ConardLi/easy-dataset 1.3.3

[1.3.3] 2025-5-20

on GitHub

🔧 修复

1. 修复文本块待生成问题筛选失效的问题
2. 修复文本块排序错乱的问题
3. 修复上传文档后不等待接口响应直接刷新业务的问题

⚡ 优化

1. 文本块查询时剔除包含“distill content”的无效文本块

✨ 新功能：后台异步任务

背景：原前端同步执行批量任务易受浏览器并发限制，导致页面卡顿。
优化：将任务迁移至后台异步处理，提升大规模数据操作效率。

1. 支持的异步任务类型

   • 自动提取问题：创建任务后，后台自动批量处理未生成问题的文本块，支持配置并发量。
     

   • 自动生成数据集：后台自动为未生成答案的问题批量生成答案，释放前端资源。
     

2. 交互改进

   • 任务状态图标：右上角显示实时进度，点击查看任务详情、日志及异常处理选项。
     

🔧 Fixes

1. Fixed the issue of invalid filtering for "to-be-generated questions" in text blocks.
2. Resolved the problem of text block sorting chaos.
3. Fixed the issue where the business interface refreshed directly without waiting for the response after document upload.

⚡ Optimizations

1. Excluded invalid text blocks containing "distill content" from text block queries.

✨ New Feature: Background Asynchronous Tasks

Context: Frontend synchronous execution of batch tasks was limited by browser concurrency (typically 6-8 connections), causing page freezes.
Improvement: Migrated tasks to background asynchronous processing for large-scale data operations.

1. Supported Asynchronous Tasks

   • Automatic Question Extraction: After creating a task, the background automatically processes text blocks without generated questions in batches, with configurable concurrency.
   • Automatic Dataset Generation: The background batch-generates answers for questions without answers, freeing up frontend resources.

2. Interaction Enhancements

   • Task Status Icon: A real-time progress indicator (e.g., 🔄) in the top-right corner allows clicking to view task details, logs, and exception handling options.
   • Resilient Processing: Automatic retries for failed tasks, with manual termination or restart support for complex network scenarios.