RunTree

class langsmith.run_trees.RunTree(*, id: UUID = None, name: str, start_time: datetime = None, run_type: str = 'chain', end_time: datetime | None = None, extra: Dict = None, error: str | None = None, serialized: dict | None = None, events: List[Dict] = None, inputs: dict = None, outputs: dict | None = None, reference_example_id: UUID | None = None, parent_run_id: UUID | None = None, tags: List[str] | None = None, attachments: Dict[str, Tuple[str, bytes] | Attachment | Tuple[str, Path]] | Dict[str, AttachmentInfo] = None, parent_run: RunTree | None = None, child_runs: List[RunTree] = None, project_name: str = None, project_id: UUID | None = None, ls_client: Any | None = None, dotted_order: str = '', trace_id: UUID = '', dangerously_allow_filesystem: bool | None = False)

Run Schema with back-references for posting runs.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Attributes

client	Return the client.
metadata	Retrieve the metadata (if any).
revision_id	Retrieve the revision ID (if any).

Methods

__init__(**data)	Create a new model by parsing and validating input data from keyword arguments.
add_event(events)	Add an event to the list of events.
add_inputs(inputs)	Upsert the given outputs into the run.
add_metadata(metadata)	Add metadata to the run.
add_outputs(outputs)	Upsert the given outputs into the run.
add_tags(tags)	Add tags to the run.
construct([_fields_set])	Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data.
copy(*[, include, exclude, update, deep])	Duplicate a model, optionally choose which fields to include, exclude and change.
create_child(name[, run_type, run_id, ...])	Add a child run to the run tree.
dict(*[, include, exclude, by_alias, ...])	Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
end(*[, outputs, error, end_time, events, ...])	Set the end time of the run and all child runs.
ensure_dotted_order(values)	Ensure the dotted order of the run.
from_dotted_order(dotted_order, **kwargs)	Create a new 'child' span from the provided dotted order.
from_headers(headers, **kwargs)	Create a new 'parent' span from the provided headers.
from_orm(obj)
from_runnable_config(config, **kwargs)	Create a new 'child' span from the provided runnable config.
get_url()	Return the URL of the run.
infer_defaults(values)	Assign name to the run.
json(*[, include, exclude, by_alias, ...])	Generate a JSON representation of the model, include and exclude arguments as per dict().
parse_file(path, *[, content_type, ...])
parse_obj(obj)
parse_raw(b, *[, content_type, encoding, ...])
patch()	Patch the run tree to the API in a background thread.
post([exclude_child_runs])	Post the run tree to the API asynchronously.
schema([by_alias, ref_template])
schema_json(*[, by_alias, ref_template])
to_headers()	Return the RunTree as a dictionary of headers.
update_forward_refs(**localns)	Try to update ForwardRefs on fields based on this Model, globalns and localns.
validate(value)
wait()	Wait for all _futures to complete.

Parameters:

• id (UUID)

• name (str)

• start_time (datetime)

• run_type (str)

• end_time (datetime | None)

• extra (Dict)

• error (str | None)

• serialized (dict | None)

• events (List[Dict])

• inputs (dict)

• outputs (dict | None)

• reference_example_id (UUID | None)

• parent_run_id (UUID | None)

• tags (List[str] | None)

• attachments (Dict[str, Tuple[str, bytes] | Attachment | Tuple[str, Path]] | Dict[str, AttachmentInfo])

• parent_run (RunTree | None)

• child_runs (List[RunTree])

• project_name (str)

• project_id (UUID | None)

• ls_client (Any | None)

• dotted_order (str)

• trace_id (UUID)

• dangerously_allow_filesystem (bool | None)

__init__(**data: Any) → None

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Parameters:

data (Any)

Return type:

None

add_event(events: RunEvent | Sequence[RunEvent] | Sequence[dict] | dict | str) → None

Add an event to the list of events.

