User Guide: KG Builder - custom Data Loader inaccurate

[martinohanlon]

The documentation for implementing a custom data loader is out of date:

https://neo4j.com/docs/neo4j-graphrag-python/current/user_guide_kg_builder.html#data-loader

The documentation specifies the following:

from pathlib import Path
from neo4j_graphrag.experimental.components.pdf_loader import DataLoader, PdfDocument

class MyDataLoader(DataLoader):
    async def run(self, path: Path) -> PdfDocument:
        # process file in `path`
        return PdfDocument(text="text")

When using as part of the SimpleKGPipeline, the interface expects filepath and DocumentInfo e.g.

from pathlib import Path
from neo4j_graphrag.experimental.components.pdf_loader import DataLoader, PdfDocument, DocumentInfo

class MyDataLoader(DataLoader):
    async def run(self, filepath: Path) -> PdfDocument:
        # process file in `filepath`
        return PdfDocument(
            text="text",
            document_info=DocumentInfo(
                path=str(filepath),
                metadata={}
            )
        )