Skip to content

0.28.0
Compare
Choose a tag to compare
@langchain4j langchain4j released this 11 Mar 19:14
· 169 commits to main since this release
0.28.0
90fe304
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.

New Integrations

New Core Features

Notable Updates

  • Gemini function calling support by @glaforge in #692
  • Allow reading prompt (both system & user) message from a resource by @gkfirst8 in #527
  • Make the Vertex AI embedding model adapt automatically the number of batch calls to make by @glaforge in #626
  • Add type to array parameter in tool specification by @Wadimz in #624
  • Implement missing parameters in Azure OpenAI by @jdubois in #616
  • Upgrade langchain4j-opensearch to use latest version of opensearch-java client which enables Java 8 support by @Hrvojeee in #663
  • FileSystemDocumentLoader: add possibility to load recursively and with glob/regex filtering by @langchain4j in #657
  • Ability to specify the task type for calculating embeddings by @glaforge in #722

Other Updates

  • fix for issue #633 adding instructions for additional artifact for Op… by @sshaaf in #634
  • [Documentation] Add Mistralai docs by @czelabueno in #623
  • Fill in some details of the Quarkus integration in the docs by @holly-cummins in #632
  • Remove unneeded waiting strategy by @ilopezluna in #647
  • Clarify the mandatory and optional Azure connection parameter by @agoncal in #636
  • Adds a test to check that the API version is set to the latest if incorrect by @agoncal in #635
  • Adding a script to deploy all the needed model to run the integration tests by @agoncal in #629
  • Fixed snapshot release by @langchain4j in #650
  • Bump org.postgresql:postgresql from 42.6.0 to 42.7.2 in /langchain4j-pgvector by @dependabot in #649
  • Updates to Infinispan Dev09 by @karesti in #646
  • Remove direct dependency to the langchain4j-open-ai by @jdubois in #656
  • fix [BUG] QianFanChatModel Not Support SystemMessage by @lane12138 in #648
  • Use Testcontainers Vector Database modules by @eddumelendez in #654
  • Docs: Updated the redundant base route from /docs to / by @amithkoujalgi in #655
  • Add langchain4j-embeddings-all-minilm-l6-v2-q to the BOM by @boris-petrov in #579
  • recursion error on nested POJO extractor by @tenpigs267 in #625
  • Strengthen coverage for DefaultToolExecutor. by @crutcher in #590
  • Bump azure-ai-openai from 1.0.0-beta.6 to 1.0.0-beta.7 by @jdubois in #700
  • Delombok before JavaDoc. by @crutcher in #595
  • use maven.compiler.release instead of source+target by @hboutemy in #617
  • refactor: AssertJ best practices by @timtebeek in #622
  • Bump com.azure:azure-search-documents from 11.6.1 to 11.6.2 by @jdubois in #664
  • Bump azure-storage-common and azure-storage-blob versions by @jdubois in #677
  • docu: added link to Guide to Choosing Quantization Methods and Infere… by @dliubars in #705
  • Bump com.azure:azure-identity from 1.11.2 to 1.11.3 by @jdubois in #695
  • Fix ChatMessage.text() method that is deprecated by @jdubois in #678
  • Throw error if more than one retriever/contentRetriever/retrievalAugm… by @jmartisk in #710
  • Fix #602: Enum values (names) should be sent to the LLM in original case by @langchain4j in #669
  • added missing Javadoc for deprecated methods by @langchain4j in #668
  • Update documentation on Vertex AI by @OTR in #709
  • Add option to specify num_ctx parameter in for ollama. Fixes #682 by @mmanrai in #683
  • Update README.md by @eltociear in #711
  • Fix #585: Automatically evict following orphan ToolExecutionResultMessage(s) after evicting AiMessage containing ToolExecutionRequest(s) by @langchain4j in #666
  • fix #670 by @langchain4j in #716
  • fix #715: Improve Milvus integration performance: load collection in memory only when creating MilvusEmbeddingStore by @langchain4j in #717
  • update okhttp version to 4.12.0 by @langchain4j in #724
  • Fix UserMessage example in AiServices by @theawesomenayak in #719
  • Solve the problem of occasional incomplete response content. by @jiangsier-xyz in #699
  • Fix the check whether retriever is already set by @jmartisk in #728

New Contributors

Full Changelog: 0.27.1...0.28.0

Contributors

glaforge, karesti, and 28 other contributors
Assets 2