1from __future__ import annotations
2
3import os
4
5import daft
6from daft import col
7
8from daft.aihc.common.udf import aihc_udf
9from daft.aihc.functions.doc.doc_convert import DocConvert
10
11if __name__ == "__main__":
12    if os.getenv("DAFT_RUNNER", "native") == "ray":
13        import ray
14        ray.init(dashboard_host="0.0.0.0", ignore_reinit_error=True)
15        daft.set_runner_ray()
16    daft.set_execution_config(actor_udf_ready_timeout=6000, min_cpu_per_task=0)
17
18    # TODO: 根据实际场景准备样本数据
19    samples = {"files": [...]}
20    ds = daft.from_pydict(samples)
21    constructor_kwargs = {
22        "convert_time_out": 60,
23    }
24    ds = ds.with_column(
25        "result",
26        aihc_udf(
27            DocConvert,
28            construct_args=constructor_kwargs,
29            num_cpus=1,
30            concurrency=4,
31            batch_size=8,
32        )(col("files")),
33    )
34    ds.show()