ractogateway.batch._models

Shared data models for the batch-processing subsystem.

class ractogateway.batch._models.BatchStatus(*values)[source]

Bases: str, Enum

Processing state of a batch job.

Maps to the union of OpenAI and Anthropic batch status strings.

PENDING = 'pending'

IN_PROGRESS = 'in_progress'

FINALIZING = 'finalizing'

COMPLETED = 'completed'

FAILED = 'failed'

EXPIRED = 'expired'

CANCELLING = 'cancelling'

CANCELLED = 'cancelled'

class ractogateway.batch._models.BatchItem(**data)[source]

Bases: BaseModel

A single request within a batch job.

Parameters:

custom_id (str) – User-supplied identifier used to correlate results. Must be unique within a batch.
user_message (str) – The end-user’s query string (equivalent to ChatConfig.user_message).
temperature (float) – Sampling temperature. Defaults to 0.0.
max_tokens (int) – Maximum tokens for the completion. Defaults to 4096.
extra (dict[str, Any]) – Provider-specific pass-through kwargs.

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

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

custom_id: str

user_message: str

temperature: float

max_tokens: int

extra: dict[str, Any]

model_config: ClassVar[ConfigDict] = {}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class ractogateway.batch._models.BatchJobInfo(**data)[source]

Bases: BaseModel

Metadata about a submitted batch job.

Returned by submit_batch() and poll_status().

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

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

job_id: str

provider: str

status: BatchStatus

created_at: float

request_count: int

raw: Any

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class ractogateway.batch._models.BatchResult(**data)[source]

Bases: BaseModel

The outcome of a single BatchItem.

A result is always present in the results list returned by get_results(); check error to detect failures.

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

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

custom_id: str

response: LLMResponse | None

error: str | None

raw: Any

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

property ok: bool: True when the request succeeded (no error, response present).