fix agent framework document (opensearch-project#2385)

Signed-off-by: Yaliang Wu <ylwu@amazon.com>

Author: ylwu-amzn

docs/tutorials/agent_framework/Chatbot_with_RAG.md

@@ -1,8 +1,8 @@
 # Topic
 
-> Agent Framework is an experimental feature released in OpenSearch 2.12 and is not recommended for use in a production environment. For updates on the progress of the feature or if you want to leave feedback, see the associated [GitHub issue](https://github.com/opensearch-project/ml-commons/issues/1161).
+> Agent Framework is GA released in OpenSearch 2.13. To read more details, see the OpenSearch document [Agents and tools](https://opensearch.org/docs/latest/ml-commons-plugin/agents-tools/index/).
 
-> This tutorial doesn't explain what retrieval-augmented generation (RAG) is.
+Read this AWS [retrieval-augmented-generation](https://aws.amazon.com/what-is/retrieval-augmented-generation/) doc to learn more details about RAG.
 
 One of the known limitations of large language models (LLMs) is that their knowledge base only contains information up to the time when the LLMs were trained. 
 LLMs have no knowledge of recent events or your internal data. 

docs/tutorials/agent_framework/RAG_with_conversational_flow_agent.md

@@ -1,14 +1,16 @@
 # Topic
 
-> Agent Framework is an experimental feature released in OpenSearch 2.12 and not recommended for use in a production environment. For updates on the progress of the feature or if you want to leave feedback, see the associated [GitHub issue](https://github.com/opensearch-project/ml-commons/issues/1161).
+> Agent Framework is GA released in OpenSearch 2.13. To read more details, see the OpenSearch document [Agents and tools](https://opensearch.org/docs/latest/ml-commons-plugin/agents-tools/index/).
 
-> This tutorial doesn't explain what retrieval-augmented generation(RAG) is.
+Read this AWS [retrieval-augmented-generation](https://aws.amazon.com/what-is/retrieval-augmented-generation/) doc to learn more details about RAG.
 
 This tutorial explains how to use a conversational flow agent to build  a RAG application by using your 
 OpenSearch data as knowledge base.
 
 Note: You should replace the placeholders with prefix `your_` with your own value
 
+The other way to build RAG/conversational search is using RAG pipeline, see [conversational_search_with_Cohere_Command](../conversational_search/conversational_search_with_Cohere_Command.md)
+
 # Steps
 
 ## 0. Preparation

docs/tutorials/agent_framework/build_your_own_chatbot.md

@@ -1,6 +1,6 @@
 # Topic
 
-> Agent Framework is an experimental feature released in OpenSearch 2.12 and is not recommended for use in a production environment. For updates on the progress of the feature or if you want to leave feedback, see the associated [GitHub issue](https://github.com/opensearch-project/ml-commons/issues/1161).
+> Agent Framework is GA released in OpenSearch 2.13. To read more details, see the OpenSearch document [Agents and tools](https://opensearch.org/docs/latest/ml-commons-plugin/agents-tools/index/).
 
 Some questions require more than one call to an LLM to produce an answer. For example, an LLM can't answer how many errors there are in your log index for last week because its knowledge base does not contain your proprietary data.
 You can use an agent to solve such complex problems. The agent can run tools to obtain more information and send it to the LLM as context.

docs/tutorials/conversational_search/conversational_search_with_Cohere_Command.md

@@ -4,6 +4,8 @@ This tutorial explains how to use conversational search with the Cohere Command
 
 Note: Replace the placeholders that start with `your_` with your own values.
 
+The other way to build RAG/conversational search is using Agent Framework, see [RAG_with_conversational_flow_agent](../agent_framework/RAG_with_conversational_flow_agent.md)
+
 # Steps
 
 ## 0. Preparation