Sirui's blog

Language: English | 简体中文

I added AI-assisted Concept suggestions to FLH to reduce the manual effort of reviewing extracted knowledge. The model proposes existing Concepts and explains its choice; the user confirms each item before membership changes. The implementation keeps generated evidence, current state and human authority separate.

My engineering contribution: defining bounded inputs and candidates, designing generation and confirmation as different operations, and hardening their replay, cancellation and stale-state behavior.

发布日期：2026-10-22

语言： English | 简体中文

发布日期：2026-10-22

我为 FLH 加入 AI Concept 建议，降低知识单元整理的手工成本。模型从已有 Concept 中提出候选并说明理由，用户逐项确认后才改变 membership。生成证据、当前状态和人工权威分别管理。

我的工程贡献：定义有界输入与候选，把生成和确认设计为不同操作，并完善重放、取消及过期状态处理。

Language: English | 简体中文

I improved FLH’s daily learning workflow by replacing full review-queue loading with keyset pagination, adding original-text search and direct record navigation, and building a question-intake path that can recover uncertain saves.

Result: on an isolated fixture with 1,543 reviewable units, the initial review response shrank from about 821 KB to 27 KB. The learner can return to a previous unit, find an old question and save a new one without manually constructing JSON.

发布日期：2026-10-21

语言： English | 简体中文

发布日期：2026-10-21

我通过 keyset 分页替代全量审阅队列，加入原文搜索、记录直达和可以恢复未知结果的问题保存流程，改善 FLH 的日常使用。

结果：在 1,543 个可审阅 unit 的隔离 fixture 中，首次响应从约 821 KB 缩减到 27 KB。 学习者能够返回上次审阅位置、找到旧问题，并直接输入新问题。

Language: English | 简体中文

I turned French Learning Hub into a deployable demonstration system by separating the personal workbench from a curated, read-only runtime. The work covered server-enforced access boundaries, precomputed model artifacts, Linux release packaging, browser acceptance, Terraform infrastructure and verified installation on EC2.

My engineering contribution: defining the demo’s runtime and data boundaries, connecting source provenance to release identity, and taking the deployment through an SSM-managed AWS environment with upgrade and rollback procedures.

发布日期：2026-10-20

语言： English | 简体中文

发布日期：2026-10-20

我把 FLH 的个人工作台与精选只读演示分开，完成服务边界、预计算模型 artifact、Linux 打包、浏览器验收、Terraform 基础设施与 EC2 安装验证。

我的工程贡献：定义运行时和数据边界，把源码来源连接到发布身份，并推进 SSM 管理的 AWS 部署、升级与回滚流程。

Language: English | 简体中文

I added an explicit hybrid search mode to French Learning Hub so a learner can find a Concept through both its wording and its meaning, then inspect how that result was retrieved. The implementation combines existing SQLite keyword results with Qdrant semantic results, exposes their evidence in React, and checks the final results against current records.

My engineering contribution: defining a bounded ranking contract, integrating the two production search paths, making the result evidence visible, and driving acceptance through an independent ranking oracle.

发布日期：2026-10-14

语言： English | 简体中文

发布日期：2026-10-14

我为 FLH 加入显式 Hybrid 搜索，让学习者既可以按措辞，也可以按含义找到 Concept，并查看每条结果的检索依据。实现连接 SQLite 关键词搜索与 Qdrant 语义搜索，在 React 中展示证据，并对最终结果回查当前记录。

我的工程贡献：定义有界排序合同、整合生产搜索路径、展示结果依据，并以独立 oracle 推进验收。

Language: English | 简体中文

发布日期：2026-10-12

I added persistent semantic retrieval to FLH, connecting a Windows RTX 4070 embedding service to a Linux NAS through Tailscale. The work covers Qdrant publication, reusable SQLite vector caches, bounded model calls and GPU reproducibility diagnostics.

Engineering focus: AI infrastructure, index consistency and reproducible evaluation.

French Learning Hub (FLH) is my personal French-learning service. I record the
questions I meet while learning, the system extracts knowledge units, and I
organize them into durable Concepts (for example “depuis for something still
going on”). I ran the GPU diagnostic and the
NAS acceptance myself. This article separates four kinds of evidence:

• facts: code and schema;
• author tests: tests the implementing agent ran itself;
• independent tests: acceptance by a different agent;
• human observations: results I executed myself and the agents did not
  re-check.