The OpenAIChat component is a component that collaborates with the AI functions provided by OpenAI. OpenAIChat uses a language model specialized in chat completion. It is designed to simplify conversations involving multiple interactions.
※To use this OpenAIChat component, you need to obtain an API Key in advance to call OpenAI’s AI functions. For how to obtain an API Key on the OpenAI site, please refer to here.
|Basic Properties||Specifies the basic properties of the ‘OpenAI’ category|
|API Key||API Key *1|
|Organization Id||Organization ID *1|
|Model||Select or manually enter the model name to be used. The models that can be used vary depending on the contract with OpenAI.||
|System Message||Role Setting|
|User Message Sample Input||Specifies examples of questions from the user|
|Assistant Message Sample Input||Specifies examples of answers|
|User Message||Question from the user|
|Temperature||Specifies the sampling temperature between 0 and 1|
|Max Tokens||Maximum number of tokens in the response|
|Top-P||Specifies nucleus sampling between 0 and 1. The default is 1|
|N||Number of responses generated per prompt|
|Log Probabilities||Includes the log probability of the most likely token and the selected token|
|Stop||String to stop token generation|
|Presence Penalty||Specifies whether to reuse words that have already appeared, from -2.0 to 2.0. The default is 0|
|Frequency Penalty||The more often it appears, the more penalty it gets, specified from -2.0 to 2.0. The default is 0|
|Logit Bias||Parameter to change the likelihood that the specified token will appear|
※ For details of each property related to OpenAI, please refer to OpenAI API Reference.
※1 To use the OpenAIChat component, you need to obtain an API key. For how to obtain an API key, please refer to here.
||Stores the response from the OpenAI Chat API as is|
Need more help with this?
Join our slack community for help