LLM Integration

LLM Models

dashscope.DashScopeMultiModalLLM(name, ...)	DashScope multi-modal LLM.
dashscope.DashScopeTextLLM(name, ...)	DashScope text LLM.
managed.ManagedTextGenLLM(name[, deploy_config])	Managed text LLM by MaxFrame.

Custom Model Configuration

config.ModelDeploymentConfig(*args, **kwargs)

Model deployment configuration for extending MaxFrame with custom models.

framework.InferenceFrameworkEnum(value)

Generate & Embed Functions

ContentPart(*args, **kwargs)
ImageContentType(value)	Content type for image data.
AudioContentType(value)	Content type for audio data.
VideoContentType(value)	Content type for video data.
multi_modal.embed(data, model, input[, ...])	Embed multimodal input with a multimodal embedding model.
multi_modal.generate(data, model[, ...])	Generate text with a multimodal LLM from MaxFrame data.
text.embed(series, model[, dimensions, ...])	Embed text content in a series using a text embedding model.
text.extract(series, model, schema[, ...])	Extract structured information from text content in a series using a language model.
text.generate(data, model, prompt_template)	Generate text using a text language model based on given data and prompt template.
text.translate(series, model, ...[, index])	Translate text content in a series using a language model from source language to target language.