ChatGPT

Using iMessage integration with Chat GPT-3 by OpenAI

This integration is only available if you have an active dedicated sender name.

Open the settings of your dedicated sender name in the dashboard and in the Integrations section activate ChatGPT.

After activation will need to configure your API key, AI model, and the quality of your bot.

This integration supports the next parameters:

• API key, required field. You can find it in your OpenAI account.

• AI Model, required field. Possible values: gpt-3.5-turbo, gpt-3.5-turbo-0301, text-davinci-003, text-curie-001, text-babbage-001, text-ada-001, code-davinci-002, code-cushman-001. Check the Model overview for an up-to-date list and descriptions of each model.

• Temperature, optional field. What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. The default value is 1.

• Max tokens, optional field. The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096). The default value is 16.

If you specified an incorrect value in one of the fields, then this integration may not work properly.

This integration is free and doesn't require additional fees from our side. Standard rates for 2-way communication will apply. Also, when making requests to OpenAI to generate responses, they will charge you according to their rates.

Known issues

In some cases, the API from OpenAI can be overloaded and return an error. In this case, your contact will not receive a reply from AI. We will send you a webhook message_failed with a specific error code.

At the moment, we do not have mechanisms to auto-call OpenAI later in case of such an issue. Therefore, you will have to handle such cases yourself.