quarkus-langchain4j

quarkus-langchain4j copied to clipboard

Implement embedding filtering where appropriate

3

LangChain4j 0.28 has a new metadata filter API for embedding stores. We should implement that for embedding stores where it is appropriate - for some embedding stores we don't just...

jmartisk

Re-enable native tests for in-process embeddings

1

We disabled them after upgrading to langchain4j 0.28.0: https://github.com/quarkiverse/quarkus-langchain4j/pull/369

jmartisk

RegisterAiService is locked down to ChatLanguageModel

27

Hello, Currently the RegisterAiService cannot find or be configured to use a StreamingChatLanguageModel, it's locked to a "Blocking"ChatLanguageModel It would be nice to have streaming here to write chat bots...

vietk

Updates to avoid code duplication

4

This Pr is related to this one https://github.com/langchain4j/langchain4j/pull/845

karesti

Bumps [org.mvnpm:es-module-shims](https://github.com/guybedford/es-module-shims) from 1.8.2 to 1.8.3. Release notes Sourced from org.mvnpm:es-module-shims's releases. 1.8.3 What's Changed feat: support script fetchPriority by @​guybedford in guybedford/es-module-shims#407 add wasm esm integration polyfill by @​guybedford...

dependabot[bot]

Dev UI page for testing of AI services

5

Currently we have a Chat model page in our Dev UI that injects and uses a raw chat model. That's nice but not extremely useful. Users might want to test...

jmartisk

Integration tests fail non-deterministically in native mode

6

Issue keeps popping up in https://github.com/quarkiverse/quarkiverse/issues/195 Originally seen and discussed in https://quarkusio.zulipchat.com/#narrow/stream/187038-dev/topic/GraalVM.20-.20freezing The issue seems related (although not confirmed yet) to the order in which classes are getting initialized (we...

zakkak

Observability for RAG

4

[This](https://www.rungalileo.io/blog/mastering-rag-how-to-architect-an-enterprise-rag-system) article makes a very good case for adding observability to RAG. We should probably head the advice and add metrics and tracing to our RAG approach

geoand

Retriever is deprecated in favor of ContentRetriever

4

Use ContentRetriever instead of Retriever ``` /** * Interface for retrieving relevant items. * This class is deprecated, use {@link ContentRetriever} instead. * * @param the type of the items....

karesti

Contribute an example with Infinispan

5

The chatbot example works with Infinispan https://github.com/karesti/quarkus-langchain4j/tree/chatbot-infinispan/samples/chatbot-infinispan A diff example might be beneficial to showcase how it works Any ideas ?

karesti