8.4 Integrating OpenAI in CloudCX
Integrating OpenAI into your CX system can help improve customer experience by providing faster and more accurate responses.
Connect CloudCX with OpenAI
(1)Log in to your CX control panel.
(2)From the left navigation menu, go to App & Integrations.
(3)Go to the OpenAI card, and click Settings.
(4)Populate the Secret Key you generated at OpenAI to finalize the integration configuration of OpenAI.
Please reference to How to Apply the API Key from OpenAI to create the API Key.
(5)Select a GPT model, and you can set the model temperature.
Note: The main differences between different models are price and capabilities. For more details, please refer to OpenAI’s official website: https://openai.com/
The correlation is clear: as temperature rises, creativity flourishes, but so does the likelihood of unpredictability. Conversely, lower temperatures promote precision at the expense of creative thinking.
Token Usage
The input token of GPT is the total token of the data sent to OpenAI for analysis by calling the API. This type of token is used most frequently, such as questions asked by customers, summary of retrieved data, etc.
The output token of GPT is the total token of the text content generated by openAI. For example, the content automatically replied by the AI agent, the content expanded or summarized by the AI copliot, etc.
The token of Embedding model - text-embedding -3-large is the number of words in all documents, files, and web pages used to create the AI dataset. It is usually used in large quantities only when creating an AI dataset.
(6)Click Save.