Releases: quarkiverse/quarkus-langchain4j
Releases Β· quarkiverse/quarkus-langchain4j
0.15.0
What's Changed
- Fix bearer pattern for logging Azure requests by @geoand in #601
- Add default values for URLS of HuggingFace models by @geoand in #604
- Rename csv-chatbot to sql-chatbot by @jmartisk in #605
- Restructure the code of the repository by @geoand in #606
- Polish AiServicesRecorder by @geoand in #608
- Add an example of use of image description using GPT-4o by @geoand in #614
- Update to LangChain4j 0.31.0 by @geoand in #622
- Simplify OpenTelemetry instrumentation code by @geoand in #623
- Fix issue with reload when tools are new added by @geoand in #629
- Mistral listed twice in nav by @edeandrea in #641
- Remove erroneously added service file by @geoand in #645
- make vertexai.gemini timeout configurable by @exaV in #640
- Watch files configured in
@SystemMessage
or@UserMessage
by @geoand in #639 - Bump org.assertj:assertj-core from 3.25.3 to 3.26.0 by @dependabot in #627
- Allow dynamic authorization headers for OpenAI + Azure OpenAI by @csotiriou in #646
- Introduce a way to configure tools per method of an AiService by @geoand in #613
Full Changelog: 0.14.1...0.15.0
0.14.2
0.14.1
What's Changed
- Refactor jokes jbang bot to be picocli based by @iocanel in #571
- Properly configure for embedding model by @csotiriou in #597
- Fix update sample version when releasing by @iocanel in #596
- Allow multi-deployment configuration for Azure OpenAI by @csotiriou in #598
Full Changelog: 0.14.0...0.14.1
0.14.0
What's Changed
- Fix configuration error in Gemini by @exaV in #558
- Upgrade to Quarkus Antora 0.0.4 - fix podman issues by @ppalaga in #533
- Bump org.mvnpm.at.mvnpm:vaadin-webcomponents from 24.3.11 to 24.3.12 by @dependabot in #553
- Bump io.quarkiverse.wiremock:quarkus-wiremock-test from 1.3.1 to 1.3.2 by @dependabot in #526
- Include instruction for docker users in email-me-a-poem readme by @iocanel in #562
- Drop uneeded MyChatModelSupplier from email-me-a-peom by @iocanel in #565
- Add minimal html UI for email me a peom by @iocanel in #564
- Fix distance fraud detection by @iocanel in #568
- Fix description of email-me-a-poem by @iocanel in #561
- Setup now ensures there are frauds to report by @iocanel in #566
- Add hints in the triage review page by @iocanel in #570
- Add documentation on using authentication headers with Ollama by @geoand in #573
- Fix the poem and triage samples by @cescoffier in #574
- When there is a single SystemMessage expose set it to dev ui. by @iocanel in #572
- Add missing guide link in extensions by @iocanel in #576
- Use vaadin progress bar in dev-ui embedding store by @iocanel in #575
- Introduce a new foundation for Dev Services like experience by @geoand in #557
- Apply model constraints to image ui combos by @iocanel in #579
- Improve email-me-a-poem ui by @iocanel in #582
- Bump org.mvnpm.at.mvnpm:vaadin-webcomponents from 24.3.12 to 24.3.13 by @dependabot in #583
- Update review triage sample by @geoand in #584
- Fix name in VertxAiGeminiRestApi by @geoand in #587
- Use GPT 4o in fraud detection sample by @geoand in #586
- Introduce preloading of models for Ollama by @geoand in #585
- Add docs about using Podman AI Lab by @geoand in #588
- Make token limit configuration for Ollama optional by @geoand in #589
- Introduce global timeout configuration by @geoand in #593
- Segregate memory of concurrent requests to different AI services by @geoand in #594
New Contributors
Full Changelog: 0.13.1...0.14.0
0.13.1
0.13.0
What's Changed
- Bump org.apache.maven.plugins:maven-compiler-plugin from 3.12.1 to 3.13.0 by @dependabot in #516