Parameters:

• (Union[ls_schemas.RunEvent (events) – Sequence[dict], dict, str]): The event(s) to be added. It can be a single event, a sequence of events, a sequence of dictionaries, a dictionary, or a string.

• Sequence[ls_schemas.RunEvent] – Sequence[dict], dict, str]): The event(s) to be added. It can be a single event, a sequence of events, a sequence of dictionaries, a dictionary, or a string.

• events (RunEvent | Sequence[RunEvent] | Sequence[dict] | dict | str)

Return type:

None

:paramSequence[dict], dict, str]):

The event(s) to be added. It can be a single event, a sequence of events, a sequence of dictionaries, a dictionary, or a string.

Returns:

None

Parameters:

events (RunEvent | Sequence[RunEvent] | Sequence[dict] | dict | str)

Return type:

None

add_inputs(inputs: Dict[str, Any]) → None

Upsert the given outputs into the run.

Parameters:

• outputs (Dict[str, Any]) – A dictionary containing the outputs to be added.

• inputs (Dict[str, Any])

Returns:

None

Return type:

None

add_metadata(metadata: Dict[str, Any]) → None

Add metadata to the run.

Parameters:

metadata (Dict[str, Any])

Return type:

None

add_outputs(outputs: Dict[str, Any]) → None

Upsert the given outputs into the run.

Parameters:

outputs (Dict[str, Any]) – A dictionary containing the outputs to be added.

Returns:

None

Return type:

None

add_tags(tags: Sequence[str] | str) → None

Add tags to the run.

Parameters:

tags (Sequence[str] | str)

Return type:

None

classmethod construct(_fields_set: SetStr | None = None, **values: Any) → Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

Parameters:

• _fields_set (SetStr | None)

• values (Any)

Return type:

Model

copy(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, update: DictStrAny | None = None, deep: bool = False) → Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters:

• include (AbstractSetIntStr | MappingIntStrAny | None) – fields to include in new model

• exclude (AbstractSetIntStr | MappingIntStrAny | None) – fields to exclude from new model, as with values this takes precedence over include

• update (DictStrAny | None) – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

• deep (bool) – set to True to make a deep copy of the model

• self (Model)

Returns:

new model instance

Return type:

Model

create_child(name: str, run_type: Literal['tool', 'chain', 'llm', 'retriever', 'embedding', 'prompt', 'parser'] = 'chain', *, run_id: UUID | str | None = None, serialized: Dict | None = None, inputs: Dict | None = None, outputs: Dict | None = None, error: str | None = None, reference_example_id: UUID | None = None, start_time: datetime | None = None, end_time: datetime | None = None, tags: List[str] | None = None, extra: Dict | None = None, attachments: Dict[str, Tuple[str, bytes] | Attachment | Tuple[str, Path]] | None = None) → RunTree

Add a child run to the run tree.

Parameters:

• name (str)

• run_type (Literal['tool', 'chain', 'llm', 'retriever', 'embedding', 'prompt', 'parser'])

• run_id (UUID | str | None)

• serialized (Dict | None)

• inputs (Dict | None)

• outputs (Dict | None)

• error (str | None)

• reference_example_id (UUID | None)

• start_time (datetime | None)

• end_time (datetime | None)

• tags (List[str] | None)

• extra (Dict | None)

• attachments (Dict[str, Tuple[str, bytes] | Attachment | Tuple[str, Path]] | None)

Return type:

RunTree

dict(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

Parameters:

• include (AbstractSetIntStr | MappingIntStrAny | None)

• exclude (AbstractSetIntStr | MappingIntStrAny | None)

• by_alias (bool)

• skip_defaults (bool | None)

• exclude_unset (bool)

• exclude_defaults (bool)

• exclude_none (bool)

Return type:

DictStrAny

end(*, outputs: Dict | None = None, error: str | None = None, end_time: datetime | None = None, events: Sequence[RunEvent] | None = None, metadata: Dict[str, Any] | None = None) → None

Set the end time of the run and all child runs.

