Elasticsearch self-query retriever (#9248)

Now with ElasticsearchStore VectorStore merged, i've added support for
the self-query retriever.

I've added a notebook also to demonstrate capability. I've also added
unit tests.

**Credit**
@elastic and @phoey1 on twitter.

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

@@ -11,6 +11,7 @@ from langchain.chains.query_constructor.ir import StructuredQuery, Visitor
 from langchain.chains.query_constructor.schema import AttributeInfo
 from langchain.retrievers.self_query.chroma import ChromaTranslator
 from langchain.retrievers.self_query.deeplake import DeepLakeTranslator
+from langchain.retrievers.self_query.elasticsearch import ElasticsearchTranslator
 from langchain.retrievers.self_query.myscale import MyScaleTranslator
 from langchain.retrievers.self_query.pinecone import PineconeTranslator
 from langchain.retrievers.self_query.qdrant import QdrantTranslator
@@ -20,6 +21,7 @@ from langchain.schema.language_model import BaseLanguageModel
 from langchain.vectorstores import (
     Chroma,
     DeepLake,
+    ElasticsearchStore,
     MyScale,
     Pinecone,
     Qdrant,
@@ -38,6 +40,7 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
         Qdrant: QdrantTranslator,
         MyScale: MyScaleTranslator,
         DeepLake: DeepLakeTranslator,
+        ElasticsearchStore: ElasticsearchTranslator,
     }
     if vectorstore_cls not in BUILTIN_TRANSLATORS:
         raise ValueError(

libs/langchain/langchain/retrievers/self_query/elasticsearch.py

@@ -0,0 +1,93 @@
+from typing import Dict, Tuple, Union
+
+from langchain.chains.query_constructor.ir import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+    Visitor,
+)
+
+
+class ElasticsearchTranslator(Visitor):
+    """Translate the internal query language elements to valid filters."""
+
+    allowed_comparators = [
+        Comparator.EQ,
+        Comparator.GT,
+        Comparator.GTE,
+        Comparator.LT,
+        Comparator.LTE,
+        Comparator.CONTAIN,
+        Comparator.LIKE,
+    ]
+    """Subset of allowed logical comparators."""
+
+    allowed_operators = [Operator.AND, Operator.OR, Operator.NOT]
+    """Subset of allowed logical operators."""
+
+    def _format_func(self, func: Union[Operator, Comparator]) -> str:
+        self._validate_func(func)
+        map_dict = {
+            Operator.OR: "should",
+            Operator.NOT: "must_not",
+            Operator.AND: "must",
+            Comparator.EQ: "term",
+            Comparator.GT: "gt",
+            Comparator.GTE: "gte",
+            Comparator.LT: "lt",
+            Comparator.LTE: "lte",
+            Comparator.CONTAIN: "match",
+            Comparator.LIKE: "fuzzy",
+        }
+        return map_dict[func]
+
+    def visit_operation(self, operation: Operation) -> Dict:
+        args = [arg.accept(self) for arg in operation.arguments]
+
+        return {"bool": {self._format_func(operation.operator): args}}
+
+    def visit_comparison(self, comparison: Comparison) -> Dict:
+        # ElasticsearchStore filters require to target
+        # the metadata object field
+        field = f"metadata.{comparison.attribute}"
+
+        is_range_comparator = comparison.comparator in [
+            Comparator.GT,
+            Comparator.GTE,
+            Comparator.LT,
+            Comparator.LTE,
+        ]
+
+        if is_range_comparator:
+            return {
+                "range": {
+                    field: {self._format_func(comparison.comparator): comparison.value}
+                }
+            }
+
+        if comparison.comparator == Comparator.LIKE:
+            return {
+                self._format_func(comparison.comparator): {
+                    field: {"value": comparison.value, "fuzziness": "AUTO"}
+                }
+            }
+
+        if comparison.comparator == Comparator.CONTAIN:
+            return {self._format_func(comparison.comparator): {field: comparison.value}}
+
+        # we assume that if the value is a string,
+        # we want to use the keyword field
+        field = f"{field}.keyword" if isinstance(comparison.value, str) else field
+
+        return {self._format_func(comparison.comparator): {field: 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_elasticsearch.py

