feat!: change default fuzziness from AUTO to 0 in OpenSearch retrievers (#3198)

Author: SyedShahmeerAli12

integrations/opensearch/src/haystack_integrations/components/retrievers/opensearch/bm25_retriever.py

@@ -31,7 +31,7 @@ def __init__(
         *,
         document_store: OpenSearchDocumentStore,
         filters: dict[str, Any] | None = None,
-        fuzziness: int | str = "AUTO",
+        fuzziness: int | str = 0,
         top_k: int = 10,
         scale_score: bool = False,
         all_terms_must_match: bool = False,
@@ -49,8 +49,8 @@ def __init__(
             required to transform one word into another. For example, the "fuzziness" between the words
             "wined" and "wind" is 1 because only one edit is needed to match them.
 
-            Use "AUTO" (the default) for automatic adjustment based on term length, which is optimal for
-            most scenarios. For detailed guidance, refer to the
+            Defaults to `0` (exact matching). Use `"AUTO"` for automatic adjustment based on term length.
+            For detailed guidance, refer to the
             [OpenSearch fuzzy query documentation](https://opensearch.org/docs/latest/query-dsl/term/fuzzy/).
         :param top_k: Maximum number of documents to return.
         :param scale_score: If `True`, scales the score of retrieved documents to a range between 0 and 1.

integrations/opensearch/src/haystack_integrations/components/retrievers/opensearch/open_search_hybrid_retriever.py

@@ -93,7 +93,7 @@ def __init__(
         embedder: TextEmbedder,
         # OpenSearchBM25Retriever
         filters_bm25: dict[str, Any] | None = None,
-        fuzziness: int | str = "AUTO",
+        fuzziness: int | str = 0,
         top_k_bm25: int = 10,
         scale_score: bool = False,
         all_terms_must_match: bool = False,

integrations/opensearch/src/haystack_integrations/document_stores/opensearch/document_store.py

@@ -1057,7 +1057,7 @@ def _bm25_retrieval(
         query: str,
         *,
         filters: dict[str, Any] | None = None,
-        fuzziness: int | str = "AUTO",
+        fuzziness: int | str = 0,
         top_k: int = 10,
         scale_score: bool = False,
         all_terms_must_match: bool = False,
@@ -1115,7 +1115,7 @@ async def _bm25_retrieval_async(
         query: str,
         *,
         filters: dict[str, Any] | None = None,
-        fuzziness: str = "AUTO",
+        fuzziness: int | str = 0,
         top_k: int = 10,
         scale_score: bool = False,
         all_terms_must_match: bool = False,

integrations/opensearch/tests/test_bm25_retriever.py

@@ -68,7 +68,7 @@ def test_to_dict(_mock_opensearch_client):
                 "type": "haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore",
             },
             "filters": {},
-            "fuzziness": "AUTO",
+            "fuzziness": 0,
             "top_k": 10,
             "scale_score": False,
             "filter_policy": "replace",
@@ -163,7 +163,7 @@ def test_run():
     mock_store._bm25_retrieval.assert_called_once_with(
         query="some query",
         filters={},
-        fuzziness="AUTO",
+        fuzziness=0,
         top_k=10,
         scale_score=False,
         all_terms_must_match=False,
@@ -183,7 +183,7 @@ async def test_run_async():
     mock_store._bm25_retrieval_async.assert_called_once_with(
         query="some query",
         filters={},
-        fuzziness="AUTO",
+        fuzziness=0,
         top_k=10,
         scale_score=False,
         all_terms_must_match=False,
@@ -359,7 +359,7 @@ def test_run_with_runtime_document_store():
     runtime_store._bm25_retrieval.assert_called_once_with(
         query="some query",
         filters={},
-        fuzziness="AUTO",
+        fuzziness=0,
         top_k=10,
         scale_score=False,
         all_terms_must_match=False,
@@ -390,7 +390,7 @@ async def test_run_async_with_runtime_document_store():
     runtime_store._bm25_retrieval_async.assert_called_once_with(
         query="some query",
         filters={},
-        fuzziness="AUTO",
+        fuzziness=0,
         top_k=10,
         scale_score=False,
         all_terms_must_match=False,

integrations/opensearch/tests/test_open_search_hybrid_retriever.py

@@ -78,7 +78,7 @@ class TestOpenSearchHybridRetriever:
                 },
             },
             "filters_bm25": None,
-            "fuzziness": "AUTO",
+            "fuzziness": 0,
             "top_k_bm25": 10,
             "scale_score": False,
             "all_terms_must_match": False,
@@ -227,7 +227,7 @@ def test_run_with_extra_runtime_params(self, mock_embedder):
             filters={"key": "value"},
             top_k=1,
             all_terms_must_match=False,
-            fuzziness="AUTO",
+            fuzziness=0,
             scale_score=False,
             custom_query=None,
         )
@@ -260,7 +260,7 @@ def test_run_in_pipeline(self, mock_embedder):
             filters={"param_a": "default"},
             top_k=10,
             all_terms_must_match=False,
-            fuzziness="AUTO",
+            fuzziness=0,
             scale_score=False,
             custom_query=None,
         )