Class: OpenAIModel

OpenAIModel(apiKey, modelopt)

new OpenAIModel(apiKey, modelopt)

This is a constructor function that initializes an OpenAI chatbot with a specified API key and model.

Parameters:
Name Type Attributes Default Description
apiKey string

The API key is a unique identifier that allows access to OpenAI's API services. It is required to make requests to the OpenAI API.
model string <optional>
 gpt-3.5-turbo

The model parameter is a string that specifies the OpenAI language model to use for generating text. In this case, the default model is 'gpt-3.5-turbo'.
Source:

Members

apiUrl :string

Type:
  • string
Source:

max_tokens :maxTokens|undefined

Type:
Source:

Methods

(async) chat(messages, maxTokensopt, temperatureopt) → {Promise.<any>}

This is an async function that sends a POST request to an API endpoint with specified parameters and returns the response data.

Parameters:
Name Type Attributes Default Description
messages any

An array of strings representing the conversation history or prompt for the chatbot to generate a response to.
maxTokens maxTokens <optional>

The maximum number of tokens (words) that the API should generate in response to the given messages. If not provided, the API will use its default value.
temperature number <optional>
 0.8

The temperature parameter controls the "creativity" of the AI-generated responses. A higher temperature value will result in more diverse and unpredictable responses, while a lower temperature value will result in more conservative and predictable responses. The default value is 0.8.
Source:
Returns:

the result of the API call made using the provided parameters (messages, maxTokens, and temperature) after handling any errors that may occur during the API call.

Type
Promise.<any>

config()

The function returns an object with the model and apiKey properties.

Source:
Returns:

An object with two properties: "model" and "apiKey", both of which are being accessed from the current object using "this".

(async) countPromptTokens(messages)

The function counts the number of tokens in a set of messages based on the selected language model.

Parameters:
Name Type Description
messages any

An array of objects representing messages, where each object has properties such as "name" and "text".
Source:
Returns:

the total number of tokens in the messages array, based on the model being used.

getTokenLimit() → {number}

The function returns the token limit for a specific language model.

Source:
Returns:

The function getTokenLimit() returns the token limit for a specific language model based on the value of this.model. The token limit is returned as an integer value.

Type
number

setApiKey(value)

Parameters:
Name Type Description
value string
Source:

(static) fromConfig(config)

This function returns a new OpenAIModel object using the apiKey and model specified in the config parameter.

Parameters:
Name Type Description
config Object

The config parameter is an object that contains the necessary information to create a new OpenAIModel instance. It should have the following properties:
Source:
Returns:

The fromConfig method is returning a new instance of the OpenAIModel class with the apiKey and model properties set based on the config object passed as an argument. However, the code snippet is incomplete as there is a missing argument after config.model.