[14/N][RAG Demo fixes] [dev] run 5 trials over 4 queries

cookbooks/RAG-with-Model-Graded-Eval-v2/rag.aiconfig.yaml

@@ -76,16 +76,19 @@ metadata:
     remember_chat_context: false
 name: Rag Demo With Model-graded Eval
 prompts:
-- input: "Answer the following question using the provided context. Question: {{query}}\
-    \ \nContext: {{context}}"
+- input: "Answer the following question using the provided context. \n\nQuestion:\
+    \ {{query}} \nContext: {{context}}"
   metadata:
-    model: gpt-3.5-turbo
+    model:
+      name: gpt-3.5-turbo-16k-0613
+      settings: {}
     parameters: {}
     remember_chat_context: false
   name: generate
   outputs: []
 - input: "Given the following question, and answer, does the answer satisfactorily\
-    \ answer the question? \n\nQuestion: {{query}}\nAnswer: {{generate.output}}"
+    \ answer the question? \n\nGive a relevance verdict (YES or NO) with an explanation.\n\
+    \nQuestion: {{query}}\nAnswer: {{generate.output}}\n\nVerdict:\nExplanation:"
   metadata:
     model: gpt-4
     parameters: {}
@@ -103,15 +106,31 @@ prompts:
   name: evaluate_faithfulness
   outputs: []
 - input: 'Given the following answer, is the answer self-consistent and easy to understand?
-    Answer: {{generate.output}}'
+    Answer: {{generate.output}}
+
+
+    Give a relevance verdict (YES or NO) with an explanation.
+
+
+    Verdict:
+
+    Explanation:'
   metadata:
     model: gpt-4
     parameters: {}
     remember_chat_context: false
   name: evaluate_coherence
   outputs: []
 - input: 'Given the following answer, is the answer self-consistent and easy to understand?
-    Answer: {{generate.output}}'
+    Answer: {{generate.output}}
+
+
+    Give a succinctness verdict (YES or NO) with an explanation.
+
+
+    Verdict:
+
+    Explanation:'
   metadata:
     model: gpt-4
     parameters: {}