community[minor]: Self query retriever for HANA Cloud Vector Engine (#24494)

Description:

- This PR adds a self query retriever implementation for SAP HANA Cloud
Vector Engine. The retriever supports all operators except for contains.
- Issue: N/A
- Dependencies: no new dependencies added

**Add tests and docs:**
Added integration tests to:
libs/community/tests/unit_tests/query_constructors/test_hanavector.py

**Documentation for self query retriever:**
/docs/integrations/retrievers/self_query/hanavector_self_query.ipynb

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>

libs/community/langchain_community/query_constructors/hanavector.py

@@ -0,0 +1,57 @@
+# HANA Translator/query constructor
+from typing import Dict, Tuple, Union
+
+from langchain_core.structured_query import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+    Visitor,
+)
+
+
+class HanaTranslator(Visitor):
+    """
+    Translate internal query language elements to valid filters params for
+    HANA vectorstore.
+    """
+
+    allowed_operators = [Operator.AND, Operator.OR]
+    """Subset of allowed logical operators."""
+    allowed_comparators = [
+        Comparator.EQ,
+        Comparator.NE,
+        Comparator.GT,
+        Comparator.LT,
+        Comparator.GTE,
+        Comparator.LTE,
+        Comparator.IN,
+        Comparator.NIN,
+        # Comparator.CONTAIN,
+        Comparator.LIKE,
+    ]
+
+    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/community/langchain_community/vectorstores/hanavector.py

@@ -191,7 +191,8 @@ class HanaDB(VectorStore):
                 if column_length is not None and column_length > 0:
                     if rows[0][1] != column_length:
                         raise AttributeError(
-                            f"Column {column_name} has the wrong length: {rows[0][1]}"
+                            f"Column {column_name} has the wrong length: {rows[0][1]} "
+                            f"expected: {column_length}"
                         )
             else:
                 raise AttributeError(f"Column {column_name} does not exist")
@@ -529,10 +530,18 @@ class HanaDB(VectorStore):
                     if special_op in COMPARISONS_TO_SQL:
                         operator = COMPARISONS_TO_SQL[special_op]
                         if isinstance(special_val, bool):
-                            query_tuple.append("true" if filter_value else "false")
+                            query_tuple.append("true" if special_val else "false")
                         elif isinstance(special_val, float):
                             sql_param = "CAST(? as float)"
                             query_tuple.append(special_val)
+                        elif (
+                            isinstance(special_val, dict)
+                            and "type" in special_val
+                            and special_val["type"] == "date"
+                        ):
+                            # Date type
+                            sql_param = "CAST(? as DATE)"
+                            query_tuple.append(special_val["date"])
                         else:
                             query_tuple.append(special_val)
                     # "$between"

libs/community/tests/unit_tests/query_constructors/test_hanavector.py

@@ -0,0 +1,84 @@
+from typing import Dict, Tuple
+
+import pytest as pytest
+from langchain_core.structured_query import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+)
+
+from langchain_community.query_constructors.hanavector import HanaTranslator
+
+DEFAULT_TRANSLATOR = HanaTranslator()
+
+
+def test_visit_comparison() -> None:
+    comp = Comparison(comparator=Comparator.LT, attribute="foo", value=1)
+    expected = {"foo": {"$lt": 1}}
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_operation() -> None:
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.LT, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+            Comparison(comparator=Comparator.GT, attribute="abc", value=2.0),
+        ],
+    )
+    expected = {
+        "$and": [{"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

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

@@ -177,6 +177,16 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
             if isinstance(vectorstore, PGVector):
                 return NewPGVectorTranslator()
 
+        try:
+            # Added in langchain-community==0.2.11
+            from langchain_community.query_constructors.hanavector import HanaTranslator
+            from langchain_community.vectorstores import HanaDB
+        except ImportError:
+            pass
+        else:
+            if isinstance(vectorstore, HanaDB):
+                return HanaTranslator()
+
         raise ValueError(
             f"Self query retriever with Vector Store type {vectorstore.__class__}"
             f" not supported."