Eric Deandrea
In my case too I'm not using the `AllMiniLmL6V2QuantizedEmbeddingModel`. I'm using `OllamaEmbeddingModel`.
That doesn't seem to fix the issue. I'm still seeing it... ``` Error: Tests run: 1, Failures: 0, Errors: 1, Skipped: 0, Time elapsed: 57.22 s
> But I'm not able to progress it any further without access to the cluster :) You just need Ollama running. Run ollama and then run `./mvnw clean verify -Dquarkus.profile=ollama...
It works fine on my laptop. I'm only seeing the issues on Ubuntu linux....
I'm running with Ollama 0.3.12
I really can't disable it for OpenAI because the main use case for this particular app is to use OpenAI. The [README](https://github.com/rh-rad-ai-roadshow/parasol-insurance/blob/main/app/README.md) clearly states how you would run it locally...
It does seem to be somewhat intermittent though. It is running fine at the moment (see https://github.com/rh-rad-ai-roadshow/parasol-insurance/actions/runs/11635289650/job/32404313896), but then all of a sudden it will stop working.
There isn't one that showcases this app in particular, but there was a 3-hour deep dive on LangChain4j and Quarkus that I did along with @cescoffier and @geoand https://devoxx.be/talk/java-meets-ai-build-llm-powered-apps-with-langchain4j/
I'm not sure if this is an issue here in Quarkus Langchain4j, or if its an issue with the MCP server, as I don't see the `anyOf` key anywhere when...
I'm using 0.26.2, but will probably switch to the 0.27 CR today ---------- Sent from a mobile device On Thu, May 15, 2025, 12:52 AM Jan Martiska ***@***.***> wrote: >...