Configure and publish the processes

1. 1To publish the Search Tool process, click Actions in the row that contains the process and select publish.
2. 2To publish the Action Detail Extractor process, click Actions in the row that contains the process and select Publish.
3. 3Open the Prompt AzureOpenAI process.
4. 4On the Temp Fields tab of the Start step, the Model_LLM field is set to cai-qa-gpt4turbo-sweden by default. You can optionally edit the model version. For more information about changing the model version, see the Azure documentation.
5. 5Save and publish the process.
6. 6Open the Search Tool Workflow process.
7. 7On the Temp Fields tab of the Start step, the Loop_Limit field is set to 5 by default. You can optionally edit the limit. This field defines the number of times the Search Tool subprocess can be called. You can adjust the number of repeat queries in the Search Tool to get new information and better results. However, this increases the number of tokens used.
8. 8On the Assignment tab of the Create Prompt to LLM step, the Prompt field is configured to contain the request template. Optionally, you can configure the LLM behavior using the Expression Editor, as shown in the following sample code:
<CreateChatCompletionRequest>
<temperature>0.7</temperature>
<top_p>0.9</top_p>
<max_tokens>150</max_tokens>
<messages>
<role>user</role>
<content>You are a helpful assistant.</content>
</messages>
<messages>
<role>user</role>
<content>{$temp.Prompt}</content>
</messages>
</CreateChatCompletionRequest>

For the Prompt Request field, enter values for the following properties:

Property	Description
maxOutputTokens	Defines the maximum number of tokens that 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 close to 0 makes the output more deterministic, while a higher value close to 1 increases randomness and creativity. For example, if you set temperature to 0.5, the model 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 you set topP to 0.1, the model considers only the top 10% most probable tokens at each step.

9. 9Save and publish the process.