live wire
▸Oracle Select AI generates SQL/PGQ for property graphs—but errors if one AI profile mixes graphs with tables or viewsOracle▸Domo’s data team standardizes MCP builds with shared scaffolding; beta toolkits inherit user permissionsDomo▸Databricks proposes five outcome signals for agentic BI—and says dashboard counts and license usage miss decision qualityDatabricks▸One vibe-coded database app needed 56+ human test hours and three repair rounds despite AI Studio’s verification claimsMancas & Mancas / arXiv▸BigQuery AI.IF’s default cost mode trains a local model for most rows—and drops row-error thresholdsGoogle Cloud▸AWS’s multi-tenant data-agent pattern gives the broker Lambda no data permissions; Cognito roles carry Lake Formation scopeAWS Big Data Blog▸Amazon OpenSearch’s optimized engine adds nested agent traces, but AWS reserves it for log analytics—not vector searchAWS▸Two interpretation-based provenance semantics cannot express SQL bag difference, new theorem showsKolaitis / arXiv▸Databricks Feature Views reuse one definition for training and live scoring, but online lookup still returns latest available stateDatabricks▸Databricks Genie’s Slack and Teams previews default channel answers to public, even when viewers lack source-data accessDatabricks▸Snowflake’s two-tool GraphRAG agent beat a seven-tool graph setup 70% to 60% on 22 ontology questionsSnowflake Engineering▸Semantix opens an Apache-2.0 semantic-first data-agent stack, but labels the project WIP and has no release or adoption yetGitHub / icosmos-space▸Confluent defines Streamhouse as shared current state for agents and apps, but says broader semantics and governance are still to comeConfluent▸Graph-repair retrieval cut F1 by 0.126 on one suite; a learned router used fewer tokens than always-on retrieval in all sixLin et al. / arXiv▸Oracle Select AI generates SQL/PGQ for property graphs—but errors if one AI profile mixes graphs with tables or viewsOracle▸Domo’s data team standardizes MCP builds with shared scaffolding; beta toolkits inherit user permissionsDomo▸Databricks proposes five outcome signals for agentic BI—and says dashboard counts and license usage miss decision qualityDatabricks▸One vibe-coded database app needed 56+ human test hours and three repair rounds despite AI Studio’s verification claimsMancas & Mancas / arXiv▸BigQuery AI.IF’s default cost mode trains a local model for most rows—and drops row-error thresholdsGoogle Cloud▸AWS’s multi-tenant data-agent pattern gives the broker Lambda no data permissions; Cognito roles carry Lake Formation scopeAWS Big Data Blog▸Amazon OpenSearch’s optimized engine adds nested agent traces, but AWS reserves it for log analytics—not vector searchAWS▸Two interpretation-based provenance semantics cannot express SQL bag difference, new theorem showsKolaitis / arXiv▸Databricks Feature Views reuse one definition for training and live scoring, but online lookup still returns latest available stateDatabricks▸Databricks Genie’s Slack and Teams previews default channel answers to public, even when viewers lack source-data accessDatabricks▸Snowflake’s two-tool GraphRAG agent beat a seven-tool graph setup 70% to 60% on 22 ontology questionsSnowflake Engineering▸Semantix opens an Apache-2.0 semantic-first data-agent stack, but labels the project WIP and has no release or adoption yetGitHub / icosmos-space▸Confluent defines Streamhouse as shared current state for agents and apps, but says broader semantics and governance are still to comeConfluent▸Graph-repair retrieval cut F1 by 0.126 on one suite; a learned router used fewer tokens than always-on retrieval in all sixLin et al. / arXiv
nl2sql.ai
guideRelease guide

Auto-Ontology 1.2 aligns every deployable surface—but a version bump is not a release note

NVIDIA cut a protected 1.2.0 branch and synchronized its app, APIs, MCP package and Helm images. Operators still need to verify the artifact they deploy.

By The News Desk· Nov 6, 2026the quick take — two AI hosts go live when you do

NVIDIA has cut a protected release/v1.2.0 branch for Auto-Ontology and synchronized the version number across the components operators actually deploy. The Nov. 5 merge updates the backend, ingestion worker and frontend image tags, the Helm chart and app version, both OpenAPI copies, the Python server package, the MCP package and the frontend package to 1.2.0. NVIDIA’s pull request says the release branch was cut from main, so the main branch already contains the 1.2.0 code.

That lockstep matters more than the apparently mechanical diff suggests. Auto-Ontology is not one binary: its chart coordinates separate backend, ingestion and frontend images, while agent integrations can depend on the MCP package and generated API contract. Leaving one surface at 1.1.0 would make it harder to tell whether a client/server mismatch is a product bug or simply a mixed deployment. NVIDIA says the bump was needed so staging charts built from main, the application’s reported version and the next release branch would not continue from 1.1.0.

What operators should verify

Treat 1.2.0 as a deployment set, not as a label to change in one place. Before upgrading, confirm that all three container image references resolve to the intended 1.2.0 artifacts, that the Helm chart reports 1.2.0, and that any separately installed MCP server reports the same package version. If an integration generates clients from the OpenAPI document, regenerate or compare those clients against the 1.2.0 contract rather than assuming compatibility from the server version alone.

There is also an important limit to what this source proves. At the time of this review, GitHub’s releases endpoint returned no formal latest release, and the repository’s visible tag list did not expose a conventional v1.2.0 tag. The branch and merged version bump establish that NVIDIA prepared the 1.2.0 release line; they do not, by themselves, provide a feature changelog or prove that every referenced image is available in every registry and environment.

The practical rule is simple: use the synchronized version map as an upgrade checklist, but wait for—or independently verify—the actual artifacts and release documentation before promoting 1.2.0 into production. The useful news here is not a list of undocumented features. It is that NVIDIA has made component-version drift easier to detect across the semantic layer, its deployment chart and the MCP/API surfaces agents consume.

sources

Filed by The News Desk. Corrections: desk@nl2sql.ai · Our standards →

comments · 0

    Comments are moderated before they appear. Your email is used once to confirm it is you — never shown, never sold. Corrections and questions get an answer from the desk when we have one.

    more from the desk