Configuring and publishing the process

1Open the Prompt Chaining Gemini process.
2On the Temp Fields tab of the Start step, the default Model_LLM is gemini-1.5 pro. You can optionally edit the model version. For information about changing the model version, see the Gemini documentation.
3In the Create Prompt step, enter the prompt instructions in the Assignments field by updating the Prompt_Configuration and Prompt_Request fields using the Expression Editor, as shown in the following sample code:
For Prompt_Configuration:
<generationConfig>
<stopSequences>.</stopSequences>
<candidateCount>1</candidateCount>
<maxOutputTokens>200</maxOutputTokens>
<temperature>0.5</temperature>
<topP>0.5</topP>
<topK>2</topK>
</generationConfig>
For Prompt_Request:
<Generate_Content_Request>
<contents>
<parts>
<text>Your behaviour is {$input.First_System_Prompt}, Topic is {$input.First_User_Prompt}</text>
</parts>
<role>user</role>
</contents>
<generationConfig>
<stopSequences>{$temp.Prompt_Configuration[1]/stopSequences}</stopSequences>
<candidateCount>{$temp.Prompt_Configuration[1]/candidateCount }</candidateCount>
<maxOutputTokens>{$temp.Prompt_Configuration[1]/maxOutputTokens }</maxOutputTokens>
<temperature>{$temp.Prompt_Configuration[1]/temperature }</temperature>
<topP>{$temp.Prompt_Configuration[1]/topP }</topP>
<topK>{$temp.Prompt_Configuration[1]/topK }</topK>
</generationConfig>
</Generate_Content_Request>
For the Prompt_Configuration field, enter values for the following properties:

Property	Description
stopSequences	Contains sequences of characters or strings that stop the model's output. It controls where the model must end its response.
candidateCount	Specifies the number of response candidates that the model must generate. For example, if the value is set to 1, the model generates one response. If set to a higher number, the model generates that many alternative responses for the same input.
maxOutputTokens	Defines the maximum number of tokens the model can generate in its response. Setting a limit ensures that the response is concise and fits within the desired length constraints.
temperature	Controls the randomness of the model's output. A lower value makes the output more deterministic, while a higher value increases randomness and creativity. For example, a temperature of 0.5 balances between deterministic and creative outputs.
topP	Determines the cumulative probability threshold for token selection. The model considers the smallest set of tokens whose cumulative probability meets or exceeds topP. For example, if topP is set to 0.1, the model considers only the top 10% most probable tokens at each step.
topK	Limits the number of the highest-probability tokens to consider during response generation. For example, if topK is set to 2, the model considers only the top 2 tokens at each step, controlling output diversity and quality.

After configuring the prompt instructions, the process send the details to the LLM to fetch the required response, and then stores the first response.
4In the Create Second Prompt step, in the Assignments field, update the Prompt_Request field using the Expression Editor as shown in the following sample code:

<Generate_Content_Request>
<contents>
<parts>
<text>Your behaviour is : {$input.First_System_Prompt}, Topic is : {$input.First_User_Prompt}</text>
</parts>
<role>user</role>
</contents>
<contents>
<parts>
<text>{$temp.Prompt_Response}</text>
</parts>
<role>model</role>
</contents>
<contents>
<parts>
<text>Your additional instructions are : {$input.Second_System_Prompt}. Question is {$input.Second_User_Prompt}</text>
</parts>
<role>user</role>
</contents>
<generationConfig>
<stopSequences>{$temp.Prompt_Configuration[1]/stopSequences}</stopSequences>
<candidateCount>{$temp.Prompt_Configuration[1]/candidateCount }</candidateCount>
<maxOutputTokens>{$temp.Prompt_Configuration[1]/maxOutputTokens }</maxOutputTokens>
<temperature>{$temp.Prompt_Configuration[1]/temperature }</temperature>
<topP>{$temp.Prompt_Configuration[1]/topP }</topP>
<topK>{$temp.Prompt_Configuration[1]/topK }</topK>
</generationConfig>
</Generate_Content_Request>
The LLM uses both the requests as an instruction to prepare the final response.
5 Save and publish the process.