Data store tool settings

The following data store tool configuration settings are available.

Tool settings (Conversational Agents console only)

Selecting an option from the Tool settingsdrop-down menu automatically affects which other tool configurations are available.

The Default and Optimized for voice options are default settings that will automatically configure all other parameters in the tool configuration menu.

The following options are available:

Grounding

Conversational Agents (Dialogflow CX) calculates a confidence level for each response generated from the content of your connected data stores. This gauges the confidence that all information in the response is supported by information in the data stores. You can adjust which responses are allowed by selecting the lowest confidence level you are comfortable with. You can select the lowest confidence level allowed, and the agent won't return responses lower than that level.

There are 5 confidence levels to choose from: VERY_LOW , LOW , MEDIUM , HIGH , and VERY_HIGH .

You can also apply a grounding heuristics filter. If enabled, responses containing content that is likely inaccurate based on common hallucinations are suppressed.

Select summarization model

You can select the generative model used by a data store agent for the summarization generative request. The following table contains the available options:

All listed models are available in all supported languages and supported regions .

Summarization custom prompt

You can either use a default summarization prompt with your selected summarization model or provide your own. The prompt is a text template that may contain predefined placeholders. The placeholders will be replaced with the appropriate values at runtime and the final text will be sent to the LLM.

The placeholders are as follows:

• $original-query : The user's query text.
• $rewritten-query : Dialogflow uses a rewriter module to rewrite the original user query into a more accurate format.

• $sources : Dialogflow uses Enterprise Search to search for sources based on the user's query. The found sources are rendered in a specific format:

   [1] title of first source
  content of first source
  [2] title of second source
  content of second source 
  

• $end-user-metadata : Information about the user sending the query is rendered in the following format:

   The following additional information is available about the human: {
  "key1": "value1",
  "key2": "value2",
  ...
  } 
  

• $conversation : The conversation history is rendered in the following format:

   Human: user's first query
  AGENT: answer to user's first query
  Human: user's second query
  AGENT: answer to user's second query 
  

• ${conversation USER:"<user prefix>" AGENT:"<agent prefix>" TURNS:<turn count>} : A parameterized version of the $conversation placeholder. You can customize the end-user prefix ( USER ), the agent prefix ( AGENT ), and the number of previous turns to include ( TURNS ). All placeholder parameter values must be specified.

  For example, ${conversation USER:"Human says:" AGENT:"Agent says:" TURNS:1} . The conversation history is rendered as:

   Human says: user's first query
  Agent says: answer to user's first query 
  

A custom prompt should instruct the LLM to return "NOT_ENOUGH_INFORMATION" when it cannot provide an answer. In this case, the agent will invoke a no-match event .

For example:

 Given the conversation between a Human and a AI assistant and a list of sources,
write a final answer for the AI assistant.
Follow these guidelines:
+   Answer the Human's query and make sure you mention all relevant details from
  the sources, using exactly the same words as the sources if possible.
+   The answer must be based only on the sources and not introduce any additional
  information.
+   All numbers, like price, date, time or phone numbers must appear exactly as
  they are in the sources.
+   Give as comprehensive answer as possible given the sources. Include all
  important details, and any caveats and conditions that apply.
+   The answer MUST be in English.
+   Don't try to make up an answer: If the answer cannot be found in the sources,
  you admit that you don't know and you answer NOT_ENOUGH_INFORMATION.
You will be given a few examples before you begin.

Example 1:
Sources:
[1] <product or service> Info Page
Yes, <company> offers <product or service> in various options or variations.

Human: Do you sell <product or service>?
AI: Yes, <company> sells <product or service>. Is there anything else I can
help you with?

Example 2:
Sources:
[1] Andrea - Wikipedia
Andrea is a given name which is common worldwide for both males and females.

Human: How is the weather?
AI: NOT_ENOUGH_INFORMATION

Begin! Let's work this out step by step to be sure we have the right answer.

Sources:
$sources

$end-user-metadata
$conversation
Human: $original-query
AI: 

Select rewriter model

When a user query is processed, the agent sends the user query and a prompt to the LLM to refactor the user query, which performs a rewriter.

You can select the generative model used by a data store agent for the rewriter generative request. The following table lists the available options:

All listed models are available in all supported languages and supported regions .

Rewriter custom prompt

You can use a default prompt or optionally provide your own. The prompt is a text template that may contain predefined placeholders. The placeholders will be replaced with the appropriate values at runtime and the final text will be sent to the LLM.

The placeholders and required text are as follows:

• $original-query : The user's query text.

• $conversation : The conversation history is rendered in the following format:

   Human: user's first query
  AGENT: answer to user's first query
  Human: user's second query
  AGENT: answer to user's second query 
  

• ${conversation USER:"<user prefix>" AGENT:"<agent prefix>" TURNS:<turn count>} : A parameterized version of the $conversation placeholder. You can customize the end-user prefix ( USER ), the agent prefix ( AGENT ), and the number of previous turns to include ( TURNS ). All placeholder parameter values must be specified.

  For example, ${conversation USER:"Human says:" AGENT:"Agent says:" TURNS:1} . The conversation history is rendered as:

   Human says: user's first query
  Agent says: answer to user's first query 
  

• $end-user-metadata : Information about the user sending the query is rendered in the following format:

   The following additional information is available about the human: {
  "key1": "value1",
  "key2": "value2",
  ...
  } 
  

For example:

 Your  
goal  
is  
to  
perform  
a  
search  
query  
to  
help  
the  
AI  
assistant  
respond  
to  
the  
human's  
last  
statement.
*  
Always  
output  
the  
best  
search  
query  
you  
can,  
even  
if  
you  
suspect  
it's  
not  
needed.
*  
Never  
generate  
a  
query  
that  
is  
the  
same  
as  
the  
user's  
last  
statement.
*  
Include  
as  
much  
context  
as  
necessary  
from  
the  
conversation  
history.
*  
Output  
a  
concise  
search  
query,  
and  
nothing  
else.
*  
Don't  
use  
quotes  
or  
search  
operators.
*  
The  
query  
must  
be  
in  
 ${ 
 language 
 ! 
 } 
.

Conversation  
History:  
 $conversation 
Human:  
 $original 
-query
Search  
Query: 

Payload settings

Payload settings provide a way to add the data store snippets as rich content in the response payload, which is rendered in the messenger . You have the option of turning this feature on or off.