Releasesby Glyphunstructured 0.24.0
- feat: derive category_depth from heading level in the v2 (ontology) HTML parser - fix(ci): stabilize partition benchmark with a rolling-median baseline - refactor: centralize URL fetching with host validation and default timeouts
Also shipped Jul 6, 2026Unstructured in July 2026 →
Budgets are now generally available
Budgets, including budgets for Unity Gateway, are now generally available. Budgets let admins define spending thresholds. For requests managed through Unity Gateway, including Genie interactions, admins can set additional per-user thresholds and overrides, with configurable actions such as email alerting and usage blocking.
Private Link for account-level resources (Beta)
You can now use Private Link to privately connect to Databricks account-level resources, such as the account console, through a VPC interface endpoint instead of the public internet. See Configure inbound Private Link for account-level resources .
July 6, 2026
This serverless compute release includes updates from Databricks Runtime 18 . New features Spark Declarative Pipelines on Lakeflow streaming query ID : Spark Declarative Pipelines on Lakeflow can now set the streaming query ID on demand.
You can use Gemini in Spanner Studio to fix errors in your SQL queries
You can use Gemini in Spanner Studio to fix errors in your SQL queries. When you run a query that contains an error, you can click Fix to view a line-by-line comparison of your query and a recommended correction, along with an explanation of the change. This feature is available in Preview .
Modeling
- Added support for agent-specific AI context via the omni_agent Mustache namespace, allowing you to customize AI behavior on a per-agent basis. See Optimize models for Omni AI for more information.
Self-serve identity provider changes
- New: Users with the Owner role can switch their tailnet's identity provider from the admin console for supported providers ( beta ).
More from unstructuredEvery unstructured release →
unstructured 0.24.1
- fix: sanitize v2 HTML output to prevent stored XSS (GHSA-v5mq-3xhg-98m9)
unstructured 0.25.0
Enhancements - Partition arbitrary JSON and NDJSON: partition_json() and partition_ndjson() now handle any valid JSON/NDJSON payload, not just serialized Unstructured output.
unstructured 0.23.1
- feat: extract filled AcroForm field text in PDF partitioning
unstructured 0.23.0
- fix: stop decimating embedded text on dense PDF pages - fix: keep extracted text aligned with rotated PDF page images in hi_res - feat: add enrichment origins metadata field
unstructured 0.25.2
- Terminology update: Platform -> Pipelines in README - perf(html): use indexed parent lookup - feat: add lazy chunking entry points
unstructured 0.22.32
- fix(hi_res): recover text inside PDF figure overlays
unstructured 0.22.31
- fix: rename isolate_tables chunking option to isolate_table
unstructured 0.22.30
- feat: add option for table chunking