1.4 - LLM Temperature

You can easily download and run the workflow directly in your KNIME installation. We recommend that you use the latest version of the KNIME Analytics Platform for optimal performance.

The workflows requires an OpenAI API key to run. If you don't have one yet, register with OpenAI and create a new API key under https://platform.openai.com/account/api-keys.

We use text-ada-001 in all examples with LLMs for cost saving.
Consider that using a better model over text-ada-001 significantly increases costs.

More information can be found at https://platform.openai.com/docs/models/gpt-3.

What is temperature?

In the context of language models like GPT-3 (which is an example of a large language model), temperature is a parameter that affects the randomness and creativity of the model's output. When generating text, the temperature determines how much the model prioritizes high-probability words and how much it explores less likely options.

A higher temperature, such as 1.0, makes the model more random and creative. It increases the likelihood of generating diverse and unexpected responses. On the other hand, a lower temperature, such as 0.5, makes the model more focused and conservative, favoring more probable and safe responses.

External resources

• Model Documentation
• OpenAI API Keys