Multilingual text quality scoring operator - Multilingual text quality assessment based on the E5 model
Input column name | Note |
|---|---|
texts | A column containing the texts to be processed, element type is string |
A column containing text quality scores, element type is float32
If a parameter does not have a default value, it is required
Parameter name | Type | Default value | Description |
|---|---|---|---|
model_path | str | /opt/las/models | Base path where the model files are located. Default value: "/opt/las/models" |
model_name | str | multilingual-e5-small-aligned-quality | Model name. Default value: "multilingual-e5-small-aligned-quality" |
dtype | str | float32 | Model precision. Supports bfloat16, float16, and float32. Default value: "float32" |
batch_size | int | 100 | Batch size. Description: Batch size for model inference. Default value: 100 |
rank | int | 0 | GPU index. Description: Specifies the GPU device index to use. Default value: 0 |
The following code demonstrates how to use daft to run the operator and score multilingual text quality based on the E5 model.
from __future__ import annotations import os import daft from daft import col from daft.las.functions.text.multilingual_text_quality_scorer import MultilingualTextQualityScorer from daft.las.functions.udf import las_udf if __name__ == "__main__": if os.getenv("DAFT_RUNNER", "native") == "ray": import logging import ray def configure_logging(): logging.basicConfig( level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s", datefmt="%Y-%m-%d %H:%M:%S.%s".format(), ) logging.getLogger("tracing.span").setLevel(logging.WARNING) logging.getLogger("daft_io.stats").setLevel(logging.WARNING) logging.getLogger("DaftStatisticsManager").setLevel(logging.WARNING) logging.getLogger("DaftFlotillaScheduler").setLevel(logging.WARNING) logging.getLogger("DaftFlotillaDispatcher").setLevel(logging.WARNING) ray.init(dashboard_host="0.0.0.0", runtime_env={"worker_process_setup_hook": configure_logging}) daft.set_runner_ray() daft.set_execution_config(actor_udf_ready_timeout=600) daft.set_execution_config(min_cpu_per_task=0) samples = { "text": [ "这是一篇关于人工智能技术发展的高质量学术论文,内容详实且具有很强的参考价值。", "これは量子物理学とその現代技術への応用に関するよく書かれた科学論文です。", "이것은 양자물리학과 현대 기술에의 응용에 관한 잘 쓰여진 과학 논문입니다.", None, ] } model_path = os.getenv("MODEL_PATH", "/opt/las/models") model_name = "multilingual-e5-small-aligned-quality" dtype = "float32" batch_size = 100 ds = daft.from_pydict(samples) ds = ds.with_column( "quality_score", las_udf( MultilingualTextQualityScorer, construct_args={ "model_path": model_path, "model_name": model_name, "dtype": dtype, "batch_size": batch_size, "rank": 0, }, num_gpus=1, batch_size=1, concurrency=1, )(col("text")), ) ds.show() # ╭──────────────────────────────────────────────────────────────────────────┬─────────────────────╮ # │ text ┆ quality_score │ # │ --- ┆ --- │ # │ Utf8 ┆ Float32 │ # ╞══════════════════════════════════════════════════════════════════════════╪═════════════════════╡ # │ This is a high-quality academic paper on the development of artificial intelligence technology, with detailed content and strong reference value. ┆ 0.6294931 │ # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤ # │ これは量子物理学とその現代技術への応用に関するよく書かれた科学論文です。 ┆ 0.73835784 │ # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤ # │ 이것은 양자물리학과 현대 기술에의 응용에 관한 잘 쓰여진 과학 논문입니다。 ┆ 0.7729334 │ # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┤ # │ None ┆ None │ # ╰──────────────────────────────────────────────────────────────────────────┴─────────────────────╯