Releasesby GlyphQdrant 1.18.3
Change log Bug Fixes #9882 - Fix query errors when using shard keys while resharding
Also shipped Jul 17, 2026Qdrant in July 2026 →
Databricks Genie app in Microsoft Teams is now in Public Preview
The Databricks Genie app in Microsoft Teams is now in Public Preview . The app brings Genie into Microsoft Teams so users can ask data questions and get answers without leaving Microsoft Teams. See Databricks Genie app in Microsoft Teams .
Anthropic managed ingestion connector (Beta)
The Anthropic connector in Lakeflow Connect is now available in Beta. The connector allows you to ingest Compliance API data , audit activity, organizations, users, roles, groups, settings, and Claude chats and messages , from Anthropic into Databricks. See Anthropic connector .
Data lineage ingestion control is GA for BigQuery, Spark and Airflow
Data lineage can now be controlled at the organization, folder or project level for BigQuery, Managed Service for Apache Spark and Managed Service for Apache Airflow.
Gemini 3.1 Flash Image Preview and 3 Pro Image Preview are retired
The Nano Banana preview models gemini-3.1-flash-image-preview and gemini-3-pro-image-preview have been retired and are no longer accessible. Update your code to use either gemini-3.1-flash-image or gemini-3-flash-image instead.
[Launched] Generally Available: Microsoft Defender security assessments for Azure Database for PostgreSQL Flexible Server
Microsoft Defender Cloud Security Posture Management (CSPM) assessments for Azure Database for PostgreSQL Flexible Server are now generally available. You can use assessments to continuously evaluate the security posture of your Azure PostgreSQL flexible
Legacy Claude Console Workbench sunsets on August 17, 2026
Access to the legacy Workbench ends August 17, 2026, and saved prompts, variables and evals are not supported in the updated Workbench. Export any data you want to keep from the banner or Organizational Settings.
More from QdrantEvery Qdrant release →
Qdrant 1.19.0
Change log Features ☝️ https://github.com/qdrant/qdrant/milestone/50 - TurboQuant 4-bit as a datatype of primary vector storage. Only store 4-bit quantized vectors and spare disk space on original vectors. [ docs ] #9669 , #9684 , #9950 - Unify definition of memory usage strategy for collection components.
Qdrant 1.18.2
Change log Improvements #9282 - Log slow operations during shard WAL recovery #9137 - Clear cache of ID tracker after building a segment #9138 - Don't rebuild payload index if changing on_disk flag Bug Fixes #9285 - Fix potential infinite loop in optimizer when using multi vectors with prevent_unoptimized #9217 - Clean up unfinished segment optimizations on...
Qdrant 1.19.1
Change log Improvements #10342 , #10420 - Speed up and saturate memory bandwidth in quantized scoring with prefetching #10391 , #10392 , #10362 , #10437 , #10439 , #10381 - Rework and batch 4-bit TurboQuant SIMD implementation for better performance #10441 - Limit query plane allocations for better search performance #8650 - Improve L2 cosine preprocessing...
Qdrant 1.18.1
Change log Improvements #8988 - Refactor quantized multi-vector scorers for io_uring support #9058 - Validate vector dimensions before WAL write for async upserts Bug Fixes #8990 - Notify pending consensus ops on snapshot apply #9054 - Fix indexed integer range filter with float values #9055 - Fix {match: {except: []}} returning zero results with payload...
Qdrant 1.18.0
Change log Features 🏎️ milestone!48 - Add TurboQuant quantization variant, 8x vector compression without the recall tax #8605 - Add API to create and delete named vectors in existing collection #8606 - Deep memory reporting, show memory usage breakdown for storage components #8714 - Add low memory mode, force open everything on disk to minimize out of...
Qdrant 1.19.2
Change log Improvements - - Don't rewrite full sparse posting list on every upsert, making sparse vector upserts significantly faster - , , , - Make proxy segments persist their state, prevents WAL pinning and long recovery times on restart - - Fix HNSW builds not always saturating all assigned threads - - Resolve filter IDs only once per search request...
Qdrant 1.20.0
Qdrant 1.20.0 adds BM25 scoring, TurboQuant vector datatypes, per-element payload indexes, and improved HNSW performance.
Qdrant 1.17.1
Change log Improvements milestone#46 - Defer point updates, efficiently apply and optimize points with prevent_unoptimized=true #8188 - Make Gridstore flushes non-blocking to reduce search tail latencies #8235 - Improve performance of filtered search in case of singular payload value #8402 - Add request tracing ID into audit log #8460 - Propagate WAL errors...