Technical documentation - Yacana 0.2.1

Name	Type	Description
`name`	str	Name of the agent.
`model_name`	str	Name of the LLM model.
`system_prompt`	str \| None	System prompt defining the LLM's behavior.
`model_settings`	ModelSettings	Model configuration settings.
`api_token`	str	API token for authentication.
`headers`	dict	Custom headers for requests.
`endpoint`	str \| None	Endpoint URL for the inference server.
`runtime_config`	Dict	Runtime configuration for the agent.
`task_runtime_config`	Dict	Runtime configuration for tasks.
`history`	History	The conversation history.
`_tags`	List[str]	Internal list of tags.
`thinking_tokens`	Tuple[str, str] \| None	A tuple containing the start and end tokens of a thinking LLM. For instance, "" and "" for Deepseek-R1. Setting this prevents the framework from getting sidetracked during the thinking steps and helps maintain focus on the final result.

Parameter name	Parameter type	Parameter description
`name`	str	Name of the agent. Use something short and meaningful that doesn't contradict the system prompt.
`model_name`	str	Name of the LLM model that will be sent to the inference server (e.g., 'llama:3.1' or 'mistral:latest').
`system_prompt`	str \| None Optional	Defines the way the LLM will behave (e.g., "You are a pirate" to have it talk like a pirate). Defaults to None.
`endpoint`	str Optional	The Ollama endpoint URL. Defaults to "http://127.0.0.1:11434".
`headers`	dict Optional	Custom headers to be sent with the inference request. Defaults to None.
`model_settings`	OllamaModelSettings Optional	All settings that Ollama currently supports as model configuration. Defaults to None.
`runtime_config`	Dict \| None Optional	Runtime configuration for the agent. Defaults to None.
`thinking_tokens`	Tuple[str, str] \| None Optional	A tuple containing the start and end tokens of a thinking LLM. For instance, "" and "" for Deepseek-R1. Setting this prevents the framework from getting sidetracked during the thinking steps and helps maintain focus on the final result.

Parameter name	Parameter type	Parameter description
`file_path`	str	Path of the file in which to save the data. Specify the path + filename. Be wary when using relative paths.
`strip_api_token`	bool Optional	If True, removes the API token from the exported data. Defaults to False.
`strip_headers`	bool Optional	If True, removes headers from the exported data. Defaults to False.

Name	Type	Description
`name`	str	Name of the agent.
`model_name`	str	Name of the LLM model.
`system_prompt`	str \| None	System prompt defining the LLM's behavior.
`model_settings`	ModelSettings	Model configuration settings.
`api_token`	str	API token for authentication.
`headers`	dict	Custom headers for requests.
`endpoint`	str \| None	Endpoint URL for the inference server.
`runtime_config`	Dict	Runtime configuration for the agent.
`task_runtime_config`	Dict	Runtime configuration for tasks.
`history`	History	The conversation history.
`_tags`	List[str]	Internal list of tags.
`thinking_tokens`	Tuple[str, str] \| None	A tuple containing the start and end tokens of a thinking LLM. For instance, "" and "" for Deepseek-R1. Setting this prevents the framework from getting sidetracked during the thinking steps and helps maintain focus on the final result.

Parameter name	Parameter type	Parameter description
`name`	str	Name of the agent. Use something short and meaningful that doesn't contradict the system prompt.
`model_name`	str	Name of the LLM model that will be sent to the inference server (e.g., 'gpt-4' or 'gpt-3.5-turbo').
`system_prompt`	str \| None Optional	Defines the way the LLM will behave (e.g., "You are a pirate" to have it talk like a pirate). Defaults to None.
`endpoint`	str \| None Optional	The OpenAI endpoint URL. Defaults to None (uses OpenAI's default endpoint).
`api_token`	str Optional	The API token for authentication. Defaults to an empty string.
`headers`	dict Optional	Custom headers to be sent with the inference request. Defaults to None.
`model_settings`	OpenAiModelSettings Optional	All settings that OpenAI currently supports as model configuration. Defaults to None.
`runtime_config`	Dict \| None Optional	Runtime configuration for the agent. Defaults to None.
`thinking_tokens`	Tuple[str, str] \| None Optional	A tuple containing the start and end tokens of a thinking LLM. For instance, "" and "" for Deepseek-R1. Setting this prevents the framework from getting sidetracked during the thinking steps and helps maintain focus on the final result.

Parameter name	Parameter type	Parameter description
`file_path`	str	Path of the file in which to save the data. Specify the path + filename. Be wary when using relative paths.
`strip_api_token`	bool Optional	If True, removes the API token from the exported data. Defaults to False.
`strip_headers`	bool Optional	If True, removes headers from the exported data. Defaults to False.

Task

A class representing a task to be solved by an LLM agent.

▶️ Member variables

Name	Type	Description
`prompt`	str	The task to solve. It is the prompt given to the assigned LLM.
`agent`	GenericAgent	The agent assigned to this task.
`json_output`	bool	If True, will force the LLM to answer as JSON.
`structured_output`	Type[BaseModel] \| None	The expected structured output type for the task.
`tools`	List[Tool]	A list of tools that the LLM will get access to when trying to solve this task.
`medias`	List[str] \| None	An optional list of paths pointing to images on the filesystem.
`llm_stops_by_itself`	bool	Only useful when the task is part of a GroupSolve(). Signals the assigned LLM that it will have to stop talking by its own means.
`use_self_reflection`	bool	Only useful when the task is part of a GroupSolve(). Allows keeping the self reflection process done by the LLM in the next GS iteration.
`forget`	bool	When True, the Agent won't remember this task after completion. Useful for routing purposes.
`streaming_callback`	Callable \| None	Optional callback for streaming responses.
`runtime_config`	Dict \| None	Optional runtime configuration for the task.
`tags`	List[str] \| None	Optional list of tags that will be added to all message(s) corresponding to this task.

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`prompt`	str	The task to solve. It is the prompt given to the assigned LLM.
`agent`	GenericAgent	The agent assigned to this task.
`json_output`	bool Optional	If True, will force the LLM to answer as JSON. Defaults to False.
`structured_output`	Type[BaseModel] \| None Optional	The expected structured output type for the task. If provided, the LLM's response will be validated against this type. Defaults to None.
`tools`	List[Tool] Optional	A list of tools that the LLM will get access to when trying to solve this task. Defaults to an empty list.
`medias`	List[str] \| None Optional	An optional list of paths pointing to images on the filesystem. Defaults to None.
`llm_stops_by_itself`	bool Optional	Only useful when the task is part of a GroupSolve(). Signals the assigned LLM that it will have to stop talking by its own means. Defaults to False.
`use_self_reflection`	bool Optional	Only useful when the task is part of a GroupSolve(). Allows keeping the self reflection process done by the LLM in the next GS iteration. Defaults to False.
`forget`	bool Optional	When True, the Agent won't remember this task after completion. Useful for routing purposes. Defaults to False.
`streaming_callback`	Callable \| None Optional	Optional callback for streaming responses. Defaults to None.
`runtime_config`	Dict \| None Optional	Optional runtime configuration for the task. Defaults to None.
`tags`	List[str] \| None Optional	Optional list of tags that will be added to all message(s) corresponding to this task. Defaults to None.

Return type: Task

➤ add_tool(...)

Add a tool to the list of tools available for this task.

Parameter name	Parameter type	Parameter description
`tool`	Tool	The tool to add to the task's tool list.

Return type: None

➤ solve()

Execute the task using the assigned LLM agent.

Return type: None

Name	Type	Description
`tool_name`	str	The name of the tool.
`function_description`	str	A description of the tool's functionality.
`function_ref`	Callable	Function reference that the tool will call.
`optional`	bool	Indicates if the tool is optional.
`usage_examples`	List[dict]	A list of usage examples for the tool. The dict keys should match the function parameters.
`max_custom_error`	int	Maximum number of custom errors (raised from the function) allowed before stopping the task.
`max_call_error`	int	Maximum number of call errors (eg: python can't find the function) allowed before stopping the task.

Parameter name	Parameter type	Parameter description
`tool_name`	str	A name for the tool. Should be concise and related to what the tool does.
`function_description`	str	A description for the tool. Should be concise and related to what the tool does. May contain an example of how to use. Refer to the documentation.
`function_ref`	Callable	The reference to a python function that will be called with parameters provided by the LLM.
`optional`	bool Optional	Allows to a certain extent the LLM to choose to use the given tool or not depending on the task to solve. Defaults to False.
`usage_examples`	List[dict] Optional	A list of python dictionary examples of how the tool should be called. The examples will be given to the LLM to help it call the tool correctly. Use if the LLM struggles to call the tool successfully. Defaults to an empty list.
`max_custom_error`	int Optional	The max errors a tool can raise. A tool should raise a ToolError(...) exception with a detailed explanation of why it failed. The LLM will get the exception message and try again, taking into account the new knowledge it gained from the error. When reaching the max iteration the MaxToolErrorIter() exception is thrown and the task is stopped. Defaults to 5.
`max_call_error`	int Optional	The max number of times Yacana can fail to call a tool correctly. Note that Yacana uses the parameters given to the LLM to call the tool so if they are invalid then Yacana will have a hard time to fix the situation. You should try to give examples to the LLM on how to call the tool either in the tool description or when using the @usage_examples attribute to help the model. Defaults to 5.

Parameter name	Parameter type	Parameter description
`role`	MessageRole	The role of the message sender.
`content`	str	The content of the message.
`tags`	List[str] Optional	Optional list of tags associated with the message.

Use for duck typing only.
The smallest entity representing an interaction with the LLM.
Use child class type to determine what type of message this is and the .role member to know from whom the message is from.

▶️ Member variables

Name	Type	Description
`id`	str	The unique identifier of the message.
`role`	MessageRole	From whom is the message from.
`content`	str \| None	The actual message content.
`tool_calls`	List[ToolCallFromLLM] \| None	List of tool calls associated with the message.
`medias`	List[str]	List of media file paths.
`structured_output`	Type[T] \| None	Pydantic model for structured output.
`tool_call_id`	str \| None	ID of the associated tool call.
`tags`	List[str]	List of tags associated with the message.

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`role`	MessageRole	From whom is the message from. See the MessageRole Enum.
`content`	str \| None Optional	The actual message content. Can be None if tool_calls is provided.
`tool_calls`	List[ToolCallFromLLM] \| None Optional	An optional list of tool calls that are sent by the LLM to the user.
`medias`	List[str] \| None Optional	An optional list of path pointing to images or audio on the filesystem.
`structured_output`	Type[T] \| None Optional	An optional pydantic model that can be used to store the result of a JSON response by the LLM.
`tool_call_id`	str \| None Optional	The ID of the tool call this message is associated with.
`tags`	List[str] \| None Optional	Optional list of tags associated with the message.
`id`	uuid.UUID \| None Optional	The unique identifier of the message. If None, a new UUID will be generated.

Return type: GenericMessage

➤ add_tags(...)

Add a tag to the message.

Parameter name	Parameter type	Parameter description
`tags`	List[str]	The tag to add to the message.

Return type: None

➤ create_instance(...)

@ static method

Create a new instance of a GenericMessage subclass from a dictionary.

Parameter name	Parameter type	Parameter description
`members`	Dict	Dictionary containing the message data.

Return type: GenericMessage

➤ get_as_pretty()

Get a pretty-printed string representation of the message.

Return type: str

➤ get_message_as_dict()

Convert the message to a dictionary format.

Return type: dict

➤ remove_tag(...)

Remove a tag from the message. Tags are used to filter messages in the history.

Parameter name	Parameter type	Parameter description
`tag`	str	The tag to remove from the message.

Return type: None

MessageRole

ENUM: The available types of message creators.
User messages are the ones that are sent by the user to the LLM.
Assistant messages are the ones that are sent by the LLM to the user.
System messages are the ones that defines the behavior of the LLM.
Tool messages are the ones containing the result of a tool call and then sent to the LLM. Not all LLMs support this type of message.

▶️ Member variables

Name	Type	Description
`USER`	str	User messages are the ones that are sent by the user to the LLM.
`ASSISTANT`	str	Assistant messages are the ones that are sent by the LLM to the user.
`SYSTEM`	str	System messages are the ones that defines the behavior of the LLM.
`TOOL`	str	Tool messages are the ones containing the result of a tool call and then sent to the LLM.

▶️ Methods

➤ init()

Return type: MessageRole

History

Container for an alternation of Messages representing a conversation between the user and an LLM.
To be precise, the history is a list of slots and not actual messages. Each slot contains at least one or more messages.
This class does its best to hide the HistorySlot implementation. Meaning that many methods allows you to deal with the messages directly, but under the hood it always manages the slot wrapper.

▶️ Member variables

Name	Type	Description
`slots`	List[HistorySlot]	List of history slots.
`_checkpoints`	Dict[str, list[HistorySlot]]	Dictionary of checkpoints for the history.

▶️ Methods

➤ init()

Return type: History

➤ add_message(...)

Adds a new message to the history by creating a new slot.

Parameter name	Parameter type	Parameter description
`message`	GenericMessage	The message to add to the history.

Return type: HistorySlot

➤ add_slot(...)

Adds a new slot to the history at the specified position.

Parameter name	Parameter type	Parameter description
`history_slot`	HistorySlot	The slot to add to the history.
`position`	int \| SlotPosition Optional	The position where to add the slot. Can be an integer or a SlotPosition enum value. Defaults to SlotPosition.BOTTOM.

Return type: None

➤ clean()

Resets the history, preserving only the initial system prompt if present.

Return type: None

➤ create_check_point()

Creates a checkpoint of the current history state.

Return type: str

➤ create_instance(...)

@ static method

Creates a new instance of History from a dictionary.

Parameter name	Parameter type	Parameter description
`members`	Dict	Dictionary containing the history data.

Return type: History

➤ delete_message(...)

Deletes a message from all slots in the history.

Parameter name	Parameter type	Parameter description
`message`	Message	The message to delete.

Return type: None

➤ delete_message_by_id(...)

Deletes a message from all slots in the history by its ID.

Parameter name	Parameter type	Parameter description
`message_id`	str	The ID of the message to delete. If the ID does not exist, it logs a warning.

Return type: None

➤ delete_slot(...)

Deletes a slot from the history.

Parameter name	Parameter type	Parameter description
`slot`	HistorySlot	The slot to delete.

Return type: None

➤ delete_slot_by_id(...)

Deletes a slot from the history by its ID. If the ID does not exist, it logs a warning.

Parameter name	Parameter type	Parameter description
`slot_id`	str	The ID of the slot to delete.

Return type: None

➤ get_all_messages()

Returns all messages in the history.

Return type: None

➤ get_last_message()

Returns the last message in the history.

Return type: GenericMessage

➤ get_last_slot()

Returns the last slot of the history. A good syntactic sugar to get the last item from the conversation.

Return type: HistorySlot

➤ get_message(...)

Returns the message at the given index.

Parameter name	Parameter type	Parameter description
`index`	int	The index of the message to return.

Return type: GenericMessage

➤ get_messages_as_dict()

Returns all messages in the history as a list of dictionaries.

Return type: None

➤ get_messages_by_tags(...)

Returns messages that match the given tags based on the matching mode.

Parameter name	Parameter type	Parameter description
`tags`	List[str]	The tags to filter messages by.
`strict`	bool Optional	Controls the matching mode: - If False (default), returns messages that have ANY of the specified tags. For example, searching for ["tag1"] will match messages with ["tag1", "tag2"]. This is useful for broad filtering. - If True, returns messages that have EXACTLY the specified tags (and possibly more). For example, searching for ["tag1", "tag2"] will match messages with ["tag1", "tag2", "tag3"] but not messages with just ["tag1"] or ["tag2"]. This is useful for precise filtering.

Return type: None

➤ get_slot_by_id(...)

Returns the slot with the given ID.

Parameter name	Parameter type	Parameter description
`id`	str	The ID of the slot to return.

Return type: HistorySlot

➤ get_slot_by_index(...)

Returns the slot at the given index.

Parameter name	Parameter type	Parameter description
`index`	int	The index of the slot to return.

Return type: HistorySlot

➤ get_slot_by_message(...)

Returns the slot containing the given message.

Parameter name	Parameter type	Parameter description
`message`	GenericMessage	The message to search for.

Return type: HistorySlot

➤ load_check_point(...)

Loads a checkpoint of the history. Perfect for a timey wimey rollback in time.

Parameter name	Parameter type	Parameter description
`uid`	str	The unique identifier of the checkpoint to load.

Return type: None

➤ pretty_print()

Prints the history to stdout with colored output.

Return type: None

HistorySlot

A slot is a container for messages. It can contain one or more messages.
Most of the time it will only contain one message but when using `n=2` or`n=x` in the OpenAI API, it will contain multiple variations hence multiple messages.

▶️ Member variables

Name	Type	Description
`id`	str	The unique identifier for the slot.
`creation_time`	int	The timestamp when the slot was created.
`messages`	List[GenericMessage]	List of messages in the slot.
`raw_llm_json`	str \| None	The raw LLM JSON response for the slot.
`main_message_index`	int	The index of the main message in the slot.

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`messages`	List[GenericMessage] Optional	A list of messages. Each message is a variation of the main message (defined by the @main_message_index parameter).
`raw_llm_json`	str Optional	The raw LLM JSON response for the slot. This is the raw JSON from the inference server. When using OpenAI this may contain more than one message hence the slot system acts as a container for the messages.

Return type: HistorySlot

➤ add_message(...)

Adds a new message to the slot.

Parameter name	Parameter type	Parameter description
`message`	GenericMessage	The message to add to the slot.

Return type: None

➤ create_instance(...)

@ static method

Creates an instance of the HistorySlot class from a dictionary.
Mainly used to import the object from a file.

Parameter name	Parameter type	Parameter description
`members`	Dict	Dictionary containing the slot data.

Return type: HistorySlot

➤ get_all_messages()

Returns all the messages in the slot.

Return type: None

➤ get_main_message_index()

Returns the index of the main message in the slot.

Return type: int

➤ get_message(...)

Returns the main message of the slot or the one at the given index if index is provided.

Parameter name	Parameter type	Parameter description
`message_index`	int \| None Optional	The index of the message to return. If None, returns the currently selected message.

Return type: GenericMessage

➤ keep_only_selected_message()

Keeps only the currently selected message in the slot and deletes all the others.
If there's only one message, this method does nothing.

Return type: None

➤ set_main_message_index(...)

A slot can contain any number of concurrent message. But only one can be the main slot message and actually be part of the History.
This method sets the index of the main message within the list of available messages in the slot.

Parameter name	Parameter type	Parameter description
`message_index`	int	The index of the message to select as the main message.

Return type: None

➤ set_raw_llm_json(...)

Sets the raw LLM JSON response for the slot.
This is the raw JSON from the inference server. When using OpenAI this may contain more than one message hence the slot system acts as a container for the messages.

Parameter name	Parameter type	Parameter description
`raw_llm_json`	str	The raw JSON response from the LLM.

Return type: None

SlotPosition

ENUM: The position of a slot in the history. This is only a syntactic sugar to make the code more readable.

▶️ Member variables

Name	Type	Description
`BOTTOM`	int	The slot is at the bottom of the history.
`TOP`	int	The slot is at the top of the history.

▶️ Methods

➤ init()

Return type: SlotPosition

GroupSolve

This class allows multiple agents to enter a conversation with each other.

▶️ Member variables

Name	Type	Description
`tasks`	List[Task]	All tasks that must be solved during group chat.
`mode`	EndChatMode	The modality to end a chat with multiple agents.
`reconcile_first_message`	bool	Should the first message from both LLMs be available to one another. Only useful in dual chat.
`max_iter`	int	The max number of iterations in a conversation. An iteration is complete when we get back to the first speaker.
`shift_owner`	Task	The Task to which the shift message should be assigned to. In the end it's rather the corresponding Agent
`shift_content`	str \| None	A custom message instead of using the opposite agent response as shift message content.

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`tasks`	List[Task]	All tasks that must be solved during group chat.
`end_chat`	EndChat	Defines the modality of how and when LLMs stop chatting.
`reconcile_first_message`	bool Optional	Should the first message from both LLMs be available to one another. Only useful in dual chat. Defaults to False.
`shift_message_owner`	Task Optional	The Task to which the shift message should be assigned to. In the end it's rather the corresponding Agent than the Task that is involved here. Defaults to None.
`shift_message_content`	str Optional	A custom message instead of using the opposite agent response as shift message content. Defaults to None.

Return type: GroupSolve

➤ solve()

Starts the group chat and allows all LLMs to solve their assigned tasks.

Return type: None

EndChat

Defines the modality of how and when LLMs stop chatting.

▶️ Member variables

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`mode`	EndChatMode	The modality to end a chat with multiple agents.
`max_iterations`	int Optional	The max number of iterations in a conversation. An iteration is complete when we get back to the first speaker. Defaults to 5.

Return type: EndChat

EndChatMode

ENUM: All types of group chat completion.

▶️ Member variables

Name	Type	Description
`ALL_TASK_MUST_COMPLETE`	str	Chat will continue going until all LLMs with @llm_stops_by_itself=True says they are finished. Set precise completion goals in the task prompt if you want this to actually work.
`ONE_LAST_CHAT_AFTER_FIRST_COMPLETION`	str	One agent will have the opportunity to respond after the completion of one agent allowing it to answer one last time.
`ONE_LAST_GROUP_CHAT_AFTER_FIRST_COMPLETION`	str	All agents will have one last table turn to speak before exiting the chat after the first completion arrives.
`END_CHAT_AFTER_FIRST_COMPLETION`	str	Immediately stops group chat after an agent has reached completion.
`MAX_ITERATIONS_ONLY`	str	Agents won't be asked if they have fulfilled their objectives but instead will loop until achieving max iteration. Max iteration can be set in the EndChat() class.

▶️ Methods

➤ init()

Return type: EndChatMode

OllamaModelSettings

Settings for Ollama model configuration.

▶️ Member variables

Name	Type	Description
`mirostat`	int Optional	Controls the model's creativity level (0: off, 1: on, 2: extra on).
`mirostat_eta`	float Optional	Adjusts how quickly the model learns from context (e.g., 0.1).
`mirostat_tau`	float Optional	Controls topic adherence (e.g., 5.0).
`num_ctx`	int Optional	Determines context window size (e.g., 4096).
`num_gqa`	int Optional	Controls parallel task handling (e.g., 8).
`num_gpu`	int Optional	Sets GPU utilization (e.g., 50).
`num_thread`	int Optional	Controls parallel processing (e.g., 8).
`repeat_last_n`	int Optional	Controls repetition prevention window (e.g., 64).
`repeat_penalty`	float Optional	Penalty for repeated content (e.g., 1.1).
`temperature`	float Optional	Controls response randomness (e.g., 0.7).
`seed`	int Optional	Random seed for reproducibility (e.g., 42).
`stop`	List[str] Optional	Stop sequences for generation.
`tfs_z`	float Optional	Controls response randomness reduction (e.g., 2.0).
`num_predict`	int Optional	Maximum tokens to generate (e.g., 128).
`top_k`	int Optional	Limits token selection (e.g., 40).
`top_p`	float Optional	Controls token selection probability (e.g., 0.9).

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`mirostat`	int Optional	Controls the model's creativity level (0: off, 1: on, 2: extra on).
`mirostat_eta`	float Optional	Adjusts how quickly the model learns from context (e.g., 0.1).
`mirostat_tau`	float Optional	Controls topic adherence (e.g., 5.0).
`num_ctx`	int Optional	Determines context window size (e.g., 4096).
`num_gqa`	int Optional	Controls parallel task handling (e.g., 8).
`num_gpu`	int Optional	Sets GPU utilization (e.g., 50).
`num_thread`	int Optional	Controls parallel processing (e.g., 8).
`repeat_last_n`	int Optional	Controls repetition prevention window (e.g., 64).
`repeat_penalty`	float Optional	Penalty for repeated content (e.g., 1.1).
`temperature`	float Optional	Controls response randomness (e.g., 0.7).
`seed`	int Optional	Random seed for reproducibility (e.g., 42).
`stop`	List[str] Optional	Stop sequences for generation.
`tfs_z`	float Optional	Controls response randomness reduction (e.g., 2.0).
`num_predict`	int Optional	Maximum tokens to generate (e.g., 128).
`top_k`	int Optional	Limits token selection (e.g., 40).
`top_p`	float Optional	Controls token selection probability (e.g., 0.9).

Return type: OllamaModelSettings

➤ create_instance(...)

@ static method

Create a new instance of a ModelSettings subclass from a dictionary.

Parameter name	Parameter type	Parameter description
`members`	Dict	Dictionary containing the settings and the 'type' field indicating which subclass to instantiate.

Return type: ModelSettings

➤ get_settings()

Get all current settings as a dictionary.

Return type: dict

➤ reset()

Reset all settings to their initial values.

Return type: None

OpenAiModelSettings

Settings for OpenAI model configuration.

▶️ Member variables

Name	Type	Description
`audio`	Any Optional	Parameters for audio output when using audio modality.
`frequency_penalty`	float Optional	Penalty for token frequency (-2.0 to 2.0).
`logit_bias`	Dict Optional	Token bias adjustments (-100 to 100).
`logprobs`	bool Optional	Whether to return token log probabilities.
`max_completion_tokens`	int Optional	Maximum tokens to generate.
`metadata`	Dict Optional	Additional metadata (max 16 key-value pairs).
`modalities`	List[str] Optional	Output types to generate (e.g., ["text", "audio"]).
`n`	int Optional	Number of completion choices to generate.
`prediction`	Any Optional	Configuration for predicted output.
`presence_penalty`	float Optional	Penalty for token presence (-2.0 to 2.0).
`reasoning_effort`	str Optional	Reasoning effort level ("low", "medium", "high").
`seed`	int Optional	Random seed for reproducibility.
`service_tier`	str Optional	Latency tier for processing ("auto" or "default").
`stop`	str \| List Optional	Stop sequences for generation.
`store`	bool Optional	Whether to store completion output.
`stream_options`	Any Optional	Options for streaming response.
`temperature`	float Optional	Sampling temperature (0 to 2).
`top_logprobs`	int Optional	Number of top tokens to return (0 to 20).
`top_p`	float Optional	Nucleus sampling parameter.
`user`	str Optional	End-user identifier.
`web_search_options`	Any Optional	Web search configuration.

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`audio`	Any Optional	Parameters for audio output when using audio modality.
`frequency_penalty`	float Optional	Penalty for token frequency (-2.0 to 2.0).
`logit_bias`	Dict Optional	Token bias adjustments (-100 to 100).
`logprobs`	bool Optional	Whether to return token log probabilities.
`max_completion_tokens`	int Optional	Maximum tokens to generate.
`metadata`	Dict Optional	Additional metadata (max 16 key-value pairs).
`modalities`	List[str] Optional	Output types to generate (e.g., ["text", "audio"]).
`n`	int Optional	Number of completion choices to generate.
`prediction`	Any Optional	Configuration for predicted output.
`presence_penalty`	float Optional	Penalty for token presence (-2.0 to 2.0).
`reasoning_effort`	str Optional	Reasoning effort level ("low", "medium", "high").
`seed`	int Optional	Random seed for reproducibility.
`service_tier`	str Optional	Latency tier for processing ("auto" or "default").
`stop`	str \| List Optional	Stop sequences for generation.
`store`	bool Optional	Whether to store completion output.
`stream_options`	Any Optional	Options for streaming response.
`temperature`	float Optional	Sampling temperature (0 to 2).
`top_logprobs`	int Optional	Number of top tokens to return (0 to 20).
`top_p`	float Optional	Nucleus sampling parameter.
`user`	str Optional	End-user identifier.
`web_search_options`	Any Optional	Web search configuration.

Return type: OpenAiModelSettings

➤ create_instance(...)

@ static method

Create a new instance of a ModelSettings subclass from a dictionary.

Parameter name	Parameter type	Parameter description
`members`	Dict	Dictionary containing the settings and the 'type' field indicating which subclass to instantiate.

Return type: ModelSettings

➤ get_settings()

Get all current settings as a dictionary.

Return type: dict

➤ reset()

Reset all settings to their initial values.

Return type: None

LoggerManager

Manages logging configuration for the application.

▶️ Member variables

Name	Type	Description
`LOG_LEVEL`	str	Default log level for the application.
`AVAILABLE_LOG_LEVELS`	list[str]	List of valid log levels that can be set.

▶️ Methods

➤ init()

Return type: LoggerManager

➤ set_library_log_level(...)

@ static method

Set the logging level for a specific Python library.

Parameter name	Parameter type	Parameter description
`library_name`	str	The name of the target library.
`log_level`	str	The desired log level. Must be one of: "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL", or None.

Return type: None

➤ set_log_level(...)

