From 5cdd9880a9ee3f4e4077d92d4c24eef997a9ed41 Mon Sep 17 00:00:00 2001 From: Philippe Prados Date: Thu, 20 Jun 2024 13:30:17 +0200 Subject: [PATCH 1/3] Add transalor --- langchain_postgres/__init__.py | 2 ++ langchain_postgres/translator.py | 52 ++++++++++++++++++++++++++++++++ 2 files changed, 54 insertions(+) create mode 100644 langchain_postgres/translator.py diff --git a/langchain_postgres/__init__.py b/langchain_postgres/__init__.py index ff5114f1..241c8b89 100644 --- a/langchain_postgres/__init__.py +++ b/langchain_postgres/__init__.py @@ -1,6 +1,7 @@ from importlib import metadata from langchain_postgres.chat_message_histories import PostgresChatMessageHistory +from langchain_postgres.translator import PGVectorTranslator from langchain_postgres.vectorstores import PGVector try: @@ -13,4 +14,5 @@ "__version__", "PostgresChatMessageHistory", "PGVector", + "PGVectorTranslator", ] diff --git a/langchain_postgres/translator.py b/langchain_postgres/translator.py new file mode 100644 index 00000000..83b08771 --- /dev/null +++ b/langchain_postgres/translator.py @@ -0,0 +1,52 @@ +from typing import Dict, Tuple, Union + +from langchain_core.structured_query import ( + Comparator, + Comparison, + Operation, + Operator, + StructuredQuery, + Visitor, +) + + +class PGVectorTranslator(Visitor): + """Translate `PGVector` internal query language elements to valid filters.""" + + allowed_operators = [Operator.AND, Operator.OR] + """Subset of allowed logical operators.""" + allowed_comparators = [ + Comparator.EQ, + Comparator.NE, + Comparator.GT, + Comparator.LT, + Comparator.IN, + Comparator.NIN, + Comparator.CONTAIN, + Comparator.LIKE, + ] + """Subset of allowed logical comparators.""" + + def _format_func(self, func: Union[Operator, Comparator]) -> str: + self._validate_func(func) + return f"${func.value}" + + 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: + return { + comparison.attribute: { + self._format_func(comparison.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 From 1a4993a3818fb8fdf0df85f65a6a3000e5b13c8e Mon Sep 17 00:00:00 2001 From: Philippe Prados Date: Thu, 20 Jun 2024 13:38:52 +0200 Subject: [PATCH 2/3] Fix test imports --- tests/unit_tests/test_imports.py | 1 + 1 file changed, 1 insertion(+) diff --git a/tests/unit_tests/test_imports.py b/tests/unit_tests/test_imports.py index 77cf32a4..4513d181 100644 --- a/tests/unit_tests/test_imports.py +++ b/tests/unit_tests/test_imports.py @@ -3,6 +3,7 @@ EXPECTED_ALL = [ "__version__", "PGVector", + "PGVectorTranslator", "PostgresChatMessageHistory", ] From a3b7a4ae68dc54829b6bc48ea06825f735bbb955 Mon Sep 17 00:00:00 2001 From: Philippe Prados Date: Fri, 21 Jun 2024 09:52:18 +0200 Subject: [PATCH 3/3] Add unit test for PGVectorTranslator --- .../unit_tests/query_constructors/__init__.py | 0 .../query_constructors/test_pgvector.py | 87 +++++++++++++++++++ 2 files changed, 87 insertions(+) create mode 100644 tests/unit_tests/query_constructors/__init__.py create mode 100644 tests/unit_tests/query_constructors/test_pgvector.py diff --git a/tests/unit_tests/query_constructors/__init__.py b/tests/unit_tests/query_constructors/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/tests/unit_tests/query_constructors/test_pgvector.py b/tests/unit_tests/query_constructors/test_pgvector.py new file mode 100644 index 00000000..366c0b25 --- /dev/null +++ b/tests/unit_tests/query_constructors/test_pgvector.py @@ -0,0 +1,87 @@ +from typing import Dict, Tuple + +import pytest as pytest +from langchain_core.structured_query import ( + Comparator, + Comparison, + Operation, + Operator, + StructuredQuery, +) + +from langchain_postgres import PGVectorTranslator + +DEFAULT_TRANSLATOR = PGVectorTranslator() + + +def test_visit_comparison() -> None: + comp = Comparison(comparator=Comparator.LT, attribute="foo", value=1) + expected = {"foo": {"$lt": 1}} + actual = DEFAULT_TRANSLATOR.visit_comparison(comp) + assert expected == actual + + +@pytest.mark.skip("Not implemented") +def test_visit_operation() -> None: + op = Operation( + operator=Operator.AND, + arguments=[ + Comparison(comparator=Comparator.LT, attribute="foo", value=2), + Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"), + Comparison(comparator=Comparator.GT, attribute="abc", value=2.0), + ], + ) + expected = { + "foo": {"$lt": 2}, + "bar": {"$eq": "baz"}, + "abc": {"$gt": 2.0}, + } + actual = DEFAULT_TRANSLATOR.visit_operation(op) + assert expected == actual + + +def test_visit_structured_query() -> None: + query = "What is the capital of France?" + structured_query = StructuredQuery( + query=query, + filter=None, + ) + expected: Tuple[str, Dict] = (query, {}) + actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query) + assert expected == actual + + comp = Comparison(comparator=Comparator.LT, attribute="foo", value=1) + structured_query = StructuredQuery( + query=query, + filter=comp, + ) + expected = (query, {"filter": {"foo": {"$lt": 1}}}) + actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query) + assert expected == actual + + op = Operation( + operator=Operator.AND, + arguments=[ + Comparison(comparator=Comparator.LT, attribute="foo", value=2), + Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"), + Comparison(comparator=Comparator.GT, attribute="abc", value=2.0), + ], + ) + structured_query = StructuredQuery( + query=query, + filter=op, + ) + expected = ( + query, + { + "filter": { + "$and": [ + {"foo": {"$lt": 2}}, + {"bar": {"$eq": "baz"}}, + {"abc": {"$gt": 2.0}}, + ] + } + }, + ) + actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query) + assert expected == actual