Function aexport_data

lightrag/utils.py:3048–3351

Asynchronously exports all entities, relations, and relationships to various formats. Args: chunk_entity_relation_graph: Graph storage instance for entities and relations entities_vdb: Vector database storage for entities relationships_vdb: Vector database storage f

(
    chunk_entity_relation_graph,
    entities_vdb,
    relationships_vdb,
    output_path: str,
    file_format: str = "csv",
    include_vector_data: bool = False,
)

async def aexport_data(
    chunk_entity_relation_graph,
    entities_vdb,
    relationships_vdb,
    output_path: str,
    file_format: str = "csv",
    include_vector_data: bool = False,
) -> None:
    """
    Asynchronously exports all entities, relations, and relationships to various formats.

    Args:
        chunk_entity_relation_graph: Graph storage instance for entities and relations
        entities_vdb: Vector database storage for entities
        relationships_vdb: Vector database storage for relationships
        output_path: The path to the output file (including extension).
        file_format: Output format - "csv", "excel", "md", "txt".
            - csv: Comma-separated values file
            - excel: Microsoft Excel file with multiple sheets
            - md: Markdown tables
            - txt: Plain text formatted output
        include_vector_data: Whether to include data from the vector database.
    """
    # Collect data
    entities_data = []
    relations_data = []
    relationships_data = []

    # --- Entities ---
    all_entities = await chunk_entity_relation_graph.get_all_labels()
    for entity_name in all_entities:
        # Get entity information from graph
        node_data = await chunk_entity_relation_graph.get_node(entity_name)
        source_id = node_data.get("source_id") if node_data else None

        entity_info = {
            "graph_data": node_data,
            "source_id": source_id,
        }

        # Optional: Get vector database information
        if include_vector_data:
            entity_id = compute_mdhash_id(entity_name, prefix="ent-")
            vector_data = await entities_vdb.get_by_id(entity_id)
            entity_info["vector_data"] = vector_data

        entity_row = {
            "entity_name": entity_name,
            "source_id": source_id,
            "graph_data": str(
                entity_info["graph_data"]
            ),  # Convert to string to ensure compatibility
        }
        if include_vector_data and "vector_data" in entity_info:
            entity_row["vector_data"] = str(entity_info["vector_data"])
        entities_data.append(entity_row)

    # --- Relations ---