Configuring Chat Operations
Configure the Chat Answer Prompt Operation
The Chat answer prompt operation is a simple prompt request operation to the configured LLM. It uses a plain text prompt as input and responds with a plain text answer.
To configure the Chat answer prompt operation:
-
Select the operation on the Anypoint Code Builder or Studio canvas.
-
In the General properties tab for the operation, enter plain text for the Prompt.
This is the XML configuration for this operation:
<ms-chainai:chat-answer-prompt
doc:name="Chat answer prompt"
doc:id="8ba9d534-f801-4ac7-8a31-11462fc5204b"
config-ref="MuleChain_AI_Llm_configuration"
prompt="#[payload.prompt]"
/>Output Configuration
This operation responds with a JSON payload containing the main LLM response.
This is an example response:
{
"response": "The capital of Switzerland is Bern. It's known for its well-preserved medieval old town, which is a UNESCO World Heritage site. Bern became the capital of Switzerland in 1848. The Swiss parliament, the Federal Assembly, is located in Bern."
}The operation also returns attributes that aren’t within the main JSON payload, which include information about token usage, for example:
{
"tokenUsage": {
"outputCount": 9,
"totalCount": 18,
"inputCount": 9
},
"additionalAttributes": {}
}Configure the Chat Answer Prompt With Memory Operation
The Chat answer prompt with memory operation is useful for retaining conversation history for a multi-user chat operation.
To configure the Chat answer prompt with memory operation:
-
Select the operation on the Anypoint Code Builder or Studio canvas.
-
In the General properties tab for the operation, enter these values:
-
Data
Contains the prompt for the operation.
-
Memory Name
Name of the conversation. For multi-user support, enter the unique user ID.
-
DB File Path
Path to the in-memory database for storing the conversation history.
You can also use a DataWeave expression for this field, for example:
#["/Users/john.wick/Desktop/mac-demo/db/" ++ payload.memoryName]. -
Max Messages
Maximum number of messages to remember for the conversation defined in Memory Name.
-
This is the XML configuration for this operation:
<ms-aichain:chat-answer-prompt-with-memory
doc:name="Chat answer prompt with memory"
doc:id="7e62e70e-eff7-4080-bb20-3d162bb84c39"
config-ref="MuleSoft_AI_Chain_Config"
memoryName="#[payload.memoryName]"
dbFilePath='#["/Users/john.wick/Desktop/mac-demo/db/" ++ payload.memoryName]'
maxMessages="#[payload.maxMessages]">
<ms-aichain:data><![CDATA[#[payload.prompt]]]></ms-aichain:data>
</ms-aichain:chat-answer-prompt-with-memory>Output Configuration
This operation responds with a JSON payload containing the main LLM response, with additional metadata stored in attributes.
This is an example response:
{
"response": "I'm sorry, I do not have access to personal information such as your name."
}The operation also returns attributes that aren’t within the main JSON payload, which include information about token usage, for example:
{
"tokenUsage": {
"outputCount": 13,
"totalCount": 44,
"inputCount": 31
},
"additionalAttributes": {
"memoryName": "memory",
"maxMessages": "2",
"dbFilePath": "/.../memory.db"
}
}