Turn your LLM pipeline into a transparent, step-by-step experience that shows retrieval, prompt creation, and model calls in real time. Powered by Quarkus, LangChain4j, and Granite4 on Ollama.
Sir could you please share one thread for embedding process and saving the data into vectordb using quarkus. I am building artifacts management but I have to switch to js echosystem only for embedding .
Hi! Absolutely. You might also wanna check this post which does the embedding generation process. Should be straight forward to add a vectordb to this:
Appreciate it Markus! The article was clear . I’ll try extending it to push the embeddings into Qdrant for semantic search in a Quarkus service. Thanks again!
Sir could you please share one thread for embedding process and saving the data into vectordb using quarkus. I am building artifacts management but I have to switch to js echosystem only for embedding .
Hi! Absolutely. You might also wanna check this post which does the embedding generation process. Should be straight forward to add a vectordb to this:
https://www.the-main-thread.com/p/java-quarkus-text-embeddings-similarity
Appreciate it Markus! The article was clear . I’ll try extending it to push the embeddings into Qdrant for semantic search in a Quarkus service. Thanks again!