update running examples with new metric lists

Signed-off-by: lilacheden <[email protected]>

examples/evaluate_rag_end_to_end_dataset_with_given_predictions.py

@@ -45,11 +45,21 @@
     },
 ]
 
+# select recommended metrics according to your available resources.
+metrics = [
+    "metrics.rag.end_to_end.recommended.cpu_only.all",
+    # "metrics.rag.end_to_end.recommended.small_llm.all",
+    # "metrics.rag.end_to_end.recommended.llmaj_watsonx.all",
+    # "metrics.rag.end_to_end.recommended.llmaj_rits.all"
+    # "metrics.rag.end_to_end.recommended.llmaj_azure.all"
+]
+
 dataset = create_dataset(
     task="tasks.rag.end_to_end",
     test_set=dataset,
     split="test",
     postprocessors=[],
+    metrics=metrics,
 )
 
 results = evaluate(predictions, dataset)

examples/evaluate_rag_response_generation.py

@@ -58,13 +58,23 @@
     ),
 )
 
+# select recommended metrics according to your available resources.
+metrics = [
+    "metrics.rag.response_generation.recommended.cpu_only.all",
+    # "metrics.rag.response_generation.recommended.small_llm.all",
+    # "metrics.rag.response_generation.recommended.llmaj_watsonx.all",
+    # "metrics.rag.response_generation.recommended.llmaj_rits.all"
+    # "metrics.rag.response_generation.recommended.llmaj_azure.all"
+]
+
 # Verbalize the dataset using the template
 dataset = load_dataset(
     card=card,
     template_card_index="simple",
     format="formats.chat_api",
     split="test",
     max_test_instances=10,
+    metrics=metrics,
 )