mstar.api_server.request_types

Classes

APIServerMessage(message_type[, body])	Envelope for messages received by the API server.
DataWorkerProfile(request_id[, ...])	Profiling reported by the API-server data worker at preprocess finish: the timestamp at which the request was handed to the conductor and the per-modality sizes of the raw inputs.
PreprocessInput(request_id, text, ...)
RequestComplete(request_id, final_outputs, ...)	Signals that a request has finished processing.
ResultChunk(request_id, modality, data[, ...])	One chunk of generated output for a request.
ResultTensors(request_id, modality, ...)

class mstar.api_server.request_types.APIServerMessage(message_type, body=None)

Bases: object

Envelope for messages received by the API server.

Parameters:

• message_type (str)

• body (ResultTensors | RequestComplete | None)

body: ResultTensors | RequestComplete | None = None

message_type: str

class mstar.api_server.request_types.DataWorkerProfile(request_id, preprocess_finish_time=None, inputs=<factory>)

Bases: object

Profiling reported by the API-server data worker at preprocess finish: the timestamp at which the request was handed to the conductor and the per-modality sizes of the raw inputs. (The data worker’s tx/rx are read directly from its tensor manager at request completion, not via this.)

Parameters:

• request_id (str)

• preprocess_finish_time (float | None)

• inputs (list[InputInfo])

inputs: list[InputInfo]

preprocess_finish_time: float | None = None

request_id: str

class mstar.api_server.request_types.PreprocessInput(request_id: str, text: str | None, file_paths: dict[str, list[str]] | None, input_modalities: list[str], output_modalities: list[str], model_kwargs: dict)

Bases: object

Parameters:

• request_id (str)

• text (str | None)

• file_paths (dict[str, list[str]] | None)

• input_modalities (list[str])

• output_modalities (list[str])

• model_kwargs (dict)

file_paths: dict[str, list[str]] | None

input_modalities: list[str]

model_kwargs: dict

output_modalities: list[str]

request_id: str

text: str | None

class mstar.api_server.request_types.RequestComplete(request_id, final_outputs, conductor_ingest_time, conductor_finish_time, graph_timings=<factory>, rx_info=<factory>, tx_info=<factory>)

Bases: object

Signals that a request has finished processing.

Parameters:

• request_id (str)

• final_outputs (dict[str, NestedLoopIndices])

• conductor_ingest_time (float)

• conductor_finish_time (float)

• graph_timings (dict[tuple[str, str], GraphTiming])

• rx_info (list[RxInfo])

• tx_info (list[TxInfo])

conductor_finish_time: float

conductor_ingest_time: float

final_outputs: dict[str, NestedLoopIndices]

graph_timings: dict[tuple[str, str], GraphTiming]

request_id: str

rx_info: list[RxInfo]

tx_info: list[TxInfo]

class mstar.api_server.request_types.ResultChunk(request_id, modality, data, metadata=<factory>)

Bases: object

One chunk of generated output for a request.

Parameters:

• request_id (str)

• modality (str)

• data (bytes)

• metadata (dict)

data: bytes

metadata: dict

modality: str

request_id: str

class mstar.api_server.request_types.ResultTensors(request_id: str, modality: str, graph_edge: mstar.graph.base.GraphEdge, loop_indices: mstar.graph.loop_indices.NestedLoopIndices, metadata: dict = <factory>)

Bases: object

Parameters:

• request_id (str)

• modality (str)

• graph_edge (GraphEdge)

• loop_indices (NestedLoopIndices)

• metadata (dict)

graph_edge: GraphEdge

loop_indices: NestedLoopIndices

metadata: dict

modality: str

request_id: str