참고소스 수정본

참고/neo4j-graphrag-python-main/examples/customize/build_graph/components/resolvers/custom_resolver.py

@@ -0,0 +1,25 @@
+"""The base EntityResolver class does not enforce
+a specific signature for the run method, which makes it very flexible.
+"""
+
+from typing import Any, Optional
+
+import neo4j
+from neo4j_graphrag.experimental.components.resolver import EntityResolver
+from neo4j_graphrag.experimental.components.types import ResolutionStats
+
+
+class MyEntityResolver(EntityResolver):
+    def __init__(
+        self,
+        driver: neo4j.Driver,
+        filter_query: Optional[str] = None,
+    ) -> None:
+        super().__init__(driver, filter_query)
+
+    async def run(self, *args: Any, **kwargs: Any) -> ResolutionStats:
+        # logic here
+        return ResolutionStats(
+            number_of_nodes_to_resolve=0,
+            number_of_created_nodes=0,
+        )

참고/neo4j-graphrag-python-main/examples/customize/build_graph/components/resolvers/fuzzy_match_entity_resolver_pre_filter.py

@@ -0,0 +1,36 @@
+"""The FuzzyMatchResolver merges nodes with same label
+and similar textual properties (by default using the "name" property) based on RapidFuzz
+for string matching.
+
+If the resolution is intended to be applied only on some nodes, for instance nodes that
+belong to a specific document, a "WHERE" query can be added. The only variable in the
+query scope is "entity".
+
+WARNING: this process is destructive, initial nodes are deleted and replaced
+by the resolved ones, but all relationships are kept.
+See apoc.refactor.mergeNodes documentation for more details.
+"""
+
+from neo4j_graphrag.experimental.components.resolver import (
+    FuzzyMatchResolver,
+)
+from neo4j_graphrag.experimental.components.types import ResolutionStats
+
+import neo4j
+
+
+async def main(driver: neo4j.Driver) -> None:
+    resolver = FuzzyMatchResolver(
+        driver,
+        # let's filter all entities that belong to a certain docId
+        filter_query="WHERE (entity)-[:FROM_CHUNK]->(:Chunk)-[:FROM_DOCUMENT]->(doc:"
+        "Document {id = 'docId'}",
+        # optionally, change the properties used for resolution (default is "name")
+        # resolve_properties=["name", "ssn"],
+        # the similarity threshold (default is 0.8)
+        # similarity_threshold=0.9
+        # and the neo4j database where data is updated
+        # neo4j_database="neo4j",
+    )
+    res: ResolutionStats = await resolver.run()
+    print(res)

참고/neo4j-graphrag-python-main/examples/customize/build_graph/components/resolvers/simple_entity_resolver_pre_filter.py

@@ -0,0 +1,36 @@
+"""The SinglePropertyExactMatchResolver merge nodes with same label
+and exact same property value (by default using the "name" property).
+
+If some nodes need to be excluded from the resolution, for instance nodes
+created from a previous run, a "WHERE" query can be added. The only variable
+in the query scope is "entity".
+
+WARNING: this process is destructive, initial nodes are deleted and replaced
+by the resolved ones, but all relationships are kept.
+See apoc.refactor.mergeNodes documentation for more details.
+"""
+
+import neo4j
+from neo4j_graphrag.experimental.components.resolver import (
+    SinglePropertyExactMatchResolver,
+)
+from neo4j_graphrag.experimental.components.types import ResolutionStats
+
+
+async def main(driver: neo4j.Driver) -> None:
+    resolver = SinglePropertyExactMatchResolver(
+        driver,
+        # let's filter out some entities assuming the EntityToExclude label
+        # was manually added to nodes in the db
+        filter_query="WHERE NOT entity:EntityToExclude",
+        # another example: in some cases, we do not want to merge
+        # entities whose name is John Doe because we don't know if it
+        # corresponds to the same real person
+        # filter_query="WHERE entity.name <> 'John Doe'",
+        # optionally, change the property used for resolution (default is "name")
+        # resolve_property="name",
+        # and the neo4j database where data is updated
+        # neo4j_database="neo4j",
+    )
+    res: ResolutionStats = await resolver.run()
+    print(res)

참고/neo4j-graphrag-python-main/examples/customize/build_graph/components/resolvers/spacy_entity_resolver_pre_filter.py

@@ -0,0 +1,37 @@
+"""The SpaCySemanticMatchResolver merges nodes with same label
+and similar textual properties (by default using the "name" property) based on spaCy
+embeddings and cosine similarities of embedding vectors.
+
+If the resolution is intended to be applied only on some nodes, for instance nodes that
+belong to a specific document, a "WHERE" query can be added. The only variable in the
+query scope is "entity".
+
+WARNING: this process is destructive, initial nodes are deleted and replaced
+by the resolved ones, but all relationships are kept.
+See apoc.refactor.mergeNodes documentation for more details.
+"""
+
+import neo4j
+from neo4j_graphrag.experimental.components.resolver import (
+    SpaCySemanticMatchResolver,
+)
+from neo4j_graphrag.experimental.components.types import ResolutionStats
+
+
+async def main(driver: neo4j.Driver) -> None:
+    resolver = SpaCySemanticMatchResolver(
+        driver,
+        # let's filter all entities that belong to a certain docId
+        filter_query="WHERE (entity)-[:FROM_CHUNK]->(:Chunk)-[:FROM_DOCUMENT]->(doc:"
+        "Document {id = 'docId'}",
+        # optionally, change the properties used for resolution (default is "name")
+        # resolve_properties=["name", "ssn"],
+        # the similarity threshold (default is 0.8)
+        # similarity_threshold=0.9
+        # the spaCy trained model (default is "en_core_web_lg")
+        # spacy_model="en_core_web_sm"
+        # and the neo4j database where data is updated
+        # neo4j_database="neo4j",
+    )
+    res: ResolutionStats = await resolver.run()
+    print(res)