GenerationChunk#

class langchain_core.outputs.generation.GenerationChunk[source]#

Bases: Generation

Generation chunk, which can be concatenated with other Generation chunks.

param generation_info: dict[str, Any] | None = None#

Raw response from the provider.

May include things like the reason for finishing or token log probabilities.

param text: str [Required]#

Generated text output.

param type: Literal['Generation'] = 'Generation'#

Type is used exclusively for serialization purposes. Set to “Generation” for this class.

Examples using GenerationChunk

• How to create a custom LLM class