For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).
Python class
GenerationOutput
GenerationOutput
class max.pipelines.context.GenerationOutput(*, request_id, final_status, output)
Bases: BaseModel
Output container for image generation pipeline operations.
This class holds a list of generated images in OpenResponses API format,
along with request tracking and status information. It implements the
PipelineOutput protocol by providing the required is_done property.
Example:
import numpy as np
from max.pipelines.context.outputs import GenerationOutput
from max.pipelines.request import RequestID
from max.pipelines.request.open_responses import OutputImageContent
from max.pipelines.context.status import GenerationStatus
img_array = (np.random.rand(512, 512, 3) * 255).astype(np.uint8)
result = GenerationOutput(
request_id=RequestID(value="req-123"),
final_status=GenerationStatus.END_OF_SEQUENCE,
output=[OutputImageContent.from_numpy(img_array, format="png")],
)
if result.is_done:
print(f"Generated {len(result.output)} images")-
Parameters:
-
- request_id (RequestID)
- final_status (GenerationStatus)
- output (list[Annotated[OutputTextContent | RefusalContent | ReasoningSummaryContent | OutputImageContent | OutputVideoContent, FieldInfo(annotation=NoneType, required=True, discriminator='type')]])
final_status
final_status: GenerationStatus
The final status of the generation process.
is_done
property is_done: bool
Indicates whether the pipeline operation has completed.
-
Returns:
-
Trueif the generation is done (status is not ACTIVE),Falseotherwise.
model_config
model_config: ClassVar[ConfigDict] = {'frozen': True}
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
output
output: list[OutputContent]
List of OutputContent objects (text, images, etc.) representing generated content.
request_id
request_id: RequestID
The unique identifier for the generation request.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!