Execute the operation, assuring that all predecessors have been executed. :param lm: The language model to be used. :type lm

Returns the thoughts associated with the operation. :return: List of scored thoughts. :rtype: List[Thought]

Iterates over all predecessors and aggregates their thoughts. :return: A list of all thoughts from the predecessors. :rtype:

Initializes a new Score operation. :param num_samples: Number of samples to use for scoring. Defaults to 1. :type num_sample

Creates a new thought from an existing one. :param thought: An instance of a Thought to clone. :return: A new Thought instan

Extract the response texts from the query response. :param query_response: The response dictionary (or list of dictionaries) from th

Query the OpenAI model for responses. :param query: The query to be posed to the language model. :type query: str :p

Helper function to remove tags from a text. :param text: The input text. :type text: str :param tag: The tag to be stripped. Default

Add a succeeding operation and update the relationships. :param operation: The operation to be set as a successor. :type ope

Checks if the operation can be executed based on its predecessors. :return: True if all predecessors have been executed, False other

Add a preceding operation and update the relationships. :param operation: The operation to be set as a predecessor. :type op

Send chat messages to the OpenAI model and retrieves the model's response. Implements backoff on OpenAI error. :param messag

Send chat messages to the OpenAI model and retrieves the model's response. Implements backoff on OpenAI error. :param messag

Generate an improve prompt for the language model. The thought state is unpacked to allow for additional keyword arguments an

Parse the response from the language model for an improve prompt. :param state: The thought state used to generate the prompt.

Parse the response from the language model for a score prompt. :param states: The thought states used to generate the prompt.

Run the controller and execute the operations from the Graph of Operations based on their readiness. Ensures the program is i

Generate a score prompt for the language model. :param state_dicts: The thought states that should be scored,

Abstract method for the actual execution of the operation. This should be implemented in derived classes. :param lm: The lan

Generate a aggregation prompt for the language model. :param state_dicts: The thought states that should be aggregated. :typ

Appends an operation to all leaves in the graph and updates the relationships. :param operation: The operation to append. :t

Generate a generate prompt for the language model. The thought state is unpacked to allow for additional keyword arguments an

Returns the best N thoughts from the predecessors based on their score. :return: List of best N thoughts. :rtype: List[Thoug

Extracts unique nodes from a Dask DataFrame. Args: ddf (dd.DataFrame): The Dask DataFrame to process. Returns: dd.DataFrame:

Generates the Graph of Operations for the IO method. :return: Graph of Operations :rtype: GraphOfOperations

Load configuration from a specified path. :param path: Path to the config file. If an empty path provided, defa

Load configuration from a specified path. :param path: Path to the config file. If an empty path provided, defa

Parse the response from the language model for a aggregation prompt. :param states: The thought states used to generate the prompt.

Parse the response from the language model for a generate prompt. :param state: The thought state used to generate the prompt.

Parse the response from the language model for a validation prompt. :param state: The thought state used to generate the prompt.