jtibshirani commented on a change in pull request #416: URL: https://github.com/apache/lucene/pull/416#discussion_r758678766
########## File path: lucene/core/src/java/org/apache/lucene/util/hnsw/HnswGraph.java ########## @@ -56,31 +59,50 @@ public final class HnswGraph extends KnnGraphValues { private final int maxConn; + private int numLevels; // the current number of levels in the graph + private int entryNode; // the current graph entry node on the top level - // Each entry lists the top maxConn neighbors of a node. The nodes correspond to vectors added to - // HnswBuilder, and the - // node values are the ordinals of those vectors. - private final List<NeighborArray> graph; + // Nodes by level expressed as the level 0's nodes' ordinals. + // As level 0 contains all nodes, nodesByLevel.get(0) is null. + private final List<int[]> nodesByLevel; + + // graph is a list of graph levels. + // Each level is represented as List<NeighborArray> – nodes' connections on this level. + // Each entry in the list has the top maxConn neighbors of a node. The nodes correspond to vectors + // added to HnswBuilder, and the node values are the ordinals of those vectors. + // Thus, on all levels, neighbors expressed as the level 0's nodes' ordinals. + private final List<List<NeighborArray>> graph; // KnnGraphValues iterator members private int upto; private NeighborArray cur; - HnswGraph(int maxConn) { - graph = new ArrayList<>(); - // Typically with diversity criteria we see nodes not fully occupied; average fanout seems to be - // about 1/2 maxConn. There is some indexing time penalty for under-allocating, but saves RAM - graph.add(new NeighborArray(Math.max(32, maxConn / 4))); + HnswGraph(int maxConn, int levelOfFirstNode) { this.maxConn = maxConn; + this.numLevels = levelOfFirstNode + 1; + this.graph = new ArrayList<>(numLevels); + this.entryNode = 0; + for (int i = 0; i < numLevels; i++) { + graph.add(new ArrayList<>()); + // Typically with diversity criteria we see nodes not fully occupied; + // average fanout seems to be about 1/2 maxConn. + // There is some indexing time penalty for under-allocating, but saves RAM + graph.get(i).add(new NeighborArray(Math.max(32, maxConn / 4))); + } + + this.nodesByLevel = new ArrayList<>(numLevels); + nodesByLevel.add(null); // we don't need this for 0th level, as it contains all nodes + for (int l = 1; l < numLevels; l++) { + nodesByLevel.add(new int[] {0}); + } } /** - * Searches for the nearest neighbors of a query vector. + * Searches HNSW graph for the nearest neighbors of a query vector. * * @param query search query vector * @param topK the number of nodes to be returned - * @param numSeed the size of the queue maintained while searching, and controls the number of - * random entry points to sample + * @param numSeed the size of the queue maintained while searching Review comment: It works for me to have a separate discussion. Maybe at least in this PR we can rename this to `numCandidates`, since the 'seed' naming no longer makes sense? As context, I still think it makes sense to remove the `numCandidates` vs. `k` distinction in `HnswGraph`. The public signature `KnnVectorsReader#search` does not include a notion of "num candidates", so users have no way to even use this distinction. I'd be in favor of removing it from `HnswGraph`, then having a follow-up discussion about whether the vector search APIs should handle `numCandidates` vs `k`. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org