diff --git a/libs/langchain/langchain/retrievers/self_query/astradb.py b/libs/langchain/langchain/retrievers/self_query/astradb.py new file mode 100644 index 00000000000..0b8d3ab800f --- /dev/null +++ b/libs/langchain/langchain/retrievers/self_query/astradb.py @@ -0,0 +1,70 @@ +"""Logic for converting internal query language to a valid AstraDB query.""" +from typing import Dict, Tuple, Union + +from langchain.chains.query_constructor.ir import ( + Comparator, + Comparison, + Operation, + Operator, + StructuredQuery, + Visitor, +) + +MULTIPLE_ARITY_COMPARATORS = [Comparator.IN, Comparator.NIN] + + +class AstraDBTranslator(Visitor): + """Translate AstraDB internal query language elements to valid filters.""" + + """Subset of allowed logical comparators.""" + allowed_comparators = [ + Comparator.EQ, + Comparator.NE, + Comparator.GT, + Comparator.GTE, + Comparator.LT, + Comparator.LTE, + Comparator.IN, + Comparator.NIN, + ] + + """Subset of allowed logical operators.""" + allowed_operators = [Operator.AND, Operator.OR] + + def _format_func(self, func: Union[Operator, Comparator]) -> str: + self._validate_func(func) + map_dict = { + Operator.AND: "$and", + Operator.OR: "$or", + Comparator.EQ: "$eq", + Comparator.NE: "$ne", + Comparator.GTE: "$gte", + Comparator.LTE: "$lte", + Comparator.LT: "$lt", + Comparator.GT: "$gt", + Comparator.IN: "$in", + Comparator.NIN: "$nin", + } + return map_dict[func] + + def visit_operation(self, operation: Operation) -> Dict: + args = [arg.accept(self) for arg in operation.arguments] + return {self._format_func(operation.operator): args} + + def visit_comparison(self, comparison: Comparison) -> Dict: + if comparison.comparator in MULTIPLE_ARITY_COMPARATORS and not isinstance( + comparison.value, list + ): + comparison.value = [comparison.value] + + comparator = self._format_func(comparison.comparator) + return {comparison.attribute: {comparator: comparison.value}} + + def visit_structured_query( + self, structured_query: StructuredQuery + ) -> Tuple[str, dict]: + if structured_query.filter is None: + kwargs = {} + else: + kwargs = {"filter": structured_query.filter.accept(self)} + return structured_query.query, kwargs diff --git a/libs/langchain/langchain/retrievers/self_query/base.py b/libs/langchain/langchain/retrievers/self_query/base.py index 4a033580b4f..9c6a584a6e1 100644 --- a/libs/langchain/langchain/retrievers/self_query/base.py +++ b/libs/langchain/langchain/retrievers/self_query/base.py @@ -3,6 +3,7 @@ import logging from typing import Any, Dict, List, Optional, Sequence, Tuple, Type, Union from langchain_community.vectorstores import ( + AstraDB, Chroma, DashVector, DeepLake, @@ -33,6 +34,7 @@ from langchain.callbacks.manager import ( from langchain.chains.query_constructor.base import load_query_constructor_runnable from langchain.chains.query_constructor.ir import StructuredQuery, Visitor from langchain.chains.query_constructor.schema import AttributeInfo +from langchain.retrievers.self_query.astradb import AstraDBTranslator from langchain.retrievers.self_query.chroma import ChromaTranslator from langchain.retrievers.self_query.dashvector import DashvectorTranslator from langchain.retrievers.self_query.deeplake import DeepLakeTranslator @@ -55,6 +57,7 @@ logger = logging.getLogger(__name__) def _get_builtin_translator(vectorstore: VectorStore) -> Visitor: """Get the translator class corresponding to the vector store class.""" BUILTIN_TRANSLATORS: Dict[Type[VectorStore], Type[Visitor]] = { + AstraDB: AstraDBTranslator, Pinecone: PineconeTranslator, Chroma: ChromaTranslator, DashVector: DashvectorTranslator, diff --git a/libs/langchain/tests/unit_tests/retrievers/self_query/test_astradb.py