Auto-produce RetrievalAugmentor bridging Camel ingestion with @RegisterAiService RAG

[JiriOndrusek]

When Camel routes ingest documents into an EmbeddingStore (via langchain4j-embeddingstore component), the retrieved knowledge should be available to Quarkus LangChain4j @RegisterAiService for RAG-augmented chat. This adds auto-production of RetrievalAugmentor CDI beans that bridge the two, so they share the same EmbeddingStore instance without explicit user wiring.

Covered scenarios

• Single store + model, no existing RAG: auto-produce a defaultBean() RetrievalAugmentor backed by the @Default store (zero config)
• Single store + model, existing RAG (Easy RAG or user-provided): defaultBean() yields, no conflict
• Multiple stores, no config: auto-produce a default RAG backed by the @Default store
• Multiple stores with config: named RetrievalAugmentor beans via quarkus.camel.langchain4j.rag.augmentors.<name>.embedding-store-name

New files

• RagBridgeConfig — @ConfigRoot(BUILD_AND_RUN_TIME_FIXED) for named augmentor config
• DefaultRetrievalAugmentorSupplier — lazily resolves EmbeddingStore + EmbeddingModel from CDI
• Build steps in SupportQuarkusLangchain4jProcessor
• Integration test module langchain4j-rag-bridge-ql4j

Related

• Benefits from (but does not require) CAMEL-24366 which adds auto-embed to the embeddingstore component