Langchain has documentation on how to add scores to retriever results when similarity_search is used. How to add scores to retriever results | :parrot::link: LangChain But I want to use MMR (Minimal Marginal Relevance), instead of similarity_search. Can someone please point out how I can do that? T…

hi @DLin1 MMR (Maximal Marginal Relevance) is a reranking algorithm that selects items iteratively to balance: relevance to the query, and non-redundancy with already selected items. Formally, at each step it chooses: argmax_i [ λ * sim(query, doc_i) − (1 − λ) * max_j sim(doc_i, doc_j) ] where…

How to add scores to Qdrant vectorstore retriever results when MMR is used?

OSS Product Help LangChain

DLin1 October 8, 2025, 9:50pm 3

Makes sense. Thanks, Pawel.

Topic		Replies	Views
Best way to work with VectorDB in Langchain V1.0 LangChain product-feedback , python-help	1	186	February 20, 2026
Add Qdrant-backed checkpoint saver and memory store (langgraph-checkpoint-qdrant) LangGraph python-help , feature-request	0	59	April 21, 2026
Index and adding documents to qdrant cloud LangChain python-help	1	433	July 28, 2025
Qdrantvectorstore: Support for Multiple Dense Vectors in Qdrant LangSmith Product Help	0	185	September 25, 2025
Help with local RAG pipeline – poor retrieval quality, wrong page numbers LangSmith Product Help python-help	0	53	April 20, 2026

How to add scores to Qdrant vectorstore retriever results when MMR is used?

Related topics