Changed OnError default to 'CONTINUE' (#167)

* Changed OnError default to 'CONTINUE'

* Fix incorrect docstring description

* Remove text_splitter

Author: willtai

README.md

@@ -65,7 +65,6 @@ kg_builder = SimpleKGPipeline(
     llm=llm,
     driver=driver,
     embedder=OpenAIEmbeddings(),
-    file_path=file_path,
     entities=entities,
     relations=relations,
 )

docs/source/api.rst

@@ -78,16 +78,24 @@ SinglePropertyExactMatchResolver
     :members: run
 
 
-
 .. _pipeline-section:
 
 ********
 Pipeline
 ********
 
+Pipeline
+========
+
 .. autoclass:: neo4j_graphrag.experimental.pipeline.Pipeline
     :members: run, add_component, connect, get_pygraphviz_graph
 
+SimpleKGPipeline
+================
+
+.. autoclass:: neo4j_graphrag.experimental.pipeline.kg_builder.SimpleKGPipeline
+    :members: run_async
+
 
 .. _retrievers-section:
 

src/neo4j_graphrag/experimental/pipeline/kg_builder.py

@@ -81,9 +81,8 @@ class SimpleKGPipeline:
         text_splitter (Optional[Any]): A text splitter component. Defaults to FixedSizeSplitter().
         pdf_loader (Optional[Any]): A PDF loader component. Defaults to PdfLoader().
         kg_writer (Optional[Any]): A knowledge graph writer component. Defaults to Neo4jWriter().
-        on_error (str): Error handling strategy. Defaults to "RAISE". Possible values: "RAISE" or "IGNORE".
+        on_error (str): Error handling strategy. Defaults to "CONTINUE". Possible values: "RAISE" or "CONTINUE".
         perform_entity_resolution (bool): Merge entities with same label and name. Default: True
-        text_splitter (Optional[Any]): A text splitter component. Defaults to FixedSizeSplitter().
         prompt_template (str): A custom prompt template to use for extraction.
     """
 
@@ -99,7 +98,7 @@ def __init__(
         text_splitter: Optional[Any] = None,
         pdf_loader: Optional[Any] = None,
         kg_writer: Optional[Any] = None,
-        on_error: str = "RAISE",
+        on_error: str = "CONTINUE",
         prompt_template: Union[ERExtractionTemplate, str] = ERExtractionTemplate(),
         perform_entity_resolution: bool = True,
     ):