From 8498b336f8b8b84031a497a99b04a29e3bebea60 Mon Sep 17 00:00:00 2001
From: estelle <estelle.scifo@neo4j.com>
Date: Tue, 13 May 2025 09:19:37 +0200
Subject: [PATCH 1/2] Fix issue requiring to install spacy and rapidfuzz even
 if not used

---
 .../experimental/components/resolver.py       | 65 +++++++++++++++----
 1 file changed, 53 insertions(+), 12 deletions(-)

diff --git a/src/neo4j_graphrag/experimental/components/resolver.py b/src/neo4j_graphrag/experimental/components/resolver.py
index ecff8cd0e..6201d1242 100644
--- a/src/neo4j_graphrag/experimental/components/resolver.py
+++ b/src/neo4j_graphrag/experimental/components/resolver.py
@@ -12,18 +12,36 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
+from __future__ import annotations
+
 import abc
 import logging
 from itertools import combinations
-from typing import Any, List, Optional
+from typing import Any, List, Optional, TYPE_CHECKING
+
+
+try:
+    from rapidfuzz import fuzz
+    from rapidfuzz import utils
+
+    IS_RAPIDFUZZ_INSTALLED = True
+except ImportError:
+    IS_RAPIDFUZZ_INSTALLED = False
+
+try:
+    import spacy
+    from spacy.cli.download import download as spacy_download
+    from spacy.language import Language
+    import numpy as np
+
+    IS_SPACY_INSTALLED = True
+except ImportError:
+    IS_SPACY_INSTALLED = False
 
-import numpy as np
-import rapidfuzz.fuzz
-import spacy
-from numpy.typing import NDArray
-from rapidfuzz import utils
-from spacy.cli.download import download as spacy_download
-from spacy.language import Language
+
+if TYPE_CHECKING:
+    import numpy as np
+    from numpy.typing import NDArray
 
 import neo4j
 from neo4j_graphrag.experimental.components.types import ResolutionStats
@@ -334,6 +352,11 @@ def __init__(
         spacy_model: str = "en_core_web_lg",
         neo4j_database: Optional[str] = None,
     ) -> None:
+        if not IS_SPACY_INSTALLED:
+            raise ImportError("""`spacy` python module needs to be installed to use
+            the SpaCySemanticMatchResolver. Install it with:
+            `pip install "neo4j-graphrag[nlp]"`
+            """)
         super().__init__(
             driver,
             filter_query,
@@ -398,6 +421,27 @@ class FuzzyMatchResolver(BasePropertySimilarityResolver):
     and 1.
     """
 
+    def __init__(
+        self,
+        driver: neo4j.Driver,
+        filter_query: Optional[str] = None,
+        resolve_properties: Optional[List[str]] = None,
+        similarity_threshold: float = 0.8,
+        neo4j_database: Optional[str] = None,
+    ) -> None:
+        if not IS_RAPIDFUZZ_INSTALLED:
+            raise ImportError("""`rapidfuzz` python module needs to be installed to use
+            the SpaCySemanticMatchResolver. Install it with:
+            `pip install "neo4j-graphrag[fuzzy-matching]"`
+            """)
+        super().__init__(
+            driver,
+            filter_query,
+            resolve_properties,
+            similarity_threshold,
+            neo4j_database,
+        )
+
     async def run(self) -> ResolutionStats:
         return await super().run()
 
@@ -406,7 +450,4 @@ def compute_similarity(self, text_a: str, text_b: str) -> float:
         # normalize the input strings before the comparison is done (processor=utils.default_process)
         # e.g., lowercase the text, strip whitespace, and remove punctuation
         # normalize the score to the 0..1 range
-        return (
-            rapidfuzz.fuzz.WRatio(text_a, text_b, processor=utils.default_process)
-            / 100.0
-        )
+        return fuzz.WRatio(text_a, text_b, processor=utils.default_process) / 100.0

From 1805bf9f7b5319f79778876760da6c2ce33445b6 Mon Sep 17 00:00:00 2001
From: estelle <estelle.scifo@neo4j.com>
Date: Tue, 13 May 2025 09:28:21 +0200
Subject: [PATCH 2/2] Update CHANGELOG and doc

---
 CHANGELOG.md          | 4 ++++
 docs/source/index.rst | 6 ++----
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8a0533cfa..53c88b143 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,10 @@
 
 ## Next
 
+### Fixed
+
+- Fixed a bug where `spacy` and `rapidfuzz` needed to be installed even if not using the relevant entity resolvers.
+
 ## 1.7.0
 
 ### Added
diff --git a/docs/source/index.rst b/docs/source/index.rst
index d6700ef55..d9bd1749b 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -98,10 +98,8 @@ List of extra dependencies:
     - **pinecone**: store vectors in Pinecone
     - **qdrant**: store vectors in Qdrant
 - **experimental**: experimental features mainly from the Knowledge Graph creation pipelines.
-- nlp:
-   - **spaCy**: load spaCy trained models for nlp pipelines, used by `SpaCySemanticMatchResolver` component from the Knowledge Graph creation pipelines.
-- fuzzy-matching:
-   - **rapidfuzz**: apply fuzzy matching using string similarity, used by `FuzzyMatchResolver` component from the Knowledge Graph creation pipelines.
+- **nlp**: installs spaCy for nlp pipelines, used by `SpaCySemanticMatchResolver` component from the Knowledge Graph creation pipelines.
+- **fuzzy-matching**: installs **rapidfuzz** to fuzzy matching using string similarity, used by `FuzzyMatchResolver` component from the Knowledge Graph creation pipelines.
 
 ********
 Examples