from_llm

from_llm(
  cls,
  llm: BaseLanguageModel,
  retriever: BaseRetriever,
  condense_question_prompt: BasePromptTemplate

condense_question_llm

combine_docs_chain_kwargs

Parameters

Name	Type	Description
`llm`*	`BaseLanguageModel`	The default language model to use at every part of this chain (eg in both the question generation and the answering)
`retriever`*	`BaseRetriever`	The retriever to use to fetch relevant documents from.
`condense_question_prompt`	`BasePromptTemplate`	Default:`CONDENSE_QUESTION_PROMPT` The prompt to use to condense the chat history and new question into a standalone question.
`chain_type`	`str`	Default:`'stuff'`
`verbose`	`bool`	Default:`False`
`condense_question_llm`	`BaseLanguageModel \| None`	Default:`None`
`combine_docs_chain_kwargs`	`dict \| None`	Default:`None`
`callbacks`	`Callbacks`	Default:`None`
`kwargs`	`Any`	Default:`{}`

Convenience method to load chain from LLM and retriever.

This provides some logic to create the question_generator chain as well as the combine_docs_chain.

The chain type to use to create the combine_docs_chain, will be sent to load_qa_chain.

Verbosity flag for logging to stdout.

The language model to use for condensing the chat history and new question into a standalone question. If none is provided, will default to llm.

Parameters to pass as kwargs to load_qa_chain when constructing the combine_docs_chain.

Callbacks to pass to all subchains.

Additional parameters to pass when initializing ConversationalRetrievalChain