Chain to use to combine results of applying llm_chain to documents.
Variable name in the LLM chain to put the documents in
Ensures that the map step is taken regardless of max tokens
LLM Wrapper to use after formatting documents
The maximum number of iterations to run through the map
The maximum number of tokens before requiring to do the reduction
Optional
memoryReturn the results of the map steps in the output.
Return the string type key uniquely identifying this class of chain.
Protected
_Invoke the chain with the provided input and returns the output.
Input values for the chain run.
Optional
options: anyPromise that resolves with the output of the chain run.
Return a json-like object representing this chain.
Static
deserializeLoad a chain from a json-like object describing it.
Static
lc_
Combine documents by mapping a chain over them, then combining results.