You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Improve retrieval quality with reranking layer #204
Currently we rely on vector similarity alone to pick top-k documents. In some cases this returns chunks that are close semantically but not the most useful for answering the query.
A simple improvement would be to introduce a reranking step after retrieval:
expand the candidate pool slightly
rerank using additional signals (e.g. keyword overlap, metadata)
select top-k after reranking
This should improve answer quality without adding much complexity.
I can work on an initial version of this if this direction makes sense.
Hey @Ayush-kathil !
I'd like to work on this improvement.
I explored the current retrieval flow and found search_kubeflow_docs() where Milvus currently returns the top-k results directly. My plan is to expand the retrieval candidate pool, add a lightweight reranking step using semantic similarity + keyword overlap (and potentially metadata signals later), then select the final top-k results after reranking.
Starting with a simple implementation first to keep complexity low.
Activity
Flux07-gezz commentedon May 14, 2026
Hey @Ayush-kathil !
I'd like to work on this improvement.
I explored the current retrieval flow and found
search_kubeflow_docs()where Milvus currently returns the top-k results directly. My plan is to expand the retrieval candidate pool, add a lightweight reranking step using semantic similarity + keyword overlap (and potentially metadata signals later), then select the final top-k results after reranking.Starting with a simple implementation first to keep complexity low.
tanich04 commentedon Jun 4, 2026
hey @Ayush-kathil ,I’d like to work on this.
Proposed first PR scope:
Does this scope sound useful?
chasecadet commentedon Nov 20, 2026
Closing as completed: TEI cross-encoder reranking and extractive context compression shipped on
mainin #262.