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 module

max.pipelines.modeling.types.pipeline_variants

Input and output types for each generation modality: text, image, audio, and embeddings.

Text generation

BatchType	Type of batch.
CompletedBatchStats	Execution stats for a batch whose outputs have been synchronized.
ImageContentPart	An image content part of a message.
MessageContent	One part of a chat message: text, an image, or a video.
TextContentPart	A plain-text content part of a message.
TextGenerationInputs	Input parameters for text generation pipeline operations.
TextGenerationRequest	An immutable request for text token generation from a pipeline.
TextGenerationRequestFunction	Represents a function definition for a text generation request.
TextGenerationRequestMessage	A single message in a text generation request conversation.
TextGenerationRequestTool	Represents a tool definition for a text generation request.
VideoContentPart	A video content part of a message.

Audio generation

AudioGenerationInputs	Input data structure for audio generation pipelines.

Embeddings

EmbeddingsContext	Protocol defining the interface for embeddings generation contexts.
EmbeddingsGenerationContextType	The context type an embeddings pipeline serves.
EmbeddingsGenerationInputs	Batched inputs for an embeddings generation pipeline step.
EmbeddingsGenerationOutput	Response structure for embedding generation.

Image generation

PixelGenerationInputs	Input data structure for pixel generation pipelines.