- New version of RAG_SPECIALIST and RAG_AGENT, including definition of conversation_purpose and response_depth.

config/tasks/globals/RAG_TASK/1.1.0.yaml

@@ -3,24 +3,29 @@ name: "RAG Task"
 task_description: >
   Answer the following question (in between triple £):
   
-  £££{question}£££
+  £££
+  {question}
+  £££
   
   Base your answer on the following context (in between triple $): 
   
-  $$${context}$$$
+  $$$
+  {context}
+  $$$
   
   Take into account the following history of the conversation (in between triple €):
   
-  €€€{history}€€€
+  €€€
+  {history}
+  €€€
   
   The HUMAN parts indicate the interactions by the end user, the AI parts are your interactions.
   
   Best Practices are:
   
-  - Answer the provided question as precisely and directly as you can, combining elements of the provided context.
-  - Always focus your answer on the actual HUMAN question.
-  - Try not to repeat your answers (preceded by AI), unless absolutely necessary. 
-  - Focus your answer on the question at hand.
+  - Answer the provided question, combining elements of the provided context.
+  - Always focus your answer on the actual question.
+  - Try not to repeat your historic answers, unless absolutely necessary.
   - Always be friendly and helpful for the end user.
 
   {custom_description}