deploy: dd9cfa3

databases/vectordb/diskann.html

@@ -183,6 +183,10 @@ <h4 id="vamana-graph-construction-algorithm"><a class="header" href="#vamana-gra
 <p>从下图可以看出，第一行使用 α = 1 消除了很多不必要的边，第二行使用 α &gt; 1 将一些所谓的 long-range edges 加回到图中:</p>
 <p><img src="/assets/images/vamana_graph_generation.png" alt="Progression of the graph generated by the Vamana" /></p>
 <p>DiskANN 通过 BeamSearch(设置 beamwidth 一次读多个数据块) 和缓存最常访问的节点（eg. by caching all vertices that are C = 3 or 4 hops from the starting point s）来加速查询。 另外，DiskANN 将邻居节点的向量保存在磁盘索引文件中，来提高搜索的精度（Implicit Re-Ranking Using Full-Precision Vectors）。</p>
+<h3 id="code"><a class="header" href="#code">Code</a></h3>
+<ul>
+<li><a href="https://github.com/microsoft/DiskANN">microsoft/DiskANN</a>, Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search</li>
+</ul>
 <h3 id="further-readings"><a class="header" href="#further-readings">Further readings</a></h3>
 <ul>
 <li><a href="/assets/pdfs/FreshDiskANN_2021.pdf">FreshDiskANN: A Fast and Accurate Graph-Based ANN Index for Streaming Similarity Search</a>, 2021</li>

databases/vectordb/index.html

@@ -188,6 +188,10 @@ <h3 id="misc"><a class="header" href="#misc">Misc</a></h3>
 <li><a href="https://developer.nvidia.com/blog/accelerating-vector-search-using-gpu-powered-indexes-with-rapids-raft/">Accelerating Vector Search: Using GPU-Powered Indexes with RAPIDS RAFT</a></li>
 <li><a href="https://developer.nvidia.com/blog/accelerating-vector-search-fine-tuning-gpu-index-algorithms/">Accelerating Vector Search: Fine-Tuning GPU Index Algorithms</a></li>
 <li><a href="https://developer.nvidia.com/blog/accelerated-vector-search-approximating-with-rapids-raft-ivf-flat/">Accelerated Vector Search: Approximating with RAPIDS RAFT IVF-Flat</a></li>
+<li><a href="https://www.pinecone.io/learn/semantic-search/">Semantic Search: Measuring Meaning From Jaccard to Bert</a></li>
+<li><a href="https://www.pinecone.io/learn/splade/">SPLADE for Sparse Vector Search Explain</a></li>
+<li><a href="https://medium.com/@infiniflowai/sparse-embedding-or-bm25-84c942b3eda7">Sparse embedding or BM25?</a></li>
+<li><a href="https://zilliz.com/blog/unlock-advanced-recommendation-engines-with-milvus-new-range-search">Unlock Advanced Recommendation Engines with Milvus' New Range Search</a></li>
 </ul>
 
                     </main>

print.html

@@ -1167,6 +1167,10 @@ <h3 id="misc"><a class="header" href="#misc">Misc</a></h3>
 <li><a href="https://developer.nvidia.com/blog/accelerating-vector-search-using-gpu-powered-indexes-with-rapids-raft/">Accelerating Vector Search: Using GPU-Powered Indexes with RAPIDS RAFT</a></li>
 <li><a href="https://developer.nvidia.com/blog/accelerating-vector-search-fine-tuning-gpu-index-algorithms/">Accelerating Vector Search: Fine-Tuning GPU Index Algorithms</a></li>
 <li><a href="https://developer.nvidia.com/blog/accelerated-vector-search-approximating-with-rapids-raft-ivf-flat/">Accelerated Vector Search: Approximating with RAPIDS RAFT IVF-Flat</a></li>
+<li><a href="https://www.pinecone.io/learn/semantic-search/">Semantic Search: Measuring Meaning From Jaccard to Bert</a></li>
+<li><a href="https://www.pinecone.io/learn/splade/">SPLADE for Sparse Vector Search Explain</a></li>
+<li><a href="https://medium.com/@infiniflowai/sparse-embedding-or-bm25-84c942b3eda7">Sparse embedding or BM25?</a></li>
+<li><a href="https://zilliz.com/blog/unlock-advanced-recommendation-engines-with-milvus-new-range-search">Unlock Advanced Recommendation Engines with Milvus' New Range Search</a></li>
 </ul>
 <div style="break-before: page; page-break-before: always;"></div><h3 id="a-hrefdatabasesvectordbassetspdfshnsw_160309320pdfefficient-and-robust-approximate-nearest-neighbor-search-using-hierarchical-navigable-small-world-graphsa"><a class="header" href="#a-hrefdatabasesvectordbassetspdfshnsw_160309320pdfefficient-and-robust-approximate-nearest-neighbor-search-using-hierarchical-navigable-small-world-graphsa"><a href="databases/vectordb//assets/pdfs/hnsw_1603.09320.pdf">Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs</a></a></h3>
 <blockquote>
@@ -1254,6 +1258,10 @@ <h4 id="vamana-graph-construction-algorithm"><a class="header" href="#vamana-gra
 <p>从下图可以看出，第一行使用 α = 1 消除了很多不必要的边，第二行使用 α &gt; 1 将一些所谓的 long-range edges 加回到图中:</p>
 <p><img src="databases/vectordb//assets/images/vamana_graph_generation.png" alt="Progression of the graph generated by the Vamana" /></p>
 <p>DiskANN 通过 BeamSearch(设置 beamwidth 一次读多个数据块) 和缓存最常访问的节点（eg. by caching all vertices that are C = 3 or 4 hops from the starting point s）来加速查询。 另外，DiskANN 将邻居节点的向量保存在磁盘索引文件中，来提高搜索的精度（Implicit Re-Ranking Using Full-Precision Vectors）。</p>
+<h3 id="code"><a class="header" href="#code">Code</a></h3>
+<ul>
+<li><a href="https://github.com/microsoft/DiskANN">microsoft/DiskANN</a>, Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search</li>
+</ul>
 <h3 id="further-readings-2"><a class="header" href="#further-readings-2">Further readings</a></h3>
 <ul>
 <li><a href="databases/vectordb//assets/pdfs/FreshDiskANN_2021.pdf">FreshDiskANN: A Fast and Accurate Graph-Based ANN Index for Streaming Similarity Search</a>, 2021</li>