For the complete documentation index, see llms.txt. This page is also available as Markdown.

languagemodeloutput Kind

LLM / VLM output.

LLM / VLM output

Data representation

External

External data representation is relevant for Workflows clients - it dictates what is the input and output format of data.

Type: str

Internal

Internal data representation is relevant for Workflows blocks creators - this is the type that will be provided by Execution Engine in runtime to the block that consumes input of this kind.

Type: str

Details

This kind represents output generated by language model. It is Python string, which can be processed by blocks transforming LLMs / VLMs output into structured form.

Examples:

{"predicted_class": "car", "confidence": 0.7}  # which is example JSON with classification prediction
"The is A."  # which is example unstructured generation for VQA task 

Last updated

Was this helpful?