From 80c97b6ac2b6ead2ce5c327233a652a174e71d64 Mon Sep 17 00:00:00 2001 From: generall Date: Thu, 13 Jul 2023 01:45:36 +0200 Subject: [PATCH] properly assign language to snippets --- qdrant-landing/content/articles/quantum-quantization.md | 2 +- qdrant-landing/content/articles/scalar-quantization.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/qdrant-landing/content/articles/quantum-quantization.md b/qdrant-landing/content/articles/quantum-quantization.md index 4231d8259..177f2535c 100644 --- a/qdrant-landing/content/articles/quantum-quantization.md +++ b/qdrant-landing/content/articles/quantum-quantization.md @@ -23,7 +23,7 @@ Quantum quantization is a novel approach that leverages the power of quantum com The conversion of float32 vectors to qbit vectors can be represented by the following formula: -``` +```text qbit_vector = Q( float32_vector ) ``` diff --git a/qdrant-landing/content/articles/scalar-quantization.md b/qdrant-landing/content/articles/scalar-quantization.md index 191fe84ee..ef4b1dabc 100644 --- a/qdrant-landing/content/articles/scalar-quantization.md +++ b/qdrant-landing/content/articles/scalar-quantization.md @@ -29,7 +29,7 @@ So a single number needs 4 bytes of the memory and a 512-dimensional vector occu 2 kB. That's only the memory used to store the vector. There is also an overhead of the HNSW graph, so as a rule of thumb we estimate the memory size with the following formula: -``` +```text memory_size = 1.5 * number_of_vectors * vector_dimension * 4 bytes ```