Parameters:

• outputs (Dict | None)

• error (str | None)

• end_time (datetime | None)

• events (Sequence[RunEvent] | None)

• metadata (Dict[str, Any] | None)

Return type:

None

classmethod ensure_dotted_order(values: dict) → dict

Ensure the dotted order of the run.

Parameters:

values (dict)

Return type:

dict

classmethod from_dotted_order(dotted_order: str, **kwargs: Any) → RunTree

Create a new ‘child’ span from the provided dotted order.

Returns:

The new span.

Return type:

RunTree

Parameters:

• dotted_order (str)

• kwargs (Any)

classmethod from_headers(headers: Mapping[str | bytes, str | bytes], **kwargs: Any) → RunTree | None

Create a new ‘parent’ span from the provided headers.

Extracts parent span information from the headers and creates a new span. Metadata and tags are extracted from the baggage header. The dotted order and trace id are extracted from the trace header.

Returns:

The new span or None if

no parent span information is found.

Return type:

Optional[RunTree]

Parameters:

• headers (Mapping[str | bytes, str | bytes])

• kwargs (Any)

classmethod from_orm(obj: Any) → Model

Parameters:

obj (Any)

Return type:

Model

classmethod from_runnable_config(config: dict | None, **kwargs: Any) → RunTree | None

Create a new ‘child’ span from the provided runnable config.

Requires langchain to be installed.

Returns:

The new span or None if

no parent span information is found.

Return type:

Optional[RunTree]

Parameters:

• config (dict | None)

• kwargs (Any)

get_url() → str

Return the URL of the run.

Return type:

str

classmethod infer_defaults(values: dict) → dict

Assign name to the run.

Parameters:

values (dict)

Return type:

dict

json(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Callable[[Any], Any] | None = None, models_as_dict: bool = True, **dumps_kwargs: Any) → str

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

Parameters:

• include (AbstractSetIntStr | MappingIntStrAny | None)

• exclude (AbstractSetIntStr | MappingIntStrAny | None)

• by_alias (bool)

• skip_defaults (bool | None)

• exclude_unset (bool)

• exclude_defaults (bool)

• exclude_none (bool)

• encoder (Callable[[Any], Any] | None)

• models_as_dict (bool)

• dumps_kwargs (Any)

Return type:

str

classmethod parse_file(path: str | Path, *, content_type: str = None, encoding: str = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model

Parameters:

• path (str | Path)

• content_type (str)

• encoding (str)

• proto (Protocol)

• allow_pickle (bool)

Return type:

Model

classmethod parse_obj(obj: Any) → Model

Parameters:

obj (Any)

Return type:

Model

classmethod parse_raw(b: str | bytes, *, content_type: str = None, encoding: str = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model

Parameters:

• b (str | bytes)

• content_type (str)

• encoding (str)

• proto (Protocol)

• allow_pickle (bool)

Return type:

Model

patch() → None

Patch the run tree to the API in a background thread.

Return type:

None

post(exclude_child_runs: bool = True) → None

Post the run tree to the API asynchronously.

Parameters:

exclude_child_runs (bool)

Return type:

None

classmethod schema(by_alias: bool = True, ref_template: str = '#/definitions/{model}') → DictStrAny

Parameters:

• by_alias (bool)

• ref_template (str)

Return type:

DictStrAny

classmethod schema_json(*, by_alias: bool = True, ref_template: str = '#/definitions/{model}', **dumps_kwargs: Any) → str

Parameters:

• by_alias (bool)

• ref_template (str)

• dumps_kwargs (Any)

Return type:

str

to_headers() → Dict[str, str]

Return the RunTree as a dictionary of headers.

Return type:

Dict[str, str]

classmethod update_forward_refs(**localns: Any) → None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

Parameters:

localns (Any)

Return type:

None

classmethod validate(value: Any) → Model

Parameters:

value (Any)

Return type:

Model

wait() → None

Wait for all _futures to complete.

Return type:

None