autointent.generation.Generator#

class autointent.generation.Generator(base_url=None, model_name=None, **generation_params)#

Wrapper class for accessing OpenAI API.

Parameters:

  • base_url (str | None) – HTTP-endpoint for sending API requests to OpenAI API compatible server. Omit this to infer OPENAI_BASE_URL from environment.

  • model_name (str | None) – Name of LLM. Omit this to infer OPENAI_MODEL_NAME from environment.

  • **generation_params (Any) – kwargs that will be sent with a request to the endpoint.

model_name = None#
client#
async_client#
generation_params#
get_chat_completion(messages)#

Prompt LLM and return its answer.

Parameters:

messages (list[autointent.generation.chat_templates.Message]) – List of messages to send to the model.

Return type:

str

async get_chat_completion_async(messages)#

Prompt LLM and return its answer asynchronously.

Parameters:

messages (list[autointent.generation.chat_templates.Message]) – List of messages to send to the model.

Return type:

str