langchain.schema.output.LLMResult

class langchain.schema.output.LLMResult(*, generations: List[List[Generation]], llm_output: Optional[dict] = None, run: Optional[List[RunInfo]] = None)

Bases: BaseModel

Class that contains all results for a batched LLM call.

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param generations: List[List[langchain.schema.output.Generation]] [Required]

List of generated outputs. This is a List[List[]] because each input could have multiple candidate generations.

param llm_output: Optional[dict] = None

Arbitrary LLM provider-specific output.

param run: Optional[List[langchain.schema.output.RunInfo]] = None

List of metadata info for model call for each input.

flatten() → List[LLMResult]

Flatten generations into a single list.

Unpack List[List[Generation]] -> List[LLMResult] where each returned LLMResult

contains only a single Generation. If token usage information is available, it is kept only for the LLMResult corresponding to the top-choice Generation, to avoid over-counting of token usage downstream.

Returns

List of LLMResults where each returned LLMResult contains a single

Generation.

Examples using LLMResult

• Async callbacks