Update change log and docs

Author: NathalieCharbel

CHANGELOG.md

@@ -3,6 +3,8 @@
 ## Next
 
 ### Added
+
+- Added optional schema enforcement as a validation layer after entity and relation extraction.
 - Introduced SearchQueryParseError for handling invalid Lucene query strings in HybridRetriever and HybridCypherRetriever.
 
 ## 1.5.0

docs/source/user_guide_kg_builder.rst

@@ -125,7 +125,7 @@ This schema information can be provided to the `SimpleKGBuilder` as demonstrated
         # ...
     )
 
-Prompt Template, Lexical Graph Config and Error Behavior
+Prompt Template, Lexical Graph Config, Schema Enforcement, and Error Behavior
 --------------------------------------------------------
 
 These parameters are part of the `EntityAndRelationExtractor` component.
@@ -138,6 +138,7 @@ They are also accessible via the `SimpleKGPipeline` interface.
         # ...
         prompt_template="",
         lexical_graph_config=my_config,
+        enforce_schema=SchemaEnforcementMode.Strict
         on_error="RAISE",
         # ...
     )
@@ -829,6 +830,38 @@ It can be used in this way:
 
 The LLM to use can be customized, the only constraint is that it obeys the :ref:`LLMInterface <llminterface>`.
 
+Schema Enforcement Behaviour
+---------------
+By default, even if a schema is provided to guide the LLM in the entity and relation extraction, the LLM response is not validated against that schema.
+This behaviour can be changed by using the `enforce_schema` flag in the `LLMEntityRelationExtractor` constructor:
+
+.. code:: python
+
+    from neo4j_graphrag.experimental.components.entity_relation_extractor import LLMEntityRelationExtractor
+    from neo4j_graphrag.experimental.components.types import SchemaEnforcementMode
+
+    extractor = LLMEntityRelationExtractor(
+        # ...
+        enforce_schema=SchemaEnforcementMode.STRICT,
+    )
+    schema = SchemaConfig(
+        entities={"Label": {"name": str}},
+        relations={"REL_TYPE": {}},
+        potential_schema=[("Label", "REL_TYPE", "Label")]
+    )
+
+   #....
+    result = await extractor.run(
+        #...
+        schema=schema
+    )
+
+In this scenario, any extracted node/relation/property that is not part of the provided schema will be pruned.
+Any relation whose start node or end node does not conform to the provided tuple in `potential_schema` will be pruned.
+If a node is left with no properties, it will be also pruned.
+
+Note that if the schema enforcement mode is on but the schema is not provided, no schema enforcement will be applied.
+
 Error Behaviour
 ---------------