get_query_constructor_prompt#

langchain.chains.query_constructor.base.get_query_constructor_prompt(
document_contents: str,
attribute_info: Sequence[AttributeInfo | dict],
*,
examples: Sequence | None = None,
allowed_comparators: Sequence[Comparator] = (Comparator.EQ, Comparator.NE, Comparator.GT, Comparator.GTE, Comparator.LT, Comparator.LTE, Comparator.CONTAIN, Comparator.LIKE, Comparator.IN, Comparator.NIN),
allowed_operators: Sequence[Operator] = (Operator.AND, Operator.OR, Operator.NOT),
enable_limit: bool = False,
schema_prompt: BasePromptTemplate | None = None,
**kwargs: Any,
) → BasePromptTemplate[source]#

Create query construction prompt.

Parameters:

  • document_contents (str) – The contents of the document to be queried.

  • attribute_info (Sequence[AttributeInfo | dict]) – A list of AttributeInfo objects describing the attributes of the document.

  • examples (Sequence | None) – Optional list of examples to use for the chain.

  • allowed_comparators (Sequence[Comparator]) – Sequence of allowed comparators.

  • allowed_operators (Sequence[Operator]) – Sequence of allowed operators.

  • enable_limit (bool) – Whether to enable the limit operator. Defaults to False.

  • schema_prompt (BasePromptTemplate | None) – Prompt for describing query schema. Should have string input variables allowed_comparators and allowed_operators.

  • kwargs (Any) – Additional named params to pass to FewShotPromptTemplate init.

Returns:

A prompt template that can be used to construct queries.

Return type:

BasePromptTemplate

Examples using get_query_constructor_prompt