Reranking in Milvus Lite #34408
Unanswered
Pratyush2758
asked this question in
Q&A and General discussion
Replies: 1 comment
-
Hi @Pratyush2758 Milvus Lite is going to support hybrid search API (https://milvus.io/docs/multi-vector-search.md), it should be released within a week. The hybrid search API supports RRF and weighted reranking. If you'd like to use reranker model for reranking, you can do that on the client side after receiving the topK results, e.g. using pymilvus[model] lib https://milvus.io/docs/rerankers-overview.md |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Does Milvus Lite use the reranking strategy or the reranking strategy can be used with the complete Milvus version only?
Beta Was this translation helpful? Give feedback.
All reactions