v6: rerank score is never unmarshalled from the search reply
还没有人认领这个 Issue。
评估
- 难度
- 3/5
- 预计耗时
- 1-2 天
- 新手友好度
- 74/100
- Issue 类型
- 缺陷
- 描述清晰度
- 基本清楚
- 活跃度
- 活跃
- 技术栈
- java
调研方向
追踪 client6 API 和内部 ORM 包中的 QueryResponse 反序列化器,从现有的 distance、certainty、score 和 explainScore 读取逻辑开始。检查 QueryMetadata 和 QueryResponseGroup,以及 MetadataResult 和 GroupByResult.rerank。完成的标准是,包含显式存在性处理的 rerank 分数可通过公共对象 API 和分组结果 API 获取。
由索引模型根据 Issue 内容生成。
描述
Summary
The server returns a rerank score per object (and per group for a grouped search), but the client never unmarshals it. A reranked search therefore arrives correctly ordered with the number that produced the order missing, and there is no way to get it through the public API.
Per object
MetadataResult carries both the value and an explicit presence flag:
double rerank_score = 21;
bool rerank_score_present = 22;
but QueryMetadata exposes only four fields:
public final class QueryMetadata extends Record {
public Float distance();
public Float certainty();
public Float score();
public String explainScore();
}
Per group
Same thing on the grouped path. GroupByResult.rerank is a RerankReply { double score = 1; }, while QueryResponseGroup exposes only:
public String name();
public Float minDistance();
public Float maxDistance();
public long numberOfObjects();
public List<QueryObjectGrouped<T>> objects();
The field is never read
Extracting io/weaviate/client6/v1/api/** and io/weaviate/client6/v1/internal/orm/** from client6-6.3.1-all.jar and grepping for rerankScore, getRerankScore and RerankReply returns zero matches. Disassembling the QueryResponse unmarshaller shows it reading getCreationTimeUnix, getLastUpdateTimeUnix, getDistance, getCertainty, getScore and getExplainScore — and nothing else.
The server does populate it
Wrapping the Rpc returned by QueryRequest.rpc(...) and reading MetadataResult off the reply before delegating to the real unmarshal yields real values, correlated by uuid — querying "fish" over a set of animal descriptions with reranker-cohere:
0.781147420 The fish is an aquatic animal that lives ...
0.051658671 The dog is a very popular domestic anima ...
0.050354082 The lion is a wild and majestic animal, ...
The row order matches the score descending, which is exactly the ordering the server applied — so the data is present on the reply and simply discarded.
Impact
Without this, a client cannot show or threshold on the rerank score, or explain the resulting order. The only workaround is to reach into GrpcTransport/QueryRequest internals and re-read the reply, which is not something a consumer should have to do.
Suggested fix
Add a rerankScore component to QueryMetadata (honouring rerank_score_present, since 0.0 is a legitimate score) and read it in the QueryResponse unmarshaller. The same for QueryResponseGroup from GroupByResult.rerank.
Version
- java-client 6.3.1 (also present in 6.3.0)
- Weaviate 1.39.0
- 主要语言
- Java
- 星标
- 34
- 派生
- 30
- PR 合并指标
- 30 天内没有已合并 PR
贡献指南
这个仓库没有索引到贡献指南
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。
weaviate/java-client 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 90/100
weaviate/java-client#621 ·
-
难度 2/5 1-3 小时 新手友好度 84/100
weaviate/java-client#619 ·
-
难度 2/5 1-3 小时 新手友好度 84/100
weaviate/java-client#615 ·
-
难度 2/5 1-3 小时 新手友好度 88/100
weaviate/java-client#607 ·
-
难度 2/5 1-3 小时 新手友好度 82/100
weaviate/java-client#603 ·
查看 weaviate/java-client 的全部 Issue
相似的 Issue
-
documentation
难度 2/5 1-3 小时 新手友好度 65/100
inu-appcenter/memorIN-backend#288 ·
-
难度 2/5 1-3 小时 新手友好度 65/100
-
frontend maui-pilot pilot-ask question
难度 2/5 1-3 小时 新手友好度 75/100
-
难度 2/5 1-3 小时 新手友好度 75/100
-
area/plugin
难度 2/5 1-3 小时 新手友好度 75/100
kestra-io/plugin-kestra#190 ·