search/find ranking: generic entities outrank project-specific memories (golden-query baseline)
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
调研方向
Start by tracing the POST /api/v1/search/find ranking path and checking whether configuration already exposes a relevance or category-normalization option; the issue does not name implementation files or tests. Use the reported queries, open-bot deployment and plugin page server, as baseline cases, and compare top results against the open-bot golden-query harness at scripts/ov-eval.ts and scripts/ov-eval.golden.json. Done means project-specific memories rank ahead of unrelated generic entities while sorted and stable result checks still pass.
由索引模型根据 Issue 内容生成。
描述
Summary
Semantic search/find ranking: generic provider entities outrank project-specific memories for project queries. Reporting with a repeatable golden-query baseline from a production open-bot instance (per-user OpenViking sidecar).
Baseline (2026-11-10, POST /api/v1/search/find, limit 5)
Query: open-bot deployment
viking://user/agent/memories/entities/api/openai.md— 0.895 (generic API-provider entity).../entities/promotion/openbot_promotion.md— 0.883viking://user/agent/memories/entities/modele_ia/clef.md— 0.865 (unrelated model entity).../entities/promotion/openbot_promo_video.md— 0.862
Query: plugin page server
.../events/2026/11/04/Chargement des plugins activés.md— 0.829.../events/2026/10/16/Migration et tests du plugin api-connectors.md— 0.828
Hard properties look good: scores are sorted descending and results are stable across repeated identical queries. The gap is relevance ordering: high-centrality generic entities (OpenAI, an unrelated model) beat memories that literally concern the queried project.
Harness
A repeatable golden-query eval lives in open-bot as scripts/ov-eval.ts + scripts/ov-eval.golden.json (records top-5 URIs/scores, latency, sorted/stable checks per query). Happy to extend the golden set or re-run against any candidate fix and share before/after.
Ask
Guidance or ranking work so project/topic-specific memories outrank generic entity pages for specific queries (e.g. lexical/entity-name match boost, or per-category score normalization). If a configuration knob already exists for this, pointing at it closes this just as well.
Related downstream reports (open-bot): shpaw415/open-bot#20, #21, #32, #71, #83.
- 主要语言
- Python
- 星标
- 41.8k
- 派生
- 3.4k
- 平均合并
- 19 小时 29 分钟
- 30 天内合并 PR
- 500
环境准备
- 提供 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
volcengine/OpenViking 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 84/100
volcengine/OpenViking#7485 · 1 条评论 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 80/100
volcengine/OpenViking#7210 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 68/100
volcengine/OpenViking#7205 · 1 条评论 ·
维护者通常 1 天内回复
-
[Bug]: Retrieval rerank fallback statistics stay zero after provider failure可能已有人在做 @97Three 于 8 天前认领。 未关闭bug kernel
难度 2/5 1-3 小时 新手友好度 78/100
volcengine/OpenViking#7014 ·
维护者通常 1 天内回复
-
[Bug]: memory.prefetch_search_topn is inert above 5 (call site omits limit), plus two docstrings state the wrong defaults可能已有人在做 @peterzhang987723 于 8 天前认领。 未关闭kernel
难度 2/5 1-3 小时 新手友好度 70/100
volcengine/OpenViking#6923 · 2 条评论 ·
维护者通常 1 天内回复
查看 volcengine/OpenViking 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 67/100
FinanceFlash/unvibecode#699 ·
维护者通常 1 天内回复
-
enhancement Website
难度 2/5 1-3 小时 新手友好度 78/100
OWASP/OWASP-Hunting#96 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 78/100
micropython/micropython#19942 ·
维护者通常 1 天内回复
-
A rebuild posts "not part of this build" success to the commit's failed `nix-build` gate and effects可能已有人在做 @Padraic-O-Mhuiris 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 78/100
维护者通常 1 天内回复
-
`epoch.Integer` raises a raw OverflowError for integers too large to convert to a float可能已有人在做 @arindam77 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 78/100
pydantic/pydantic-extra-types#479 ·
维护者通常 1 天内回复