From 7d0770f30cd01ee6093cadcc2d138019d7b208df Mon Sep 17 00:00:00 2001 From: Milvus-doc-bot Date: Thu, 28 Nov 2024 02:55:25 +0000 Subject: [PATCH] Release new docs to master --- .../site/en/userGuide/schema/sparse_vector.md | 23 ++++++++----------- v2.5.x/yarn.lock | 10 ++++---- 2 files changed, 14 insertions(+), 19 deletions(-) diff --git a/v2.5.x/site/en/userGuide/schema/sparse_vector.md b/v2.5.x/site/en/userGuide/schema/sparse_vector.md index e0062c03c..746c0eb69 100644 --- a/v2.5.x/site/en/userGuide/schema/sparse_vector.md +++ b/v2.5.x/site/en/userGuide/schema/sparse_vector.md @@ -563,17 +563,21 @@ For more information on similarity search parameters, refer to [​Basic ANN Sea When using sparse vectors in Milvus, consider the following limits: -- Currently, only the __IP__ distance metric is supported for sparse vectors. +- Currently, only the __IP__ distance metric is supported for sparse vectors. The high dimensionality of sparse vectors makes L2 and cosine distance impractical. - For sparse vector fields, only the __SPARSE_INVERTED_INDEX__ and __SPARSE_WAND__ index types are supported. -- Currently, [range search](range-search.md), [grouping search](grouping-search.md), and [search iterator](with-iterators.md) are not supported for sparse vectors. +- The data types supported for sparse vectors: -## FAQ + - The dimension part must be an unsigned 32-bit integer; + - The value part can be a non-negative 32-bit floating-point number. + +- Sparse vectors must meet the following requirements for insertion and search: -- __What distance metric is supported for sparse vectors?__ + - At least one value in the vector is non-zero; + - Vector indices are non-negative. - Sparse vectors only support the Inner Product (IP) distance metric due to the high dimensionality of sparse vectors, which makes L2 distance and cosine distance impractical. +## FAQ - __Can you explain the difference between SPARSE_INVERTED_INDEX and SPARSE_WAND, and how do I choose between them?__ @@ -583,10 +587,6 @@ When using sparse vectors in Milvus, consider the following limits: The choice of __drop_ratio_build__ and __drop_ratio_search__ depends on the characteristics of your data and your requirements for search latency/throughput and accuracy. -- __What data types are supported for sparse embeddings?__ - - The dimension part must be an unsigned 32-bit integer, and the value part can be a non-negative 32-bit floating-point number. - - __Can the dimension of a sparse embedding be any discrete value within the uint32 space?__ Yes, with one exception. The dimension of a sparse embedding can be any value in the range of `[0, maximum of uint32)`. This means you cannot use the maximum value of uint32. @@ -598,8 +598,3 @@ When using sparse vectors in Milvus, consider the following limits: - __Is it possible to have both sparse and dense vectors in a single collection?__ Yes, with multiple vector type support, you can create collections with both sparse and dense vector columns and perform hybrid searches on them. - -- __What are the requirements for sparse embeddings to be inserted or searched?__ - - Sparse embeddings must have at least one non-zero value, and vector indices must be non-negative. - diff --git a/v2.5.x/yarn.lock b/v2.5.x/yarn.lock index b2a0815da..a1453c8fa 100644 --- a/v2.5.x/yarn.lock +++ b/v2.5.x/yarn.lock @@ -4,21 +4,21 @@ argparse@^1.0.10: version "1.0.10" - resolved "https://registry.npmjs.org/argparse/-/argparse-1.0.10.tgz" + resolved "https://registry.yarnpkg.com/argparse/-/argparse-1.0.10.tgz#bcd6791ea5ae09725e17e5ad988134cd40b3d911" integrity sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg== dependencies: sprintf-js "~1.0.2" autolinker@^3.11.0: version "3.16.2" - resolved "https://registry.npmjs.org/autolinker/-/autolinker-3.16.2.tgz" + resolved "https://registry.yarnpkg.com/autolinker/-/autolinker-3.16.2.tgz#6bb4f32432fc111b65659336863e653973bfbcc9" integrity sha512-JiYl7j2Z19F9NdTmirENSUUIIL/9MytEWtmzhfmsKPCp9E+G35Y0UNCMoM9tFigxT59qSc8Ml2dlZXOCVTYwuA== dependencies: tslib "^2.3.0" remarkable@^2.0.1: version "2.0.1" - resolved "https://registry.npmjs.org/remarkable/-/remarkable-2.0.1.tgz" + resolved "https://registry.yarnpkg.com/remarkable/-/remarkable-2.0.1.tgz#280ae6627384dfb13d98ee3995627ca550a12f31" integrity sha512-YJyMcOH5lrR+kZdmB0aJJ4+93bEojRZ1HGDn9Eagu6ibg7aVZhc3OWbbShRid+Q5eAfsEqWxpe+g5W5nYNfNiA== dependencies: argparse "^1.0.10" @@ -26,10 +26,10 @@ remarkable@^2.0.1: sprintf-js@~1.0.2: version "1.0.3" - resolved "https://registry.npmjs.org/sprintf-js/-/sprintf-js-1.0.3.tgz" + resolved "https://registry.yarnpkg.com/sprintf-js/-/sprintf-js-1.0.3.tgz#04e6926f662895354f3dd015203633b857297e2c" integrity sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g== tslib@^2.3.0: version "2.6.3" - resolved "https://registry.npmjs.org/tslib/-/tslib-2.6.3.tgz" + resolved "https://registry.yarnpkg.com/tslib/-/tslib-2.6.3.tgz#0438f810ad7a9edcde7a241c3d80db693c8cbfe0" integrity sha512-xNvxJEOUiWPGhUuUdQgAJPKOOJfGnIyKySOc09XkKsgdUV/3E2zvwZYdejjmRgPCgcym1juLH3226yA7sEFJKQ==