create_qa_with_structure_chain#

langchain.chains.openai_functions.qa_with_structure.create_qa_with_structure_chain(
llm: BaseLanguageModel,
schema: dict | type[BaseModel],
output_parser: str = 'base',
prompt: PromptTemplate | ChatPromptTemplate | None = None,
verbose: bool = False,
) → LLMChain[source]#

Deprecated since version 0.2.13: This function is deprecated. Refer to this guide on retrieval and question answering with structured responses: https://python.langchain.com/docs/how_to/qa_sources/#structure-sources-in-model-response It will not be removed until langchain==1.0.

Create a question answering chain with structure.

Create a question answering chain that returns an answer with sources based on schema.

Parameters:

  • llm (BaseLanguageModel) – Language model to use for the chain.

  • schema (dict | type[BaseModel]) – Pydantic schema to use for the output.

  • output_parser (str) – Output parser to use. Should be one of pydantic or base. Default to base.

  • prompt (PromptTemplate | ChatPromptTemplate | None) – Optional prompt to use for the chain.

  • verbose (bool) – Whether to run the chain in verbose mode.

Returns:

The question answering chain.

Return type:

LLMChain