AI Devtools Radar

Weaviate

Vector databasesweaviate.io16 published changes

2 sources under watch

Change timeline

api

Hybrid search endpoint now accepts caller-supplied vectors

Extends hybrid search API flexibility by allowing users to provide custom vectors rather than only computed ones.

Evidence
+rest search: accept a caller-supplied vector on the hybrid endpoint

github.com

deprecationhigh

Remove support for restoring old backup formats

Users with old backup formats will no longer be able to restore them; users need to upgrade their backup formats before updating to this version.

Evidence
+Remove support for restoring old backup formats by @dirkkul in #12338

github.com

other

v1.39.11 release with queue, backup, shutdown reliability fixes and security patch

Users get bug fixes for queue batch replay, backup recovery, shutdown handling, and a zlib CVE security patch

Evidence
+v1.39.11 - Queue, backup and shutdown reliability fixes, plus a zlib CVE patch

github.com · also seen at 1 more source

featurehigh

Namespaces feature reaches general availability (GA)

Users can now use namespaces as a stable, production-ready feature in Weaviate v1.40.0

Evidence
+Namespaces (GA)

github.com

feature

LSM store performance improvements and HNSW ACORN & HFresh index fixes in v1.39.6

Users running Weaviate will benefit from improved LSM store performance and fixes to HNSW index implementations.

Evidence
+v1.39.6 - LSM store performance improvements, HNSW ACORN & HFresh index Fixes

github.com

other

Added LICENSE_KEY_FILE as alternative configuration option for license key management

Users can now provide license keys via file reference (LICENSE_KEY_FILE) in addition to direct environment variable (LICENSE_KEY), improving security and deployment flexibility.

Evidence
+Add LICENSE_KEY_FILE as an alternative to LICENSE_KEY

github.com

pricinghigh

Dedicated cluster pricing structure changed from fixed $400/month to contact sales model

Users seeking dedicated clusters must now contact sales instead of seeing upfront pricing; pricing transparency reduced for dedicated tier.

Evidence
−Starts at$400 /mo from $400 / month
+Dedicated | SharedContact sales for more information

weaviate.io

deprecation

Removal of /v1/modules endpoint and contextionary extension/concept handlers

Users relying on the /v1/modules endpoint, contextionary extensions, or concept handlers will need to update their integration code. This API endpoint is no longer available.

Evidence
+modules(rest): remove /v1/modules endpoint and contextionary extension/concept handlers

github.com

feature

Added DigitalOcean generative module for AI-powered text generation

Users can now use DigitalOcean as a generative AI provider within Weaviate

Evidence
+feat(generative-digitalocean): add DigitalOcean generative module by @antas-marcin in #12786

github.com

other

Bug fixes for backup chunk integrity, usage module, and async replication

Improves reliability and performance of backup operations, usage tracking, and replication features.

Evidence
+v1.38.9 - Backup chunk integrity, usage module and async replication fixes

github.com

feature

Added TwelveLabs Marengo multimodal vectorizer (multi2vec-twelvelabs)

Users can now use TwelveLabs Marengo for multimodal vectorization in Weaviate applications.

Evidence
+feat(multi2vec-twelvelabs): add TwelveLabs Marengo multimodal vectorizer by @antas-marcin in #12370

github.com

feature

Add support for cross-property AND matching in BM25 search

Users can now perform more sophisticated BM25 searches across multiple properties with AND matching logic.

Evidence
+feat: add support for cross-property AND matching in BM25 search

github.com

other

Weaviate v1.38.7 released with bug fixes and internal improvements

Users who deploy Weaviate will receive fixes for range results, namespace handling, backup deduplication, vector index initialization, and performance improvements

Evidence
+v1.38.7 - Never use a search result as a read-repair payload

github.com

pricing

SLA uptime guarantee reduced from 99.95% to 99.9%

Customers on paid tiers will receive a lower service level guarantee, meaning slightly more acceptable downtime in service agreements.

Evidence
−99.95%
+99.9%

weaviate.io

apihigh

New REST near-text search endpoint added: POST /v1/search/{collection}/near-text

Developers can now use a dedicated REST endpoint for near-text search operations, expanding API capabilities for semantic search use cases.

Evidence
+feat(rest): POST /v1/search/{collection}/near-text — REST near-text search endpoint by @g-despot in #12077

github.com

other

v1.38.5 released with LSM store performance improvements and batch vectorization deadlock fix

Users get bug fixes and performance improvements, particularly for LSM operations and batch vectorization which were causing deadlocks.

Evidence
+v1.38.5 - LSM store performance improvements, Batch vectorization potencial deadlocks Fix, Allocation free reference cacher improvement

github.com