langchain.model_laboratory.ModelLaboratory¶

class langchain.model_laboratory.ModelLaboratory(chains: Sequence[Chain], names: Optional[List[str]] = None)[source]¶

Experiment with different models.

Initialize with chains to experiment with.

Parameters

  • chains (Sequence[Chain]) – list of chains to experiment with.

  • names (Optional[List[str]]) –

Methods

__init__(chains[, names])

Initialize with chains to experiment with.

compare(text)

Compare model outputs on an input text.

from_llms(llms[, prompt])

Initialize with LLMs to experiment with and optional prompt.
__init__(chains: Sequence[Chain], names: Optional[List[str]] = None)[source]¶

Initialize with chains to experiment with.

Parameters

  • chains (Sequence[Chain]) – list of chains to experiment with.

  • names (Optional[List[str]]) –

compare(text: str) → None[source]¶

Compare model outputs on an input text.

If a prompt was provided with starting the laboratory, then this text will be fed into the prompt. If no prompt was provided, then the input text is the entire prompt.

Parameters

text (str) – input text to run all models on.

Return type

None

classmethod from_llms(llms: List[BaseLLM], prompt: Optional[PromptTemplate] = None) → ModelLaboratory[source]¶

Initialize with LLMs to experiment with and optional prompt.

Parameters

  • llms (List[BaseLLM]) – list of LLMs to experiment with

  • prompt (Optional[PromptTemplate]) – Optional prompt to use to prompt the LLMs. Defaults to None. If a prompt was provided, it should only have one input variable.

Return type

ModelLaboratory

Examples using ModelLaboratory¶