Configuring OpenAI integration

You can configure the OpenAI integration in HCL DevOps Loop to connect to the provider and use Loop Genie services.

Before you begin

You must have completed the following tasks:

  • Ensured that you have administrative privileges in DevOps Loop.
  • Completed the steps to prepare your OpenAI account for integration with DevOps Loop. See Requirements for OpenAI integration.

Procedure

  1. Click Settings > Integrations.
    The Integrations page is displayed.
  2. Click .
    The New Integration pane is displayed with the Overview tab.
  3. Enter a name to identify the integration in Name.
  4. Select Open AI from the Provider list.
  5. Select one of the following options in the Credential Type list:
    • API Key: Go to step 6.
    • Password: Go to step 7.
  6. Enter the API key of the AI provider account to authenticate the connection in API Key.
  7. Enter the details in the following fields:
    • Username
    • Password
    • Confirm Password
  8. Click Next.
    The Configure tab is displayed.
  9. Perform the following steps in the Configure tab to set the parameters:
    1. Enter the API Endpoint URL used by your OpenAI account.
    2. Select Chat in Mode to set the mode of communication.
    3. Select an LLM to be used from the Model list.
    4. Enter the Organization ID configured in your OpenAI account for your organization.
    5. Enter the Project ID configured in your OpenAI account for your organization.
    6. Enter one or more Stop Sequences to define where the model should stop generating text. For example: "stop" or "end".
    7. Use the Temperature slider to control the creativity of the response:

      • Lower values produce more precise, consistent answers.

      • Higher values produce more creative or varied output.

    8. Set the Max Length slider to define the maximum number of tokens the model can generate.
    9. Use the Top P slider to adjust the diversity of the output:

      • Lower values focus on the most likely words.

      • Higher values allow more varied responses.

    10. Set the Frequency Penalty slider to reduce repetition of words or phrases.
      • Higher values result in less repetitive output.
    11. Set the Presence Penalty slider to encourage the model to introduce new topics rather than repeating previous ones.
    12. Set the Best Of slider to choose how many internal responses the model generates before returning the best one.
  10. Click Save to apply the configuration.

Results

You have configured the OpenAI integration with DevOps Loop.