFSET clauses down to BigQuery to cut network transfer, and optional runtime projects let queries run and bill compute separately from the owning project.
Lakehouse federation in AlloyDB is generally available ( GA )
Lakehouse federation in AlloyDB is generally available ( GA ). This feature lets you query live data in BigQuery directly from AlloyDB using the bigquery_fdw extension without moving or duplicating the data. For more information, see Access to real-time data in BigQuery overview and Configure access to real-time data in BigQuery .
MCP Toolbox for Databases adds AlloyDB observability and query insights
The Model Context Protocol Toolbox for Databases can now access AlloyDB observability features and advanced query insights directly from an IDE.
AlloyDB AI functions for data extraction and classification in preview
AlloyDB AI now offers preview functions for extracting structured data and classifying text directly within database queries. The update also includes parameter renaming and new instructions for AI query engine functions.
AlloyDB AI and vector search features are generally available
AlloyDB now provides general availability for four-level ScaNN vector indexes on PostgreSQL 17, supporting up to 10 billion rows. It also includes automatic index maintenance and streaming functionality for improved recall on filtered searches.
IAM group authentication is generally available for AlloyDB
IAM group authentication is now generally available for AlloyDB clusters running PostgreSQL 15 and later. This allows administrators to manage database roles and privileges at the group level.
AlloyDB AI adds pre-registered Gemini and reranking models in extension 1.6.5
AlloyDB AI version 1.6.5 adds support for newer Gemini models and the semantic-ranker-512 model while setting gemini-3.5-flash-lite as default.