@@ -0,0 +1,220 @@
+from typing import Dict, Tuple
+
+from langchain.chains.query_constructor.ir import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+)
+from langchain.retrievers.self_query.elasticsearch import ElasticsearchTranslator
+
+DEFAULT_TRANSLATOR = ElasticsearchTranslator()
+
+
+def test_visit_comparison() -> None:
+    comp = Comparison(comparator=Comparator.EQ, attribute="foo", value="1")
+    expected = {"term": {"metadata.foo.keyword": "1"}}
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_comparison_range_gt() -> None:
+    comp = Comparison(comparator=Comparator.GT, attribute="foo", value=1)
+    expected = {"range": {"metadata.foo": {"gt": 1}}}
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_comparison_range_gte() -> None:
+    comp = Comparison(comparator=Comparator.GTE, attribute="foo", value=1)
+    expected = {"range": {"metadata.foo": {"gte": 1}}}
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_comparison_range_lt() -> None:
+    comp = Comparison(comparator=Comparator.LT, attribute="foo", value=1)
+    expected = {"range": {"metadata.foo": {"lt": 1}}}
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_comparison_range_lte() -> None:
+    comp = Comparison(comparator=Comparator.LTE, attribute="foo", value=1)
+    expected = {"range": {"metadata.foo": {"lte": 1}}}
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_comparison_range_match() -> None:
+    comp = Comparison(comparator=Comparator.CONTAIN, attribute="foo", value="1")
+    expected = {"match": {"metadata.foo": "1"}}
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_comparison_range_like() -> None:
+    comp = Comparison(comparator=Comparator.LIKE, attribute="foo", value="bar")
+    expected = {"fuzzy": {"metadata.foo": {"value": "bar", "fuzziness": "AUTO"}}}
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_operation() -> None:
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.EQ, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+        ],
+    )
+    expected = {
+        "bool": {
+            "must": [
+                {"term": {"metadata.foo": 2}},
+                {"term": {"metadata.bar.keyword": "baz"}},
+            ]
+        }
+    }
+    actual = DEFAULT_TRANSLATOR.visit_operation(op)
+    assert expected == actual
+
+
+def test_visit_operation_or() -> None:
+    op = Operation(
+        operator=Operator.OR,
+        arguments=[
+            Comparison(comparator=Comparator.EQ, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+        ],
+    )
+    expected = {
+        "bool": {
+            "should": [
+                {"term": {"metadata.foo": 2}},
+                {"term": {"metadata.bar.keyword": "baz"}},
+            ]
+        }
+    }
+    actual = DEFAULT_TRANSLATOR.visit_operation(op)
+    assert expected == actual
+
+
+def test_visit_operation_not() -> None:
+    op = Operation(
+        operator=Operator.NOT,
+        arguments=[
+            Comparison(comparator=Comparator.EQ, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+        ],
+    )
+    expected = {
+        "bool": {
+            "must_not": [
+                {"term": {"metadata.foo": 2}},
+                {"term": {"metadata.bar.keyword": "baz"}},
+            ]
+        }
+    }
+    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, limit=None)
+    expected: Tuple[str, Dict] = (query, {})
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual
+
+
+def test_visit_structured_query_filter() -> None:
+    query = "What is the capital of France?"
+    comp = Comparison(comparator=Comparator.EQ, attribute="foo", value="1")
+    structured_query = StructuredQuery(query=query, filter=comp, limit=None)
+    expected = (
+        query,
+        {"filter": [{"term": {"metadata.foo.keyword": "1"}}]},
+    )
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual
+
+
+def test_visit_structured_query_filter_and() -> None:
+    query = "What is the capital of France?"
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.EQ, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+        ],
+    )
+    structured_query = StructuredQuery(query=query, filter=op, limit=None)
+    expected = (
+        query,
+        {
+            "filter": [
+                {
+                    "bool": {
+                        "must": [
+                            {"term": {"metadata.foo": 2}},
+                            {"term": {"metadata.bar.keyword": "baz"}},
+                        ]
+                    }
+                }
+            ]
+        },
+    )
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual
+
+
+def test_visit_structured_query_complex() -> None:
+    query = "What is the capital of France?"
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.EQ, attribute="foo", value=2),
+            Operation(
+                operator=Operator.OR,
+                arguments=[
+                    Comparison(comparator=Comparator.LT, attribute="bar", value=1),
+                    Comparison(comparator=Comparator.LIKE, attribute="bar", value="10"),
+                ],
+            ),
+        ],
+    )
+    structured_query = StructuredQuery(query=query, filter=op, limit=None)
+    expected = (
+        query,
+        {
+            "filter": [
+                {
+                    "bool": {
+                        "must": [
+                            {"term": {"metadata.foo": 2}},
+                            {
+                                "bool": {
+                                    "should": [
+                                        {"range": {"metadata.bar": {"lt": 1}}},
+                                        {
+                                            "fuzzy": {
+                                                "metadata.bar": {
+                                                    "value": "10",
+                                                    "fuzziness": "AUTO",
+                                                }
+                                            }
+                                        },
+                                    ]
+                                }
+                            },
+                        ]
+                    }
+                }
+            ]
+        },
+    )
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual