Controller

meganno_client.controller.Controller

The Controller class manages annotation agents and runs agent jobs.

__init__(service, auth)

Init function

Parameters:

Name	Type	Description	Default
service	Service	MEGAnno service object for the connected project.	required
auth	Authentication	MEGAnno authentication object.	required

list_agents(created_by_filter=None, provider_filter=None, api_filter=None, show_job_list=False)

Get the list of registered agents by their issuer IDs.

Parameters:

Name	Type	Description	Default
created_by_filter	list	List of user IDs to filter agents, by default None (if None, list all)	None
provider_filter		Returns agents with the specified provider eg. openai	None
api_filter		Returns agents with the specified api eg. completion	None
show_job_list		if True, also return the list uuids of jobs of the agent.	False

Returns:

Type	Description
list	A list of agents that are created by specified issuers.

list_jobs(filter_by, filter_values, show_agent_details=False)

Get the list of jobs with querying filters.

Parameters:

Name	Type	Description	Default
filter_by	str	Filter options. Must be ["agent_uuid" | "issued_by" | "uuid"] | None	required
filter_values	list	List of uuids of entity specified in 'filter_by'	required
show_agent_details	bool	If True, return agent configuration, by default False	False

Returns:

Type	Description
list	A list of jobs that match given filtering criteria.

list_jobs_of_agent(agent_uuid, show_agent_details=False)

Get the list of jobs of a given agent.

Parameters:

Name	Type	Description	Default
agent_uuid	str	Agent uuid	required
show_agent_details	bool	If True, return agent configuration, by default False	False

Returns:

Type	Description
list	A list of jobs of a given agent

register_agent(model_config, prompt_template_str, provider_api)

Register an agent with backend service.

Parameters:

Name	Type	Description	Default
model_config	dict	Model configuration object	required
prompt_template_str	str	Serialized prompt template	required
provider_api	str	Name of provider and corresponding api eg. 'openai:chat'	required

Returns:

Type	Description
dict	object with unique agent id.

persist_job(agent_uuid, job_uuid, label_name, annotation_uuid_list)

Given annoations for a subset, persist them as a job for the project.

Parameters:

Name	Type	Description	Default
agent_uuid	str	Agent uuid	required
job_uuid	str	Job uuid	required
label_name	str	Label name used for annotation	required
annotation_uuid_list	list	List of uuids of records that have valid annotations from the job	required

Returns:

Type	Description
dict	Object with job uuid and annotation count

create_agent(model_config, prompt_template, provider_api='openai:chat')

Validate model configs and register a new agent. Return new agent's uuid.

Parameters:

Name	Type	Description	Default
model_config	dict	Model configuration object	required
prompt_template	str	PromptTemplate object	required
provider_api	str	Name of provider and corresponding api eg. 'openai:chat'	'openai:chat'

Returns:

Name	Type	Description
agent_uuid	str	Agent uuid

get_agent_by_uuid(agent_uuid)

Return agent model configuration, prompt template, and creator id of specified agent.

Parameters:

Name	Type	Description	Default
agent_uuid	str	Agent uuid	required

Returns:

Type	Description
dict	A dict containing agent details.

list_my_agents()

Get the list of registered agents by me.

Returns:

Name	Type	Description
agents	list	A list of agents that are created by me.

list_my_jobs(show_agent_details=False)

Get the list of jobs of issued by me.

Parameters:

Name	Type	Description	Default
show_agent_details	bool	If True, return agent configuration, by default False	False

Returns:

Name	Type	Description
jobs	list	A list of jobs of issued by me.

run_job(agent_uuid, subset, label_name, batch_size=1, num_retrials=2, label_meta_names=[], fuzzy_extraction=False)

Create, run, and persist an LLM annotation job with given agent and subset.

Parameters:

Name	Type	Description	Default
agent_uuid	str	Uuid of an agent to be used for the job	required
subset	Subset	[Megagon-only] MEGAnno Subset object to be annotated in the job	required
label_name	str	Label name used for annotation	required
batch_size	int	Size of batch to each Open AI prompt	1
num_retrials	int	Number of retrials to OpenAI in case of failure in response	2
label_meta_names		list of label metadata names to be set	[]
fuzzy_extraction		Set to True if fuzzy extraction desired in post processing	False

Returns:

Name	Type	Description
job_uuid	str	Job uuid