community[minor]: Add SelfQueryRetriever support to PGVector (#16991)

- **Description:** Add SelfQueryRetriever support to PGVector
  - **Issue:** -
  - **Dependencies:** -
  - **Twitter handle:** -

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

libs/langchain/langchain/retrievers/self_query/base.py

@@ -12,6 +12,7 @@ from langchain_community.vectorstores import (
     MongoDBAtlasVectorSearch,
     MyScale,
     OpenSearchVectorSearch,
+    PGVector,
     Pinecone,
     Qdrant,
     Redis,
@@ -43,6 +44,7 @@ from langchain.retrievers.self_query.milvus import MilvusTranslator
 from langchain.retrievers.self_query.mongodb_atlas import MongoDBAtlasTranslator
 from langchain.retrievers.self_query.myscale import MyScaleTranslator
 from langchain.retrievers.self_query.opensearch import OpenSearchTranslator
+from langchain.retrievers.self_query.pgvector import PGVectorTranslator
 from langchain.retrievers.self_query.pinecone import PineconeTranslator
 from langchain.retrievers.self_query.qdrant import QdrantTranslator
 from langchain.retrievers.self_query.redis import RedisTranslator
@@ -58,6 +60,7 @@ 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,
+        PGVector: PGVectorTranslator,
         Pinecone: PineconeTranslator,
         Chroma: ChromaTranslator,
         DashVector: DashvectorTranslator,

libs/langchain/langchain/retrievers/self_query/pgvector.py

@@ -0,0 +1,52 @@
+from typing import Dict, Tuple, Union
+
+from langchain.chains.query_constructor.ir 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

libs/langchain/tests/unit_tests/retrievers/self_query/test_pgvector.py

@@ -0,0 +1,87 @@
+from typing import Dict, Tuple
+
+import pytest as pytest
+
+from langchain.chains.query_constructor.ir import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+)
+from langchain.retrievers.self_query.pgvector 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