class langgraph_agent_toolkit.core.observability.empty.EmptyObservability(prompts_dir=None)

Bases: BaseObservabilityPlatform

Empty implementation of observability platform.

Initialize EmptyObservability.

Parameters:

prompts_dir (str | None) – Optional directory to store prompts locally. If None, a system temp directory is used.

__init__(prompts_dir=None)

Initialize EmptyObservability.

Parameters:

prompts_dir (str | None) – Optional directory to store prompts locally. If None, a system temp directory is used.

get_callback_handler(**kwargs)

Get the callback handler for the observability platform.

Return type:

None

before_shutdown()

Perform any necessary cleanup before shutdown.

Return type:

None

record_feedback(run_id, key, score, **kwargs)

Record feedback for a run with Empty observability platform.

Parameters:

• run_id (str)

• key (str)

• score (float)

Return type:

None

push_prompt(name, prompt_template, metadata=None, force_create_new_version=True)

Push a prompt using local storage.

Parameters:

• name (str) – Name of the prompt

• prompt_template (str | List[ChatMessageDict]) – String template, list of message dicts, or prompt object

• metadata (Dict[str, Any] | None) – Additional metadata for the prompt

• force_create_new_version (bool) – If True, overwrite existing prompt with new version

Return type:

None

pull_prompt(name, template_format='f-string', **kwargs)

Pull a prompt from local storage.

Parameters:

• name (str)

• template_format (Literal['f-string', 'mustache', 'jinja2'])

Return type:

ChatPromptTemplate | str | dict | None

delete_prompt(name)

Delete a prompt from local storage.

Parameters:

name (str) – Name of the prompt to delete

Return type:

None

get_template(name)

Parameters:

name (str)

Return type:

str

property prompts_dir: Path

render_prompt(prompt_name, **variables)

Parameters:

prompt_name (str)

Return type:

str

property required_vars: List[str]

static requires_env_vars(func)

Parameters:

func (Callable[[...], T])

Return type:

Callable[[…], T]

validate_environment()

Return type:

bool