GraphRAG 索引

# Via Poetry
poetry run poe cli --root <data_root> # default config mode
poetry run poe cli --config your_pipeline.yml # custom config mode

# Via Node
yarn run:index --root <data_root> # default config mode
yarn run:index --config your_pipeline.yml # custom config mode

from graphrag.index import run_pipeline
from graphrag.index.config import PipelineWorkflowReference

workflows: list[PipelineWorkflowReference] = [
    PipelineWorkflowReference(
        steps=[
            {
                # built-in verb
                "verb": "derive",  # https://github.com/microsoft/datashaper/blob/main/python/datashaper/datashaper/engine/verbs/derive.py
                "args": {
                    "column1": "col1",  # from above
                    "column2": "col2",  # from above
                    "to": "col_multiplied",  # new column name
                    "operator": "*",  # multiply the two columns
                },
                # Since we're trying to act on the default input, we don't need explicitly to specify an input
            }
        ]
    ),
]

dataset = pd.DataFrame([{"col1": 2, "col2": 4}, {"col1": 5, "col2": 10}])
outputs = []
async for output in await run_pipeline(dataset=dataset, workflows=workflows):
    outputs.append(output)
pipeline_result = outputs[-1]
print(pipeline_result)