b/libs/langchain/tests/unit_tests/retrievers/self_query/test_astradb.py new file mode 100644 index 00000000000..78fc47603a4 --- /dev/null +++ b/libs/langchain/tests/unit_tests/retrievers/self_query/test_astradb.py @@ -0,0 +1,131 @@ +from typing import Dict, Tuple + +from langchain.chains.query_constructor.ir import ( + Comparator, + Comparison, + Operation, + Operator, + StructuredQuery, +) +from langchain.retrievers.self_query.astradb import AstraDBTranslator + +DEFAULT_TRANSLATOR = AstraDBTranslator() + + +def test_visit_comparison_lt() -> None: + comp = Comparison(comparator=Comparator.LT, attribute="qty", value=20) + expected = {"qty": {"$lt": 20}} + actual = DEFAULT_TRANSLATOR.visit_comparison(comp) + assert expected == actual + + +def test_visit_comparison_eq() -> None: + comp = Comparison(comparator=Comparator.EQ, attribute="qty", value=10) + expected = {"qty": {"$eq": 10}} + actual = DEFAULT_TRANSLATOR.visit_comparison(comp) + assert expected == actual + + +def test_visit_comparison_ne() -> None: + comp = Comparison(comparator=Comparator.NE, attribute="name", value="foo") + expected = {"name": {"$ne": "foo"}} + actual = DEFAULT_TRANSLATOR.visit_comparison(comp) + assert expected == actual + + +def test_visit_comparison_in() -> None: + comp = Comparison(comparator=Comparator.IN, attribute="name", value="foo") + expected = {"name": {"$in": ["foo"]}} + actual = DEFAULT_TRANSLATOR.visit_comparison(comp) + assert expected == actual + + +def test_visit_comparison_nin() -> None: + comp = Comparison(comparator=Comparator.NIN, attribute="name", value="foo") + expected = {"name": {"$nin": ["foo"]}} + actual = DEFAULT_TRANSLATOR.visit_comparison(comp) + assert expected == actual + + +def test_visit_operation() -> None: + op = Operation( + operator=Operator.AND, + arguments=[ + Comparison(comparator=Comparator.GTE, attribute="qty", value=10), + Comparison(comparator=Comparator.LTE, attribute="qty", value=20), + Comparison(comparator=Comparator.EQ, attribute="name", value="foo"), + ], + ) + expected = { + "$and": [ + {"qty": {"$gte": 10}}, + {"qty": {"$lte": 20}}, + {"name": {"$eq": "foo"}}, + ] + } + actual = DEFAULT_TRANSLATOR.visit_operation(op) + assert expected == actual + + +def test_visit_structured_query_no_filter() -> None: + query = "What is the capital of France?" + structured_query = StructuredQuery( + query=query, + filter=None, + ) + expected: Tuple[str, Dict] = (query, {}) + actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query) + assert expected == actual + + +def test_visit_structured_query_one_attr() -> None: + query = "What is the capital of France?" + comp = Comparison(comparator=Comparator.IN, attribute="qty", value=[5, 15, 20]) + structured_query = StructuredQuery( + query=query, + filter=comp, + ) + expected = ( + query, + {"filter": {"qty": {"$in": [5, 15, 20]}}}, + ) + actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query) + assert expected == actual + + +def test_visit_structured_query_deep_nesting() -> None: + query = "What is the capital of France?" + op = Operation( + operator=Operator.AND, + arguments=[ + Comparison(comparator=Comparator.EQ, attribute="name", value="foo"), + Operation( + operator=Operator.OR, + arguments=[ + Comparison(comparator=Comparator.GT, attribute="qty", value=6), + Comparison( + comparator=Comparator.NIN, + attribute="tags", + value=["bar", "foo"], + ), + ], + ), + ], + ) + structured_query = StructuredQuery( + query=query, + filter=op, + ) + expected = ( + query, + { + "filter": { + "$and": [ + {"name": {"$eq": "foo"}}, + {"$or": [{"qty": {"$gt": 6}}, {"tags": {"$nin": ["bar", "foo"]}}]}, + ] + } + }, + ) + actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query) + assert expected == actual