Hacktoberfest 2026:维护者为十月标记出来的 issue,仍然开放、适合新手。 浏览 Hacktoberfest issue

Feed Topic Summary (AI-powered, like X)

未关闭
#2 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
35/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
停滞
技术栈
dart, flutter
领域
ai, mobile

调研方向

Start by reading docs/graphrag.md and tracing how NoteModel.tTags, eTagRefs, and rootEventId are used to fetch and expand notes. Then investigate the Flutter feed/thread views and the on-device Shiv/Gemma integration mentioned in the issue. Done means eligible feeds and threads show a collapsible, streaming summary with regeneration, without a cloud API call.

由索引模型根据 Issue 内容生成。

描述

enhancement

Summary
When multiple notes share the same topic tag (tTag) or are in the same reply thread, show a 2–3 line AI-generated summary at the top of the topic feed or thread view. Powered entirely on-device by Shiv (Gemma via flutter_gemma) — no cloud API call.

Flow

  1. User opens a topic feed (e.g. #bitcoin) or a long reply thread
  2. App fetches top N notes from Isar filtered by tTag or rootEventId
  3. Notes are BFS-expanded via eTagRefs (GraphRAG — see docs/graphrag.md)
  4. Subgraph is verbalized into a prompt and sent to Gemma
  5. Summary streams token-by-token at the top of the feed/thread

User experience

  • Collapsed by default — tap to expand
  • Regenerate button to re-summarize with latest notes
  • Only appears when there are 5+ notes on the same topic

Data layer impact
None. NoteModel.tTags and NoteModel.eTagRefs are already in place for graph traversal.

When to build
Shiv AI phase (last major feature).

主要语言
Dart
星标
2
派生
2
平均合并
1 天 35 分钟
30 天内合并 PR
36

环境准备

  • 没有 Dockerfile 或 Docker Compose 文件
  • 没有 Pull Request 模板
  • 阅读贡献指南

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

basictech01/uniun 的其他 Issue

查看 basictech01/uniun 的全部 Issue

相似的 Issue

更多 Dart Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。