@ static method

Set the logging level for the application.

Parameter name	Parameter type	Parameter description
`log_level`	str \| None	The desired log level. Must be one of: "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL", or None. If None, logging will be disabled.

Return type: None

➤ setup_logging(...)

@ static method

Initialize logging configuration for the application.

Parameter name	Parameter type	Parameter description
`log_level`	str \| None Optional	The desired log level. Must be one of: "DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL", or None. If None, uses the default LOG_LEVEL. Defaults to None.

Return type: None

ToolError

Exception raised when a tool encounters incorrect parameters.

▶️ Member variables

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`message`	str	A descriptive message that will be given to the LLM to help fix the issue. Example: 'Parameter xxxx expected type int but got type string'.

Return type: ToolError

MaxToolErrorIter

Exception raised when maximum error iterations are reached.

▶️ Member variables

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`message`	str	Information about which specific iteration counter reached its maximum.

Return type: MaxToolErrorIter

IllogicalConfiguration

Exception raised when the framework is used in an incoherent way.

▶️ Member variables

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`message`	str	A description of the illogical configuration or usage.

Return type: IllogicalConfiguration

ReachedTaskCompletion

Exception raised when a task has been successfully completed.

▶️ Member variables

▶️ Methods

➤ init()

Return type: ReachedTaskCompletion

TaskCompletionRefusal

Exception raised when the model refuses to complete a task.

▶️ Member variables

▶️ Methods

➤ init(...)

Parameter name	Parameter type	Parameter description
`message`	str	The reason for the task completion refusal.

Return type: TaskCompletionRefusal

UnknownResponseFromLLM

Exception raised when the model returns an unknown response.

▶️ Member variables

▶️ Methods

➤ init()

Return type: UnknownResponseFromLLM

▶️ Member variables

▶️ Methods

➤ __init__(...)

➤ export_to_file(...)

▶️ Member variables

▶️ Methods

➤ __init__(...)

➤ export_to_file(...)

▶️ Member variables

▶️ Methods

➤ __init__(...)

➤ add_tool(...)

➤ solve()

▶️ Member variables

▶️ Methods

➤ __init__(...)

▶️ Member variables

▶️ Methods

➤ __init__(...)

➤ add_tags(...)

➤ create_instance(...)

➤ get_as_pretty()

➤ get_message_as_dict()

➤ remove_tag(...)

▶️ Member variables

▶️ Methods

➤ __init__(...)

➤ add_tags(...)

➤ create_instance(...)

➤ get_as_pretty()

➤ get_message_as_dict()

➤ remove_tag(...)

▶️ Member variables

▶️ Methods

➤ __init__()

▶️ Member variables

▶️ Methods

➤ __init__()

➤ add_message(...)

➤ add_slot(...)

➤ clean()

➤ create_check_point()

➤ create_instance(...)

➤ delete_message(...)

➤ delete_message_by_id(...)

➤ delete_slot(...)

➤ delete_slot_by_id(...)

➤ get_all_messages()

➤ get_last_message()

➤ get_last_slot()

➤ get_message(...)

➤ get_messages_as_dict()

➤ get_messages_by_tags(...)

➤ get_slot_by_id(...)

➤ get_slot_by_index(...)

➤ get_slot_by_message(...)

➤ load_check_point(...)

➤ pretty_print()

▶️ Member variables

▶️ Methods

➤ __init__(...)

➤ add_message(...)

➤ create_instance(...)

➤ get_all_messages()

➤ get_main_message_index()

➤ get_message(...)

➤ keep_only_selected_message()

➤ set_main_message_index(...)

➤ set_raw_llm_json(...)

▶️ Member variables

▶️ Methods

➤ __init__()

▶️ Member variables

▶️ Methods

➤ __init__(...)

➤ solve()

▶️ Member variables

▶️ Methods

➤ __init__(...)

▶️ Member variables

➤ init(...)

➤ init(...)

➤ init(...)

➤ init(...)

➤ init(...)

➤ init(...)

➤ init()

➤ init()

➤ init(...)

➤ init()

➤ init(...)

➤ init(...)

➤ init()

➤ init(...)

➤ init(...)

➤ init()

➤ init(...)

➤ init(...)

➤ init(...)

➤ init()

➤ init(...)

➤ init()