0.15.0

🚀 Enhancement

• Enable multiple prefixes per index #471 (@rbs333)
• Add Python 3.14 support #468 (@abrookins @vishal-bala)
• Expose max_distance as an optional setting in multi vector queries #478 (@justin-cechmanek)

🐛 Bug Fix

• fix: avoid NLTK download race condition in parallel test workers #477 (@bsbodden)

CI/CD

• ci: Use correct env variable for git name/email #509 (@vishal-bala)
• ci: Add app ID and repo owner to workflow #507 (@vishal-bala)
• ci: Use Applied AI release bot token to create release commits #506 (@vishal-bala)
• ci: Remove deprecated auto configuration field #505 (@vishal-bala)
• ci: Enable automated releases with auto workflow #504 (@vishal-bala)
• ci: Minor adjustment to test automated releases #503 (@vishal-bala)
• ci: Implement automated releases with auto (dry-run for now) #482 (@vishal-bala)

📝 Documentation

• docs: Add note about automated version bumps #510 (@vishal-bala)
• docs: integrate redis-ai-resources examples into documentation #481 (@nkanu17)
• docs: Update terminology from 'hybrid queries' to 'complex filtering' #472 (cloud-agent@localhost @tylerhutcherson @jeremyplichta)
• docs: Enhance user guide structure with improved navigation and content #474 (cloud-agent@localhost @tylerhutcherson @nkanu17 @jeremyplichta)

Contributors

• Andrew Brookins (@abrookins)
• Brian Sam-Bodden (@bsbodden)
• Jeremy Plichta (@jeremyplichta)
• Justin Cechmanek (@justin-cechmanek)
• nitin (@nkanu17)
• Robert Shelton (@rbs333)
• Tyler Hutcherson (@tylerhutcherson)
• Vishal Bala (@vishal-bala)

0.14.0

Changes

• Feat/sql redis query (#467)
• Fix index clear (#463)
• ci: Minor clean-ups for GH Actions workflow for testing fork PRs (#466)
• ci: Enable GH Actions testing for forked PRs (#462)
• Patch/dtype vectorizer from dict (#461)

🐛 Bug Fixes

• fix: Avoid catching non-exception; skip retry for ValueErrors from VertexAI (#470)

Contributors

We'd like to thank all the contributors who worked on this release!

@dfroger, @rbs333 and @vishal-bala

0.13.2

This releases fixes a bug where the redisvl.utils.vectorize module had an unintentional dependency on the botocore package.

0.13.0

Changes

New Features

• Added HybridQuery interface for FT.HYBRID search command introduced in Redis 8.4.0 (#447, #455)
• Added support for multimodal embeddings in vectorizers, with implementations for Amazon Bedrock, Vertex AI, Voyage AI (#452)

Enhancements

• Added support for item-specific TTLs to the LangCache semantic cache implementation (#442)
• Added support for wildcard pattern matching for Tag filters using the modulo (%) operator (#454)

Fixes

• Fixed inconsistent outputs between SemanticCache().check and .acheck (#446)
• Fixed logging issues in packages importing RedisVL caused by the root logger being configured (#445)
• Fixed a bug where redisvl.extensions.message_history.schema.ChatMessage ID-generation could encounter collisions if multiple messages were added rapidly with the same timestamp, resulting in potential message loss (#450)
• Fixes a bug where setting a TTL on async pipelines would prematurely initialize the pipeline and delete queued commands (#420)

Docs

• Fixed documentation to reflect that Redis COSINE distance thresholds use the range [0-2], not [0-1] (#451)

Contributors

We'd like to thank all the contributors who worked on this release!

@abrookins, @dfroger, @nkanu17 and @vishal-bala

0.12.1

Changes

• Add runtime parameter support for HNSW and SVS-VAMANA vector indexes (#439)

Contributors

We'd like to thank all the contributors who worked on this release!

@nkanu17

0.12.0

Changes

New Features

• Add index level stopwords support in configuration in index schema (#436)

Bug fixes

• Fix more problematic attribute values for LangCache (#438)
• Decode LangCache attribute values on retrieval (#437)
• Ensure field modifiers (schema) follow canonical order for RediSearch parser (#434)

Contributors

We'd like to thank all the contributors who worked on this release!

@abrookins and @nkanu17

0.11.1

Changes

Fixes

• Fix LangCache clear() 400 error by using flush() API (#428)

Tests

• Add LangCache integration tests (#429)

Docs

• Fix broken links to hash and json data types (#421)
• Fix broken link in VectorQuery docs (#426)

Contributors

We'd like to thank all the contributors who worked on this release!

@Copilot, @abrookins, @copilot-swe-agent, @nicoweidner and @vinaykulk621

0.11.0

Changes

New Features

• Add LangCache integration (LLM cache extension) (#408, #418)
• Add SVS-VAMANA implementation (#404)

Enhancements

• Add optional text word weights to HybridQuery and TextQuery (#410)
• Vector objects automatically convert vectors to byte strings (#411)

Fixes

• Rename HybridQuery to AggregateHybridQuery (#422)
• Fix flaky text word weights (#416)
• Fix typo in doc string (#414)
• Fix inconsistent FLAT/HNSW algorithm recommendations (#409)

Docs

• Remove duplicate embeddings cache reference in the API docs (#413)
• Adds user guide on advanced query classes (#406)

Contributors

We'd like to thank all the contributors who worked on this release!

@abrookins, @justin-cechmanek and @nkanu17

0.10.0

Changes

• Adds multi vector query class (#402)

Contributors

We'd like to thank all the contributors who worked on this release!

@justin-cechmanek and @rbs333

0.9.1

Changes

• refactor: obtain version information dynamically from the installed p… (#401)
• release: bump version to 0.9.1 (#400)

Contributors

We'd like to thank all the contributors who worked on this release!

@bsbodden