Base Agent

class oscopilot.agents.base_agent.BaseAgent

Bases: object

BaseAgent serves as the foundational class for all agents types within the system.

This class initializes the core attributes common across different agents, providing a unified interface for further specialization. Attributes include a language learning model, the execution environments, an action library, and a maximum iteration limit for agents operations.

llm

Placeholder for a language learning model, initialized as None.

environments

The execution environments for the agents, initialized as None.

action_lib

A library of actions available to the agents, initialized as None.

max_iter

The maximum number of iterations the agents can perform, initialized as None.

extract_information(message, begin_str='[BEGIN]', end_str='[END]')

Extracts substrings from a message that are enclosed within specified begin and end markers.

Parameters:

• message (str) – The message from which information is to be extracted.

• begin_str (str) – The marker indicating the start of the information to be extracted.

• end_str (str) – The marker indicating the end of the information to be extracted.

Returns:

A list of extracted substrings found between the begin and end markers.

Return type:

list[str]

extract_json_from_string(text)

Identifies and extracts JSON data embedded within a given string.

This method searches for JSON data within a string, specifically looking for JSON blocks that are marked with `json` notation. It attempts to parse and return the first JSON object found.

Parameters:

text (str) – The text containing the JSON data to be extracted.

Returns:

The parsed JSON data as a dictionary if successful. str: An error message indicating a parsing error or that no JSON data was found.

Return type:

dict