Merge branch 'main' into eugene/add_implementations

Author: eyurtsev

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",
 ]

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

poetry.lock

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-postgres"
-version = "0.0.7"
+version = "0.0.9"
 description = "An integration package connecting Postgres and LangChain"
 authors = []
 readme = "README.md"
@@ -11,7 +11,7 @@ license = "MIT"
 "Source Code" = "https://github.com/langchain-ai/langchain-postgres/tree/master/langchain_postgres"
 
 [tool.poetry.dependencies]
-python = "^3.9"
+python = "^3.8.1"
 langchain-core = "^0.2.13"
 psycopg = "^3"
 psycopg-pool = "^3.2.1"

pyproject.toml

@@ -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

tests/unit_tests/query_constructors/__init__.py

@@ -3,6 +3,7 @@
 EXPECTED_ALL = [
     "__version__",
     "PGVector",
+    "PGVectorTranslator",
     "PostgresChatMessageHistory",
 ]