MongoDBStructuredQueryTranslator#

class langchain_mongodb.retrievers.self_querying.MongoDBStructuredQueryTranslator[source]#

Translator between MongoDB Query API and LangChain’s StructuredQuery.

With Vector Search Indexes, one can index boolean, date, number, objectId, string, and UUID fields to pre-filter your data. Filtering your data is useful to narrow the scope of your semantic search and ensure that not all vectors are considered for comparison. It reduces the number of documents against which to run similarity comparisons, which can decrease query latency and increase the accuracy of search results.

Attributes

allowed_comparators	Available logical operators.
allowed_operators	Allowed operators for the visitor.

Methods

visit_comparison(comparison)	Translate a Comparison.
visit_operation(operation)	Translate an Operation.
visit_structured_query(structured_query)	Translate a StructuredQuery.

visit_comparison(

comparison: Comparison,

) → Dict[source]#

Translate a Comparison.

Parameters:

comparison (Comparison) – Comparison to translate.

Return type:

Dict

visit_operation(

operation: Operation,

) → Dict[source]#

Translate an Operation.

Parameters:

operation (Operation) – Operation to translate.

Return type:

Dict

visit_structured_query(

structured_query: StructuredQuery,

) → Tuple[str, dict][source]#

Translate a StructuredQuery.

Parameters:

structured_query (StructuredQuery) – StructuredQuery to translate.

Return type:

Tuple[str, dict]