A utility to experiment with and compare the performance of different models.
A sequence of chains to experiment with. Each chain must have exactly one input and one output variable.
Optional list of names corresponding to each chain. If provided, its length must match the number of chains.
Initialize the ModelLaboratory with LLMs and an optional prompt.
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.