Interact with the chat completions API. The following is an example screenshot:
You can adjust the prompt messages on the left side of the playground. There are three role types of prompt messages: system, user, and assistant.
You can add and edit the system message at the top of the playground.
To add a user or assistant message, click the Add button.
To remove a user or assistant message, click the minus button at the right corner of the message.
To change the role of a message, click the User or Assistant text at the beginning of the message.
You can add images to the prompt by clicking the Upload Image button.
You can add audio files to the prompt by clicking the Upload Audio button.
Click the Clear button to clear all the prompts.
You can select available models in GPUStack by clicking the model dropdown at the top-right corner of the playground. Please refer to Model Deployment Management to learn about how to deploy models.
You can customize completion parameters in the Parameters section.
You can do a completion by clicking the Submit button or pressing Enter.
Once you've done experimenting with the prompts and parameters, you can click the View Code button to check how you can call the API with the same input by code. Code examples in curl, Python, and Node.js are provided.
You can compare multiple models in the playground. The following is an example screenshot:
You can choose the number of models to compare by clicking the comparison view buttons, including 2, 3, 4 and 6-model comparison.
You can adjust the prompt messages similar to the chat playground.
You can add images to the prompt by clicking the Upload Image button.
You can add audio files to the prompt by clicking the Upload Audio button.
Click the Clear button to clear all the prompts.
You can select available models in GPUStack by clicking the model dropdown at the top-left corner of each model panel.
You can customize completion parameters by clicking the settings button of each model.