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• Remove an outdated comment by @jmartisk in #878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

0.18.0.CR1

What's Changed

• Check for logStreamingResponses in the QuarkusRestClientBuilder builder. by @dastrobu in #839
• Tavily web search engine integration by @jmartisk in #841
• Add PromptFormatter functionality by @andreadimaio in #830
• Add streamingChatLanguageModelSupplier property to @RegisterAiService by @dastrobu in #844
• Update version in jbang sample by @geoand in #847
• Easy rag sample: move catalog files out of src/main/resources by @jmartisk in #850
• Initial code around the output guardrails idea by @cescoffier in #843
• Drop a jetbrains annotation by @gsmet in #853
• Constrain the build for better compatibility with mvnd by @gsmet in #852
• Filter logs of low value related to djl tokenizers by @gsmet in #858
• Improve pgvector documentation by @gsmet in #857
• Also allow to inject PgVectorEmbeddingStore with upstream type by @gsmet in #855
• Bump org.mvnpm.at.mvnpm:vaadin-webcomponents from 24.4.5 to 24.4.7 by @dependabot in #848
• Bump org.apache.maven.plugins:maven-surefire-plugin from 3.3.1 to 3.5.0 by @dependabot in #832
• [WATSONX] Enable tool functionality for the model llama3.1 by @andreadimaio in #859
• Avoid NPE when converting template param value by @gsmet in #862
• Initial code around the input guardrails idea by @cescoffier in #860
• Bump org.apache.maven.plugins:maven-surefire-plugin from 3.3.1 to 3.5.0 by @dependabot in #865
• Do not log error in AiServiceMethodImplementationSupport by @gsmet in #864
• Bump quarkus-neo4j.version from 4.2.2 to 4.3.0 by @dependabot in #866
• Revert "Upgrade to Quarkus Antora 0.0.4 - fix podman issues" by @maxandersen in #840
• Update to LangChain4j 0.34 by @geoand in #875
• Introduce Easy RAG codestart by @ia3andy in #874

New Contributors

• @ia3andy made their first contribution in #874

Full Changelog: 0.17.2...0.18.0.CR1

0.17.2

What's Changed

• Support LangChain4j's Result return type by @geoand in #824
• fix docs on topP by @dastrobu in #829
• Properly handle resource missing case for user and system messages by @dastrobu in #834
• Add Bearer scheme in the default Vertex AI Gemini authentication filter by @sberyozkin in #835

New Contributors

• @dastrobu made their first contribution in #829

Full Changelog: 0.17.1...0.17.2

0.17.1

What's Changed

• Introduce some basic metadata filtering tests for Milvus by @jmartisk in #806
• Bump org.mvnpm:lit from 3.1.4 to 3.2.0 by @dependabot in #810
• Bump org.mvnpm.at.mvnpm:vaadin-webcomponents from 24.4.4 to 24.4.5 by @dependabot in #807
• Fix #813 to add proxy support for openai by @zhfeng in #814
• Replaced ProfileManager with ConfigUtils to check active profiles. by @fmatar in #812
• Bump quarkus-neo4j.version from 4.2.1 to 4.2.2 by @dependabot in #816
• Bump org.apache.maven.plugins:maven-failsafe-plugin from 3.3.1 to 3.4.0 by @dependabot in #817

New Contributors

• @zhfeng made their first contribution in #814
• @fmatar made their first contribution in #812

Full Changelog: 0.17.0...0.17.1

0.17.0

What's Changed

• Pretty print Ollama responses by @geoand in #785
• Bump quarkus-neo4j.version from 4.2.0 to 4.2.1 by @dependabot in #791
• Make Multi AiService work with RAG by @geoand in #793
• Fix embedding model handling with Easy RAG by @jmartisk in #792
• Introduce the MANUAL ingestion strategy for Easy RAG by @jmartisk in #794
• Bump io.quarkiverse.mailpit:quarkus-mailpit from 1.1.1 to 1.2.1 by @dependabot in #796
• Introduce OllamaModelAuthProvider support to Ollama by @geoand in #798
• Introduce observability into Ollama ChatLanguageModel by @geoand in #799
• Bump io.quarkiverse.mailpit:quarkus-mailpit from 1.2.1 to 1.2.2 by @dependabot in #802
• Introduce @SeedMemory for AiServices by @geoand in #804
• Improve JSON sanitize by @andreadimaio in #803

Full Changelog: 0.17.0.CR1...0.17.0

0.17.0.CR1

What's Changed

• Add prompt-joiner property for watsonx provider by @andreadimaio in #756
• Fix the version in the native script by @dandreadis in #759
• Use newer method for RetrievalAugmentor call in AiService implementation by @geoand in #763
• Bump org.wiremock:wiremock-standalone from 3.8.0 to 3.9.0 by @dependabot in #762
• Bump quarkus-neo4j.version from 4.1.0 to 4.2.0 by @dependabot in #749
• Bump org.mvnpm.at.mvnpm:vaadin-webcomponents from 24.4.2 to 24.4.4 by @dependabot in #769
• Stop skipping Ollama responses with whitespaces by @kucharzyk in #768
• Ensure that @Retry works properly with chat memory by @geoand in #764
• Make gpt-4o-mini the default OpenAI model by @geoand in #772
• Replace Singleton with ApplicationScoped by @emmanuelbernard in #770
• Fix case where Ollama embedding model was not pulled automatically by @geoand in #773
• Use llama3.1 as the default Ollama model by @geoand in #775
• Polish watsonx code by @andreadimaio in #774
• Bump org.wiremock:wiremock-standalone from 3.9.0 to 3.9.1 by @dependabot in #779
• Update to LangChain4j 0.33 by @geoand in #781
• Improve JSON sanitize by @andreadimaio in #780
• Add initial Ollama support for tool invocation by @geoand in #783

New Contributors

• @kucharzyk made their first contribution in #768
• @emmanuelbernard made their first contribution in #770

Full Changelog: 0.16.4...0.17.0.CR1

0.16.4

What's Changed

• Document Ollama and OpenAI compatible serving in samples by @geoand in #753
• Set false as default value for fullText in hugging face config by @GregJohnStewart in #750
• Add observability to AzureOpenAI by @geoand in #752
• Bump io.quarkiverse.mailpit:quarkus-mailpit from 1.1.0 to 1.1.1 by @dependabot in #746
• Bump io.mvnpm:importmap from 1.0.10 to 1.0.11 by @dependabot in #747

New Contributors

• @GregJohnStewart made their first contribution in #750

Full Changelog: 0.16.3...0.16.4

0.16.3

What's Changed

• Bump org.mvnpm.at.mvnpm:vaadin-webcomponents from 24.4.0 to 24.4.2 by @dependabot in #742
• Bump org.apache.maven.plugins:maven-failsafe-plugin from 3.3.0 to 3.3.1 by @dependabot in #741
• Bump org.apache.maven.plugins:maven-surefire-plugin from 3.3.0 to 3.3.1 by @dependabot in #740
• Ollama Role serialization in lower case, fix issue with Ollama 0.2.5 by @humcqc in #744

Full Changelog: 0.16.2...0.16.3