OpenParable
Skip to content
← Back to skills

Naive Grouper

Documents
naive_grouper

Naive Grouper is an Agent Skill for documents published in the cas-bigdatalab/piflow repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

将所有样本分组为一批样品。当用户提到样本合并、合并所有样本、一批分组、全部聚合等需求时使用此skill。 即使用户没有明确说出"合并",只要任务涉及将多个样本合并为单个批次,就应该使用此skill。

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/cas-bigdatalab/piflow/blob/HEAD/workspace/skills/naive_grouper/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/naive-grouper, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Naive Grouper

将所有样本分组为一批样品。

本SKILL使用依赖data_juicer,请在调用前安装好python环境并安装data_juicer,你可用同以下指令进行安装:

pip install py-data-juicer

核心参数

参数类型必填默认值说明
input_pathstring是-输入JSON文件路径
output_pathstring是-输出JSON文件路径

使用方法

python scripts/run_naive_grouper.py --input_path <input_path> --output_path <output_path>

实现原理

参照测试代码 test_naive_grouper.py 中的 _run_helper 函数:

# 1. 将输入列表转换为Dataset
dataset = Dataset.from_list(samples)

# 2. 初始化算子并执行(无需参数)
op = NaiveGrouper()
new_dataset = op.run(dataset)

输入输出格式

输入格式 (JSON数组)

[
  {"text": "Sample 1"},
  {"text": "Sample 2"},
  {"text": "Sample 3"}
]

输出格式 (JSON数组,只有一个元素)

[
  {"text": ["Sample 1", "Sample 2", "Sample 3"]}
]

示例

执行:

python scripts/run_naive_grouper.py --input_path example_input.json --output_path output.json

注意事项

  • 此算子无需额外参数
  • 所有输入样本会被合并为一个批次
  • 合并后的字段值为数组形式