langgraph_agent_toolkit.core.prompts.chat_prompt_template module

class langgraph_agent_toolkit.core.prompts.chat_prompt_template.ObservabilityChatPromptTemplate(messages=None, *, prompt_name=None, prompt_version=None, prompt_label=None, load_at_runtime=False, observability_platform=None, observability_backend=None, cache_ttl_seconds=3600, template_format='f-string', input_variables=None, partial_variables=None, name=None, optional_variables=[], input_types=<factory>, output_parser=None, metadata=None, tags=None, validate_template=False, **kwargs)[source][source]

Bases: ChatPromptTemplate

Chat prompt template that loads prompts from observability platforms.

Initialize ObservabilityChatPromptTemplate.

Parameters:

  • messages (Sequence[BaseMessagePromptTemplate | BaseMessage | BaseChatPromptTemplate | tuple[str | type, str | Sequence[dict[str, Any]] | Sequence[object]] | str | dict[str, Any]] | None)

  • prompt_name (str | None)

  • prompt_version (int | None)

  • prompt_label (str | None)

  • load_at_runtime (bool)

  • observability_platform (BaseObservabilityPlatform | None)

  • observability_backend (ObservabilityBackend | str | None)

  • cache_ttl_seconds (int)

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

  • input_variables (List[str] | None)

  • partial_variables (Dict[str, Any] | None)

  • name (str | None)

  • optional_variables (list[str])

  • input_types (dict[str, Any])

  • output_parser (BaseOutputParser | None)

  • metadata (dict[str, Any] | None)

  • tags (list[str] | None)

  • validate_template (bool)

  • kwargs (Any)

model_config = {'arbitrary_types_allowed': True, 'extra': 'allow', 'protected_namespaces': ()}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

__init__(messages=None, *, prompt_name=None, prompt_version=None, prompt_label=None, load_at_runtime=False, observability_platform=None, observability_backend=None, cache_ttl_seconds=settings.LANGFUSE_PROMPT_CACHE_DEFAULT_TTL_SECONDS, template_format='f-string', input_variables=None, partial_variables=None, **kwargs)[source][source]

Initialize ObservabilityChatPromptTemplate.

Parameters:

  • messages (Sequence[BaseMessagePromptTemplate | BaseMessage | BaseChatPromptTemplate | tuple[str | type, str | Sequence[dict[str, Any]] | Sequence[object]] | str | dict[str, Any]] | None)

  • prompt_name (str | None)

  • prompt_version (int | None)

  • prompt_label (str | None)

  • load_at_runtime (bool)

  • observability_platform (BaseObservabilityPlatform | None)

  • observability_backend (ObservabilityBackend | str | None)

  • cache_ttl_seconds (int)

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

  • input_variables (List[str] | None)

  • partial_variables (Dict[str, Any] | None)

  • kwargs (Any)

prompt_name: str | None
prompt_version: int | None
prompt_label: str | None
load_at_runtime: bool
observability_backend: ObservabilityBackend | None
cache_ttl_seconds: int
template_format: str
property observability_platform: BaseObservabilityPlatform | None

Get the observability platform.

model_post_init(context, /)

This function is meant to behave like a BaseModel method to initialize private attributes.

It takes context as an argument since that’s what pydantic-core passes when calling it.

Parameters:

  • self (BaseModel) – The BaseModel instance.

  • context (Any) – The context.

Return type:

None

format_messages(**kwargs)[source][source]

Format messages with standard partial and placeholder handling.

Parameters:

kwargs (Any)

Return type:

List[BaseMessage]

async aformat_messages(**kwargs)[source][source]
Parameters:

kwargs (Any)

Return type:

List[BaseMessage]

invoke(input, config=None, **kwargs)[source][source]

Invoke the prompt with standard input validation and callbacks.

Parameters:

  • input (Any)

  • config (Dict[str, Any] | None)

  • kwargs (Any)

Return type:

PromptValue

async ainvoke(input, config=None, **kwargs)[source][source]

Asynchronously invoke the prompt with standard callbacks.

Parameters:

  • input (Any)

  • config (Dict[str, Any] | None)

  • kwargs (Any)

Return type:

PromptValue

partial(**kwargs)[source][source]

Keep the remote backend when binding partial variables.

Parameters:

kwargs (Any)

Return type:

ObservabilityChatPromptTemplate

classmethod from_observability_platform(prompt_name, observability_platform, *, prompt_version=None, prompt_label=None, load_at_runtime=True, **kwargs)[source][source]

Create a chat prompt template from an observability platform.

Parameters:

  • prompt_name (str)

  • observability_platform (BaseObservabilityPlatform)

  • prompt_version (int | None)

  • prompt_label (str | None)

  • load_at_runtime (bool)

  • kwargs (Any)

Return type:

ObservabilityChatPromptTemplate

classmethod from_observability_backend(prompt_name, observability_backend, *, prompt_version=None, prompt_label=None, load_at_runtime=True, **kwargs)[source][source]

Create a chat prompt template from an observability backend.

Parameters:

  • prompt_name (str)

  • observability_backend (ObservabilityBackend | str)

  • prompt_version (int | None)

  • prompt_label (str | None)

  • load_at_runtime (bool)

  • kwargs (Any)

Return type:

ObservabilityChatPromptTemplate