Bump dev.langchain4j:langchain4j from 1.0.0-alpha1 to 1.0.0-beta1

[dependabot]

Bumps dev.langchain4j:langchain4j from 1.0.0-alpha1 to 1.0.0-beta1.

Release notes

Sourced from dev.langchain4j:langchain4j's releases.

1.0.0-beta1

Announcements

• We are deprecating our old ChatLanguageModel.generate(...) and StreamingChatLanguageModel.generate(...) APIs in favour of the new ChatLanguageModel.chat(...) and StreamingChatLanguageModel.chat(...) APIs. We plan to fully migrate all of our chat model integrations to the new chat() API in the upcoming releases. If you have any concerns or comments, please reach out.
• We have started decoupling our modules from OkHttp client. Ollama is the first module that has been migrated as part of this release. When using the langchain4j-ollama dependency, Ollama*Models will now use JDK's HttpClient by default. When using the langchain4j-ollama-spring-boot-starter dependency, Ollama*Models will now use Spring's RestClient. This change reduces unnecessary dependencies, enables out-of-the-box observability and makes it easy to customize supported HTTP clients or integrate other HTTP clients. We plan to migrate a few other modules (OpenAI, Anthropic, Mistral, Hugging Face, etc.) in the future releases. If you have any concerns or comments, please reach out.

Notable Changes

• OpenAI:
  • Ensure O1/O3 models are supported by @​dliubarskyi in langchain4j/langchain4j#2450 and langchain4j/langchain4j#2500
  • Support audio inputs by @​sergioverde90 in langchain4j/langchain4j#2473
• Azure OpenAI: support Structured Outputs in streaming mode by @​jdubois in langchain4j/langchain4j#2334
• AWS Bedrock:
  • Support Converse API by @​tenpigs267 in langchain4j/langchain4j#2404
  • Support Cohere embeddings by @​LucaPizzarelliDev in langchain4j/langchain4j#2319
• Customizable HTTP clients by @​dliubarskyi in langchain4j/langchain4j#2413
• Model Context Protocol:
  • Send the notifications/initialized message by @​jmartisk in langchain4j/langchain4j#2360
  • Ping responses and simplification of McpTransport by @​jmartisk in langchain4j/langchain4j#2394
  • Improvements for error handling by @​jmartisk in langchain4j/langchain4j#2424
  • Integration tests rework by @​jmartisk in langchain4j/langchain4j#2425
  • Support logging by @​jmartisk in langchain4j/langchain4j#2458
• Introduce a strategy for handling tool name hallucinations by @​mariofusco in langchain4j/langchain4j#2460
• MariaDB embedding store integration by @​rusher in langchain4j/langchain4j#2225
• Jina: support late chunking in long-context embedding models by @​ddobrin in langchain4j/langchain4j#2301
• Support ContainsString metadata filter by @​florian-h05 in langchain4j/langchain4j#2344
• Centralise observability/listener logic for chat models by @​dliubarskyi in langchain4j/langchain4j#2403

Breaking Changes

• langchain4j/langchain4j#2450: Removed default values for modelName (gpt-3.5-turbo) and temperature (0.7) for OpenAiChatModel and OpenAiStreamingChatModel. Please set those values explicitly.
• langchain4j/langchain4j#1988: Converted Document and Content into interfaces. If you use Document or Content constructors, please either use the Document.from(...)/Content.from(...) static factories, or use the DefaultDocument/DefaultContent constructors.
• langchain4j/langchain4j#2403:
  • OpenAiStreamingChatModel: in case of errors that happen in the middle of streaming, partial response (everything that was streamed before the error occured) is not propagated into the ChatModelListener.onError() any more in order to simplify the design and implementation. Please reach out if you have any concerns about it.
  • OpenAiChatModel and OpenAiStreamingChatModel: if the maxCompletionTokens property is set, it's value is now not propagated into the ChatModelListener via ChatModelRequest.maxTokens().
• langchain4j/langchain4j#2330: Exceptions due to content policy violation are now propagated from AzureOpenAiImageModel, AzureOpenAiLanguageModel and AzureOpenAiStreamingLanguageModel.
• langchain4j/langchain4j#2436:
• langchain4j/langchain4j#2492: Renamed langchain4j-redis maven artifact into langchain4j-community-redis.
• langchain4j/langchain4j#2466: Moved IllegalConfigurationException from the dev.langchain4j.exception into the dev.langchain4j.service package.

Potentially Breaking Changes

• Ollama: migrated from OkHttp to JDK's HttpClient and Spring's RestClient by @​dliubarskyi in langchain4j/langchain4j#2413 and langchain4j/langchain4j-spring#104
• Chroma: migrate from Gson to Jackson by @​pibizza in langchain4j/langchain4j#1773
• Vespa: migrate from Gson to Jackson by @​Heezer in langchain4j/langchain4j#2056

Updates in the Spring Boot integration

See https://github.com/langchain4j/langchain4j-spring/releases/tag/1.0.0-beta1

... (truncated)

Commits

• 0d64977 Removed concrete DefaultChatRequestParameters type from DefaultChatRequestPar...
• 8076b54 Expose tool service initialization (#2507)
• 45d4131 added missing convenience methods to the chat() API
• d8b5993 Expose tools internals (#2506)
• 4f71e87 deprecated old APIs
• 5c8e9da Fix #2429 (#2504)
• 6fe895f removed AstraDB ITs
• 6f34a64 fixed failing ITs
• 50f7cf7 relaxed jacoco
• b92a6c1 disabled failing tests
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)