This setting allows you to choose the AI model you prefer your chatbot to use. By default, it’s set to the GPT-4o model. You can opt to use any of the available AI models:
- GPT-4
- GPT-4 Turbo
- GPT-3.5 Turbo
- GPT-4o
- GPT-4o Mini
For enterprise accounts, you can opt-out to use private models loaded on the company secure cloud and select a number of the private LLMs:
- Llama 2 latest
- Llama 3.1 latest
- Llama 3.2 1b
- Llama 3.2 latest
If you use a GPT model but run out of credits and are on the Enterprise plan, you can use your personal Open AI API key. You can input your API key in the Account usage.
Temperature
The temperature corresponds with the “creativity” of the bots’ responses. This value is set at zero, which instructs your chatbot to choose the most likely output when generating responses, resulting in more consistent and less random answers. You can adjust this number and experiment with the bot to fit your needs.
Fallback Responses for unknown queries
Rather than offering a vague response such as “Hmm, I am not sure,” it would be more appropriate to provide a clear and concise explanation. For instance, you could say, “I’m sorry, I don’t have the information you’re looking for. Please contact customer support.”