add multi model

config/retriex/model.yaml

@@ -18,3 +18,10 @@ parameters:
   # Hard upper bound for generated output tokens. Prevents runaway repeated answers
   # before they can become very long streamed or blocking responses.
   retriex.llm.num_predict: 2048
+
+  # Optional model override per existing LLM call.
+  # null or an empty value keeps the active default model from ModelGenerationConfig.
+  retriex.llm.call_models:
+    input_normalization: null
+    shop_query_optimization: null
+    final_answer: null