For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python class

TextGenerationOutput

TextGenerationOutput

class max.pipelines.context.TextGenerationOutput(*, request_id, tokens, final_status, log_probabilities=None, num_cached_tokens=None)

source

Bases: object

Represents the output of a text generation operation.

Combines token IDs, final generation status, request ID, and optional log probabilities for each token.

Parameters:

• request_id (RequestID)
• tokens (list[int])
• final_status (GenerationStatus)
• log_probabilities (list[LogProbabilities] | None)
• num_cached_tokens (int | None)

final_status

final_status: GenerationStatus

source

The final status of the generation process.

is_done

property is_done: bool

source

Indicates whether the text generation process is complete.

Returns:

True if the generation is done, False otherwise.

log_probabilities

log_probabilities: list[LogProbabilities] | None = None

source

Optional list of log probabilities for each token.

merge()

classmethod merge(outputs)

source

Combine many TextGenerationOutput chunks into a single TextGenerationOutput.

Parameters:

outputs (list[TextGenerationOutput])

Return type:

TextGenerationOutput

num_cached_tokens

num_cached_tokens: int | None = None

source

Number of prompt tokens served from the KV prefix cache.

request_id

request_id: RequestID

source

The unique identifier for the generation request.

tokens

tokens: list[int]

source

List of generated token IDs.