In the website GPT chat model, you can extract information from a website of your choice and incorporate it into ChatGPT in SprintHub. This allows you to associate it with a chatbot and provide information specific to that site. Additionally, in text mode, you can use text of your choice to extract information and pass it to a ChatBot as well.
Set a name for your Model.
Create a description for your model.
A higher level of contextualization means that Chat GPT will receive more company information during a conversation, increasing the quality of responses. Conversely, response time may increase, as will tokens used. For a low contextualization level, consumption is estimated at about 300 to 400 tokens per message. For a medium contextualization level, consumption is estimated at about 600 to 700 tokens per message. For a high contextualization level, consumption is estimated at about 1000 to 1200 tokens per message.
Select which Chat GPT model you want to use.
Increasing the temperature, for example to 1, will make Chat GPT more creative and prone to random responses. Decreasing the temperature, for example to 0, will make the model more cautious and conservative in its responses.
Add your new questions and answers. Enter the questions you want to "simulate", as if a customer were asking them, and the answers you want Chat GPT to provide, aligned with your company's guidelines.
It is possible to import spreadsheets in CSV and XLSX formats that contain predefined question-and-answer templates you have already configured.
In additional information, you can describe the personality and role of your model's virtual "attendant." For example, you can outline it as a friendly company attendant whose function is to respond exclusively to the information you have previously defined.
To configure your Chat GPT in Text mode and in Website follow the step-by-step:
Click Convert and then on 'ModelsChat GPT'
When you start creating your Chat GPT model, click 'Website';
Enter the URL of the site you want to extract the information;
After clicking Extract content, wait a few minutes, and shortly after the website content will be ready.
Click Save and Close after configure your model.
To test your Chat GPT model, go back to the general tab of the Chat GPT models, and click on the name of the model you want to test;
Ask any questions you prefer about the topics related to the content extracted from the site;
Note that next to the test chat, the recent activities of the chat GPT model appear. And in it, there is information about the amount that the CHATGPTcharges for each trained (extracted) model.
To configure thetext mode, click 'Text';
Copy or type the text of your preference.
Click Save and Close after configure your model.
As with the Website method mentioned above, you can test your text model;
After testing the chat GPT models, they will be ready for use on the platform and can be used in ChatBots, for example.
