0.21.0.CR1

What's Changed

• Remove BAM module by @andreadimaio in #968
• Add support for BGE 1.5 (regular and quantized) in-process embedding by @cescoffier in #966
• Refactor CI workflows (only pull requests) by @cescoffier in #972
• Bump org.apache.maven.plugins:maven-failsafe-plugin from 3.5.0 to 3.5.1 by @dependabot in #977
• Add clarification about WebSearchRetrievalAugmentor by @jmartisk in #982
• Enable /chat and /chat_stream in watsonx.ai by @andreadimaio in #981
• Split and Reuse the Release workflow by @gastaldi in #986
• Anthropic chat model not available when enabled by @dennysfredericci in #985
• Release workflow names are inverted by @gastaldi in #987
• Enable ScoringModel in watsonx.ai by @andreadimaio in #994
• Use custom integration with Jlama by @geoand in #998
• Enable watsonx.ai to process ImageContent in UserMessage by @andreadimaio in #1000
• Move inner classes to top level classes for API concision by @holly-cummins in #1003
• Allow including configured models in the built artifact for Jlama by @geoand in #1004
• [FEATURE] ToolProvider | Select tools dynamically on incoming message by @MiggiV2 in #989
• Add optional logging to jlama requests and responses by @mariofusco in #999
• Add support for TLS configuration name by @geoand in #1006
• Don't include tools from removed beans in the ToolsMetadata by @jmartisk in #1010
• Properly support TokenStream return type in AiService by @geoand in #1005
• Implement support for output guardrail on streamed responses by @cescoffier in #1011
• Introduce llama3-java module by @geoand in #1008
• Update watsonx module: Add Text Extraction APIs, Configuration changes, and Pretty-Print logging by @andreadimaio in #1013

New Contributors

• @dennysfredericci made their first contribution in #985
• @MiggiV2 made their first contribution in #989

Full Changelog: 0.20.3...0.21.0.CR1

0.20.3

What's Changed

• Fix local embedding tokenizer location by @cescoffier in #960
• Shadows api key from tavily logs by @lordofthejars in #961
• Bump io.quarkiverse:quarkiverse-parent from 16 to 18 by @dependabot in #959
• Move OpenWebUI Dev UI Actions to deployment classpath by @phillip-kruger in #867
• Fix ONNX Runtime Execution in Native Executable by @cescoffier in #964

Full Changelog: 0.20.1...0.20.3

0.20.1

What's Changed

• Extend the chatbot sample to use streaming by @cescoffier in #953
• Upgrade to Quarkus Antora - fix issues on Arm Macs by @ppalaga in #913
• Avoid duplicating info for AiService implementation constructors by @geoand in #955

Full Changelog: 0.20.0...0.20.1

0.20.0

What's Changed

• Fix issue with Image generation in AiService by @geoand in #951

Full Changelog: 0.20.0.CR1...0.20.0

0.20.0.CR1

What's Changed

• Bump to LangChain4j 0.35 by @geoand in #948

Full Changelog: 0.19.0...0.20.0.CR1

0.19.0

What's Changed

• Bump kr.motd.maven:os-maven-plugin from 1.7.0 to 1.7.1 by @dependabot in #933
• Bump quarkus-neo4j.version from 4.3.0 to 4.4.0 by @dependabot in #920
• Use PGVector 17 by @jmartisk in #944
• Fix AiService image generation for named model by @geoand in #945

Full Changelog: 0.19.0.CR3...0.19.0

0.19.0.CR3

What's Changed

• Output guardrails are now called with the new response by @cescoffier in #939
• Fix split package issue in OpenAI modules by @geoand 4515cdb

Full Changelog: 0.19.0.CR2...0.19.0.CR3

0.19.0.CR2

What's Changed

• Bump langchain4j-embeddings.version from 0.34.0 to 0.35.0 by @dependabot in #928
• Revert "Bump langchain4j-embeddings.version from 0.34.0 to 0.35.0" by @geoand in #929
• Add support for Jlama by @jesuino in #882
• Ignore LangChain4j in dependabot config by @geoand in #930
• Make logging for named configurations work as expected by @geoand in #931
• Introduce a way to estimate the cost of an API call by @geoand in #934
• Bump to Quarkus 3.15.1 by @geoand in #935
• Introduce AiService class and method names into GenAI metrics by @geoand in #936

New Contributors

• @jesuino made their first contribution in #882

Full Changelog: 0.19.0.CR1...0.19.0.CR2

0.19.0.CR1

What's Changed

• Don't fail booting in Dev mode when embedding store is configured but… by @jmartisk in #886
• [doc] Fix a typo in the ChatModelConfig by @PierreBtz in #910
• Allow the use of uarkus.langchain4j.ollama.chat-model.model-name by @geoand in #911
• Allow use of dev-services when the base-url points to a local instance by @geoand in #908
• doc: fix wrong property name in pgvector documentation by @benDeMtp in #912
• Enable configuration of AI service method parameters allowed annotations #888 by @aldettinger in #889
• Add the ability to generate images from AI Service by @geoand in #917
• Make AI service parameters ignored annotations configurable by @aldettinger in #919
• Add the ability to describe an image via AiService by @geoand in #918
• Bump Quarkus version to the new LTS by @geoand in #921
• Remove the workaround for Redis embedding search by @jmartisk in #923
• Don't require @ImageUrl if Image is used by @geoand in #922

New Contributors

• @benDeMtp made their first contribution in #912
• @aldettinger made their first contribution in #889

Full Changelog: 0.18.0...0.19.0.CR1

0.18.0

What's Changed

• fix docs on azure-openai config. by @dastrobu in #821
• Remove an outdated comment by @jmartisk in #878
• Bump org.apache.maven.plugins:maven-failsafe-plugin from 3.4.0 to 3.5.0 by @dependabot in #877
• Avoid publishing support modules in Maven Central by @gastaldi in #880
• Bump org.mvnpm.at.mvnpm:vaadin-webcomponents from 24.4.7 to 24.4.8 by @dependabot in #884
• Evaluate 'required' attribute of @p annotation in tool for optional parameters. by @jpohlmeyer in #868
• docs: fix artifact name quarkus-langchain4j-hugging-face by @yugoccp in #891
• Fix primitive handling of AiServices by @geoand in #894
• Hide the 'loading' bubbles in chatbot samples by @jmartisk in #892
• Avoid using exceptions for control flow in guardrail's API by @mariofusco in #883
• Bump org.mvnpm.at.mvnpm:vaadin-webcomponents from 24.4.8 to 24.4.9 by @dependabot in #895
• Update packages of in-process embeddings in the docs by @jmartisk in #899
• Use QueryArgs.param or dialect depending on the Quarkus version by @jmartisk in #901
• Make chat memory available to the system message template by @geoand in #887
• Make the Quarkus version parsing a bit safer by @jmartisk in #903

New Contributors

• @jpohlmeyer made their first contribution in #868
• @yugoccp made their first contribution in #891
• @mariofusco made their first contribution in #883

Full Changelog: 0.18.0.CR1...0.18.0