From 0c9c386efeb6eea0d096758ce08c87fd44f27035 Mon Sep 17 00:00:00 2001 From: Abdon Pijpelink Date: Fri, 20 Feb 2026 11:00:18 +0100 Subject: [PATCH] Revert "Temporarily remove links (#2159)" This reverts commit 71638beabb402e8a86c7dca3acc35bcd057565d5. --- .../content/documentation/concepts/search-relevance.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/qdrant-landing/content/documentation/concepts/search-relevance.md b/qdrant-landing/content/documentation/concepts/search-relevance.md index 42b7a0249f..efb8889342 100644 --- a/qdrant-landing/content/documentation/concepts/search-relevance.md +++ b/qdrant-landing/content/documentation/concepts/search-relevance.md @@ -191,9 +191,9 @@ To leverage the feedback in search across the entire collection, Qdrant provides {{< code-snippet path="/documentation/headless/snippets/query-points-explore/relevance-feedback-naive/" >}} -Internally, Qdrant combines the feedback list into pairs, based on the relevance scores, and then uses these pairs in a formula that modifies vector space traversal during retrieval (changes the strategy of retrieval). This relevance feedback-based retrieval considers not only the similarity of candidates to the query but also to each feedback pair. +Internally, Qdrant combines the feedback list into pairs, based on the relevance scores, and then uses these pairs in a formula that modifies vector space traversal during retrieval (changes the strategy of retrieval). This relevance feedback-based retrieval considers not only the similarity of candidates to the query but also to each feedback pair. For a more detailed description of how it works, refer to the article [Relevance Feedback in Qdrant](/articles/relevance-feedback). -The `a`, `b`, and `c` parameters of the [`naive` strategy](#naive-strategy) need to be customized for each triplet of retriever, feedback model, and collection. We'll soon publish a Python framework that you can use to adapt these 3 weights to your setup. +The `a`, `b`, and `c` parameters of the [`naive` strategy](#naive-strategy) need to be customized for each triplet of retriever, feedback model, and collection. To get these 3 weights adapted to your setup, use [our open source Python package](https://github.com/qdrant/relevance-feedback).