참고소스 수정본

참고/neo4j-graphrag-python-main/examples/customize/build_graph/components/loaders/custom_loader.py

@@ -0,0 +1,27 @@
+"""Create a custom data loader to transform content into text."""
+
+from pathlib import Path
+from typing import Dict, Optional, Union
+
+from fsspec import AbstractFileSystem
+
+from neo4j_graphrag.experimental.components.data_loader import DataLoader
+from neo4j_graphrag.experimental.components.types import DocumentInfo, LoadedDocument
+
+
+class MyLoader(DataLoader):
+    async def run(
+        self,
+        filepath: Union[str, Path],
+        metadata: Optional[Dict[str, str]] = None,
+        fs: Optional[Union[AbstractFileSystem, str]] = None,
+    ) -> LoadedDocument:
+        # Implement logic here; use ``fs`` when reading from non-local storage.
+        _ = fs
+        return LoadedDocument(
+            text="<extracted text>",
+            document_info=DocumentInfo(
+                path=str(filepath),
+                metadata=metadata,
+            ),
+        )

참고/neo4j-graphrag-python-main/examples/customize/build_graph/components/loaders/pdf_loader.py

@@ -0,0 +1,20 @@
+"""Use the PdfLoader component to extract text from a PDF file."""
+
+import asyncio
+from pathlib import Path
+
+from neo4j_graphrag.experimental.components.data_loader import PdfLoader
+
+root_dir = Path(__file__).parents[4]
+file_path = root_dir / "data" / "Harry Potter and the Chamber of Secrets Summary.pdf"
+
+
+async def main() -> None:
+    loader = PdfLoader()
+    document = await loader.run(filepath=file_path)
+    print(document.text[:200])
+    print(document.document_info)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

참고/neo4j-graphrag-python-main/examples/customize/build_graph/components/loaders/pdf_loader_from_url.py

@@ -0,0 +1,17 @@
+"""Use the PdfLoader component to extract text from a remote PDF file."""
+
+import asyncio
+
+from neo4j_graphrag.experimental.components.data_loader import PdfLoader
+
+url = "https://raw.githubusercontent.com/neo4j/neo4j-graphrag-python/c166afc4d5abc56a5686f3da46a97ed7c07da19d/examples/data/Harry%20Potter%20and%20the%20Chamber%20of%20Secrets%20Summary.pdf"
+
+
+async def main() -> None:
+    loader = PdfLoader()
+    document = await loader.run(filepath=url, fs="http")
+    print(document.text[:100])
+
+
+if __name__ == "__main__":
+    asyncio.run(main())