- Ability to turn off ingestion with Easy RAG by @jmartisk in #518
- Introduce dependabot updates for samples by @geoand in #517
- Move BAM APIs version to 2024-04-15 by @andreadimaio in #520
- Add a Redis based chat memory store extension by @sebastienblanc in #429
- Improve a few things in websockets.adoc by @gsmet in #521
- Make sure the bot knows its name in samples by @geoand in #524
- Use @default literal instance by @geoand in #525
- Remove timestamps from chat messages for now by @jmartisk in #528
- Improve the Easy RAG documentation by @jmartisk in #530
- Introduce initial support for Google's Palm2 chat model by @geoand in #531
- Make Vertex AI module testable by @geoand in #532
- Introduce initial support for Google's Gemini chat model by @geoand in #534
- Properly catch JSON-RPC errors when adding embeddings by @jmartisk in #537
- Introduce global logging properties by @geoand in #536
- Add a little tip about quarkus.langchain4j.log-requests/responses by @jmartisk in #538
- feat: β¨ ollama streaming mode by @philippart-s in #522
- Use proper Ollama API for chats by @geoand in #543
- Add new parameters to the watsonx.ai chat model by @andreadimaio in #544
- Move the parsers out of the core module by @geoand in #546
Full Changelog: 0.12.1...0.13.0
0.12.1
What's Changed
- Add READMEs to all samples by @jmartisk in #499
- Improve user experience for samples by @geoand in #500
- Override the maven-compiler-plugin version in the samples by @jmartisk in #503
- JBang sample by @jmartisk in #504
- One forgotten compiler-plugin.version override by @jmartisk in #506
- Turn off built-in fault tolerance by default by @jmartisk in #507
- Update websockets.adoc by @gastaldi in #509
- Use pattern matching to simplify OpenAI REST code by @geoand in #502
- fix: π fix NPE if chunk is null for Mistral AI by @philippart-s in #510
- Bump org.wiremock:wiremock-standalone from 3.5.3 to 3.5.4 by @dependabot in #490
- Enable Embedding API in watsonx.ai by @andreadimaio in #508
Full Changelog: 0.12.0...0.12.1
0.12.0
What's Changed
- Mask the value of Set-Cookie headers by @jmartisk in #471
- Bump org.mvnpm.at.mvnpm:vaadin-webcomponents from 24.3.10 to 24.3.11 by @dependabot in #474
- Bump org.wiremock:wiremock-standalone from 3.5.2 to 3.5.3 by @dependabot in #470
- Bump org.mvnpm:lit from 3.1.2 to 3.1.3 by @dependabot in #469
- Improve testing coverage of multi-model cases by @geoand in #477
- Remove embedding model build item by @jmartisk in #480
- Added responseFormat to Azure OpenAi Chat Model by @UnvirtualHH in #483
- Allow user message to be a template by @geoand in #484
- Improve the csv-chatbot sample by @geoand in #485
- Fix the documentation about the memory of
@RegisterAiService
by @geoand in #486 - Add support for Azure AD Tokens by @csotiriou in #467
- Add qualifier to InProcessEmbeddingStore when needed 2 by @humcqc in #488
- Fix duplicate method exception when registering ai services by @iocanel in #492
- Add integration module with quarkus-websockets-next by @geoand in #487
- disable antora until having proper working solution by @maxandersen in #496
New Contributors
- @UnvirtualHH made their first contribution in #483
- @csotiriou made their first contribution in #467
Full Changelog: 0.11.1...0.12.0
0.11.1
0.11.0
What's Changed
- Use Quarkus Antora for testing and live-editting of the docs by @ppalaga in #459
- Easy RAG: ability to configure the path matcher and recursion by @jmartisk in #460
- Introduce Anthropic module (+ bump to LangChain4j 0.30) by @edeandrea in #438
Full Changelog: 0.10.4...0.11.0