OpenAI

class Client(*, api_key: str, model: str = 'gpt-3.5-turbo-16k', method: OpenAIMethod = OpenAIMethod.CHAT)

The LLM integration with OpenAI’s ChatGPT and Completion API.

Parameters:

• api_key (str) – Your secret OpenAI API key.

• model (str) – The model to use. Prefer a higher model with a high context window, as the prompt envelopes can make the LLM input quite long.

• method (OpenAIMethod) – The method to use to interact with the OpenAI API. I don’t really know the difference in terms of quality, but the chat method has worked fine so far.

complete(untrusted_user_input: str) → str

Complete the untrusted user input and return some structured output.

Parameters:

untrusted_user_input (str) – The untrusted user input.

Returns:

The structured output.

Return type:

str

class OpenAIMethod(value)

How the OpenAI API should complete the prompt. OpenAI provides two main methods of completion, both appear to be similar in quality. TODO document the differences.

CHAT = 'chat'

COMPLETION = 'completion'