data-extraction-langchain4j: Add an illustration schema

data-extract-langchain4j/README.adoc

@@ -12,10 +12,13 @@ For instance, let's imagine an insurance company that would record the transcrip
 There is probably a lot of valuable information that could be extracted from those conversation transcripts.
 In this example, we'll convert those text conversations into Java Objects that could then be used in the rest of the Camel route.
 
+image::schema.png[]
+
 In order to achieve this extraction, we'll need a https://en.wikipedia.org/wiki/Large_language_model[Large Language Model (LLM)] that natively supports JSON output.
 Here, we arbitrarily choose https://ollama.com/library/codellama[codellama] served through https://ollama.com/[ollama].
-In order to invoke the served model, we'll use the high-level LangChain4j APIs like https://docs.langchain4j.dev/tutorials/ai-services[AiServices].
-As we are using the Quarkus runtime, we can leverage all the advantages of the https://docs.quarkiverse.io/quarkus-langchain4j/dev/index.html[Quarkus LangChain4j extension].
+In order to request inference to the served model, we'll use the high-level LangChain4j APIs like https://docs.langchain4j.dev/tutorials/ai-services[AiServices].
+More precisely, we'll setup the https://docs.quarkiverse.io/quarkus-langchain4j/dev/index.html[Quarkus LangChain4j extension] to register an AiService bean.
+Finally, we'll invoke the AiService extraction method via the https://camel.apache.org/camel-quarkus/latest/reference/extensions/bean.html[Camel Quarkus bean extension] .
 
 === Start the Large Language Model